1255 files changed, 31680 insertions, 21425 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 7f4af7da3fbc..4fb76c0e8d30 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -511,10 +511,12 @@ Description:	Control Symetric Multi Threading (SMT)
 		control: Read/write interface to control SMT. Possible
 			 values:
 
-			 "on"		SMT is enabled
-			 "off"		SMT is disabled
-			 "forceoff"	SMT is force disabled. Cannot be changed.
-			 "notsupported" SMT is not supported by the CPU
+			 "on"		  SMT is enabled
+			 "off"		  SMT is disabled
+			 "forceoff"	  SMT is force disabled. Cannot be changed.
+			 "notsupported"   SMT is not supported by the CPU
+			 "notimplemented" SMT runtime toggling is not
+					  implemented for the architecture
 
 			 If control status is "forceoff" or "notsupported" writes
 			 are rejected.
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 18f179807563..c30c1957c7e6 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -155,8 +155,7 @@ keeping lock contention under control at all tree levels regardless
 of the level of loading on the system.
 
 </p><p>RCU updaters wait for normal grace periods by registering
-RCU callbacks, either directly via <tt>call_rcu()</tt> and
-friends (namely <tt>call_rcu_bh()</tt> and <tt>call_rcu_sched()</tt>),
+RCU callbacks, either directly via <tt>call_rcu()</tt>
 or indirectly via <tt>synchronize_rcu()</tt> and friends.
 RCU callbacks are represented by <tt>rcu_head</tt> structures,
 which are queued on <tt>rcu_data</tt> structures while they are
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
index 19e7a5fb6b73..57300db4b5ff 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
@@ -56,6 +56,7 @@ sections.
 RCU-preempt Expedited Grace Periods</a></h2>
 
 <p>
+<tt>CONFIG_PREEMPT=y</tt> kernels implement RCU-preempt.
 The overall flow of the handling of a given CPU by an RCU-preempt
 expedited grace period is shown in the following diagram:
 
@@ -139,6 +140,7 @@ or offline, among other things.
 RCU-sched Expedited Grace Periods</a></h2>
 
 <p>
+<tt>CONFIG_PREEMPT=n</tt> kernels implement RCU-sched.
 The overall flow of the handling of a given CPU by an RCU-sched
 expedited grace period is shown in the following diagram:
 
@@ -146,7 +148,7 @@ expedited grace period is shown in the following diagram:
 
 <p>
 As with RCU-preempt, RCU-sched's
-<tt>synchronize_sched_expedited()</tt> ignores offline and
+<tt>synchronize_rcu_expedited()</tt> ignores offline and
 idle CPUs, again because they are in remotely detectable
 quiescent states.
 However, because the
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
index 8d21af02b1f0..c64f8d26609f 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
@@ -34,12 +34,11 @@ Similarly, any code that happens before the beginning of a given RCU grace
 period is guaranteed to see the effects of all accesses following the end
 of that grace period that are within RCU read-side critical sections.
 
-<p>This guarantee is particularly pervasive for <tt>synchronize_sched()</tt>,
-for which RCU-sched read-side critical sections include any region
+<p>Note well that RCU-sched read-side critical sections include any region
 of code for which preemption is disabled.
 Given that each individual machine instruction can be thought of as
 an extremely small region of preemption-disabled code, one can think of
-<tt>synchronize_sched()</tt> as <tt>smp_mb()</tt> on steroids.
+<tt>synchronize_rcu()</tt> as <tt>smp_mb()</tt> on steroids.
 
 <p>RCU updaters use this guarantee by splitting their updates into
 two phases, one of which is executed before the grace period and
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index 687777f83b23..881353fd5bff 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@@ -81,18 +81,19 @@ currently executing on some other CPU.  We therefore cannot free
 up any data structures used by the old NMI handler until execution
 of it completes on all other CPUs.
 
-One way to accomplish this is via synchronize_sched(), perhaps as
+One way to accomplish this is via synchronize_rcu(), perhaps as
 follows:
 
 	unset_nmi_callback();
-	synchronize_sched();
+	synchronize_rcu();
 	kfree(my_nmi_data);
 
-This works because synchronize_sched() blocks until all CPUs complete
-any preemption-disabled segments of code that they were executing.
-Since NMI handlers disable preemption, synchronize_sched() is guaranteed
+This works because (as of v4.20) synchronize_rcu() blocks until all
+CPUs complete any preemption-disabled segments of code that they were
+executing.
+Since NMI handlers disable preemption, synchronize_rcu() is guaranteed
 not to return until all ongoing NMI handlers exit.  It is therefore safe
-to free up the handler's data as soon as synchronize_sched() returns.
+to free up the handler's data as soon as synchronize_rcu() returns.
 
 Important note: for this to work, the architecture in question must
 invoke nmi_enter() and nmi_exit() on NMI entry and exit, respectively.
diff --git a/Documentation/RCU/UP.txt b/Documentation/RCU/UP.txt
index 90ec5341ee98..53bde717017b 100644
--- a/Documentation/RCU/UP.txt
+++ b/Documentation/RCU/UP.txt
@@ -86,10 +86,8 @@ even on a UP system.  So do not do it!  Even on a UP system, the RCU
 infrastructure -must- respect grace periods, and -must- invoke callbacks
 from a known environment in which no locks are held.
 
-It -is- safe for synchronize_sched() and synchronize_rcu_bh() to return
-immediately on an UP system.  It is also safe for synchronize_rcu()
-to return immediately on UP systems, except when running preemptable
-RCU.
+Note that it -is- safe for synchronize_rcu() to return immediately on
+UP systems, including !PREEMPT SMP builds running on UP systems.
 
 Quick Quiz #3: Why can't synchronize_rcu() return immediately on
 	UP systems running preemptable RCU?
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 6f469864d9f5..e98ff261a438 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -182,16 +182,13 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
-	call_rcu_sched(), or call_srcu() is used, the callback function
-	will be called from softirq context.  In particular, it cannot
-	block.
+5.	If call_rcu() or call_srcu() is used, the callback function will
+	be called from softirq context.  In particular, it cannot block.
 
-6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.  The same rule applies for
-	synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
-	synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
-	synchronize_sched_expedite(), and synchronize_srcu_expedited().
+6.	Since synchronize_rcu() can block, it cannot be called
+	from any sort of irq context.  The same rule applies
+	for synchronize_srcu(), synchronize_rcu_expedited(), and
+	synchronize_srcu_expedited().
 
 	The expedited forms of these primitives have the same semantics
 	as the non-expedited forms, but expediting is both expensive and
@@ -212,20 +209,20 @@ over a rather long period of time, but improvements are always welcome!
 	of the system, especially to real-time workloads running on
 	the rest of the system.
 
-7.	If the updater uses call_rcu() or synchronize_rcu(), then the
-	corresponding readers must use rcu_read_lock() and
-	rcu_read_unlock().  If the updater uses call_rcu_bh() or
-	synchronize_rcu_bh(), then the corresponding readers must
-	use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
-	updater uses call_rcu_sched() or synchronize_sched(), then
-	the corresponding readers must disable preemption, possibly
-	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
-	If the updater uses synchronize_srcu() or call_srcu(), then
-	the corresponding readers must use srcu_read_lock() and
+7.	As of v4.20, a given kernel implements only one RCU flavor,
+	which is RCU-sched for PREEMPT=n and RCU-preempt for PREEMPT=y.
+	If the updater uses call_rcu() or synchronize_rcu(),
+	then the corresponding readers my use rcu_read_lock() and
+	rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(),
+	or any pair of primitives that disables and re-enables preemption,
+	for example, rcu_read_lock_sched() and rcu_read_unlock_sched().
+	If the updater uses synchronize_srcu() or call_srcu(),
+	then the corresponding readers must use srcu_read_lock() and
 	srcu_read_unlock(), and with the same srcu_struct.  The rules for
 	the expedited primitives are the same as for their non-expedited
 	counterparts.  Mixing things up will result in confusion and
-	broken kernels.
+	broken kernels, and has even resulted in an exploitable security
+	issue.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -288,8 +285,7 @@ over a rather long period of time, but improvements are always welcome!
 	d.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
 
-	The same cautions apply to call_rcu_bh(), call_rcu_sched(),
-	call_srcu(), and kfree_rcu().
+	The same cautions apply to call_srcu() and kfree_rcu().
 
 	Note that although these primitives do take action to avoid memory
 	exhaustion when any given CPU has too many callbacks, a determined
@@ -322,7 +318,7 @@ over a rather long period of time, but improvements are always welcome!
 
 11.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
-	spin_lock_bh(), etc.  Failing to disable irq on a given
+	spin_lock_bh(), etc.  Failing to disable softirq on a given
 	acquisition of that lock will result in deadlock as soon as
 	the RCU softirq handler happens to run your RCU callback while
 	interrupting that acquisition's critical section.
@@ -335,13 +331,16 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
-	RCU callbacks are -usually- executed on the same CPU that executed
-	the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
-	but are by -no- means guaranteed to be.  For example, if a given
-	CPU goes offline while having an RCU callback pending, then that
-	RCU callback will execute on some surviving CPU.  (If this was
-	not the case, a self-spawning RCU callback would prevent the
-	victim CPU from ever going offline.)
+	Do not assume that RCU callbacks will be executed on the same
+	CPU that executed the corresponding call_rcu() or call_srcu().
+	For example, if a given CPU goes offline while having an RCU
+	callback pending, then that RCU callback will execute on some
+	surviving CPU.	(If this was not the case, a self-spawning RCU
+	callback would prevent the victim CPU from ever going offline.)
+	Furthermore, CPUs designated by rcu_nocbs= might well -always-
+	have their RCU callbacks executed on some other CPUs, in fact,
+	for some  real-time workloads, this is the whole point of using
+	the rcu_nocbs= kernel boot parameter.
 
 13.	Unlike other forms of RCU, it -is- permissible to block in an
 	SRCU read-side critical section (demarked by srcu_read_lock()
@@ -381,11 +380,11 @@ over a rather long period of time, but improvements are always welcome!
 
 	SRCU's expedited primitive (synchronize_srcu_expedited())
 	never sends IPIs to other CPUs, so it is easier on
-	real-time workloads than is synchronize_rcu_expedited(),
-	synchronize_rcu_bh_expedited() or synchronize_sched_expedited().
+	real-time workloads than is synchronize_rcu_expedited().
 
-	Note that rcu_dereference() and rcu_assign_pointer() relate to
-	SRCU just as they do to other forms of RCU.
+	Note that rcu_assign_pointer() relates to SRCU just as it does to
+	other forms of RCU, but instead of rcu_dereference() you should
+	use srcu_dereference() in order to avoid lockdep splats.
 
 14.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before
@@ -405,6 +404,9 @@ over a rather long period of time, but improvements are always welcome!
 	read-side critical sections.  It is the responsibility of the
 	RCU update-side primitives to deal with this.
 
+	For SRCU readers, you can use smp_mb__after_srcu_read_unlock()
+	immediately after an srcu_read_unlock() to get a full barrier.
+
 16.	Use CONFIG_PROVE_LOCKING, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the
 	__rcu sparse checks to validate your RCU code.	These can help
 	find problems as follows:
@@ -428,22 +430,19 @@ over a rather long period of time, but improvements are always welcome!
 	These debugging aids can help you find problems that are
 	otherwise extremely difficult to spot.
 
-17.	If you register a callback using call_rcu(), call_rcu_bh(),
-	call_rcu_sched(), or call_srcu(), and pass in a function defined
-	within a loadable module, then it in necessary to wait for
-	all pending callbacks to be invoked after the last invocation
-	and before unloading that module.  Note that it is absolutely
-	-not- sufficient to wait for a grace period!  The current (say)
-	synchronize_rcu() implementation waits only for all previous
-	callbacks registered on the CPU that synchronize_rcu() is running
-	on, but it is -not- guaranteed to wait for callbacks registered
-	on other CPUs.
+17.	If you register a callback using call_rcu() or call_srcu(), and
+	pass in a function defined within a loadable module, then it in
+	necessary to wait for all pending callbacks to be invoked after
+	the last invocation and before unloading that module.  Note that
+	it is absolutely -not- sufficient to wait for a grace period!
+	The current (say) synchronize_rcu() implementation is -not-
+	guaranteed to wait for callbacks registered on other CPUs.
+	Or even on the current CPU if that CPU recently went offline
+	and came back online.
 
 	You instead need to use one of the barrier functions:
 
 	o	call_rcu() -> rcu_barrier()
-	o	call_rcu_bh() -> rcu_barrier()
-	o	call_rcu_sched() -> rcu_barrier()
 	o	call_srcu() -> srcu_barrier()
 
 	However, these barrier functions are absolutely -not- guaranteed
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 721b3e426515..c818cf65c5a9 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -52,10 +52,10 @@ o	If I am running on a uniprocessor kernel, which can only do one
 o	How can I see where RCU is currently used in the Linux kernel?
 
 	Search for "rcu_read_lock", "rcu_read_unlock", "call_rcu",
-	"rcu_read_lock_bh", "rcu_read_unlock_bh", "call_rcu_bh",
-	"srcu_read_lock", "srcu_read_unlock", "synchronize_rcu",
-	"synchronize_net", "synchronize_srcu", and the other RCU
-	primitives.  Or grab one of the cscope databases from:
+	"rcu_read_lock_bh", "rcu_read_unlock_bh", "srcu_read_lock",
+	"srcu_read_unlock", "synchronize_rcu", "synchronize_net",
+	"synchronize_srcu", and the other RCU primitives.  Or grab one
+	of the cscope databases from:
 
 	http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html
 
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index ab96227bad42..bf699e8cfc75 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -351,3 +351,106 @@ garbage values.
 
 In short, rcu_dereference() is -not- optional when you are going to
 dereference the resulting pointer.
+
+
+WHICH MEMBER OF THE rcu_dereference() FAMILY SHOULD YOU USE?
+
+First, please avoid using rcu_dereference_raw() and also please avoid
+using rcu_dereference_check() and rcu_dereference_protected() with a
+second argument with a constant value of 1 (or true, for that matter).
+With that caution out of the way, here is some guidance for which
+member of the rcu_dereference() to use in various situations:
+
+1.	If the access needs to be within an RCU read-side critical
+	section, use rcu_dereference().  With the new consolidated
+	RCU flavors, an RCU read-side critical section is entered
+	using rcu_read_lock(), anything that disables bottom halves,
+	anything that disables interrupts, or anything that disables
+	preemption.
+
+2.	If the access might be within an RCU read-side critical section
+	on the one hand, or protected by (say) my_lock on the other,
+	use rcu_dereference_check(), for example:
+
+		p1 = rcu_dereference_check(p->rcu_protected_pointer,
+					   lockdep_is_held(&my_lock));
+
+
+3.	If the access might be within an RCU read-side critical section
+	on the one hand, or protected by either my_lock or your_lock on
+	the other, again use rcu_dereference_check(), for example:
+
+		p1 = rcu_dereference_check(p->rcu_protected_pointer,
+					   lockdep_is_held(&my_lock) ||
+					   lockdep_is_held(&your_lock));
+
+4.	If the access is on the update side, so that it is always protected
+	by my_lock, use rcu_dereference_protected():
+
+		p1 = rcu_dereference_protected(p->rcu_protected_pointer,
+					       lockdep_is_held(&my_lock));
+
+	This can be extended to handle multiple locks as in #3 above,
+	and both can be extended to check other conditions as well.
+
+5.	If the protection is supplied by the caller, and is thus unknown
+	to this code, that is the rare case when rcu_dereference_raw()
+	is appropriate.  In addition, rcu_dereference_raw() might be
+	appropriate when the lockdep expression would be excessively
+	complex, except that a better approach in that case might be to
+	take a long hard look at your synchronization design.  Still,
+	there are data-locking cases where any one of a very large number
+	of locks or reference counters suffices to protect the pointer,
+	so rcu_dereference_raw() does have its place.
+
+	However, its place is probably quite a bit smaller than one
+	might expect given the number of uses in the current kernel.
+	Ditto for its synonym, rcu_dereference_check( ... , 1), and
+	its close relative, rcu_dereference_protected(... , 1).
+
+
+SPARSE CHECKING OF RCU-PROTECTED POINTERS
+
+The sparse static-analysis tool checks for direct access to RCU-protected
+pointers, which can result in "interesting" bugs due to compiler
+optimizations involving invented loads and perhaps also load tearing.
+For example, suppose someone mistakenly does something like this:
+
+	p = q->rcu_protected_pointer;
+	do_something_with(p->a);
+	do_something_else_with(p->b);
+
+If register pressure is high, the compiler might optimize "p" out
+of existence, transforming the code to something like this:
+
+	do_something_with(q->rcu_protected_pointer->a);
+	do_something_else_with(q->rcu_protected_pointer->b);
+
+This could fatally disappoint your code if q->rcu_protected_pointer
+changed in the meantime.  Nor is this a theoretical problem:  Exactly
+this sort of bug cost Paul E. McKenney (and several of his innocent
+colleagues) a three-day weekend back in the early 1990s.
+
+Load tearing could of course result in dereferencing a mashup of a pair
+of pointers, which also might fatally disappoint your code.
+
+These problems could have been avoided simply by making the code instead
+read as follows:
+
+	p = rcu_dereference(q->rcu_protected_pointer);
+	do_something_with(p->a);
+	do_something_else_with(p->b);
+
+Unfortunately, these sorts of bugs can be extremely hard to spot during
+review.  This is where the sparse tool comes into play, along with the
+"__rcu" marker.  If you mark a pointer declaration, whether in a structure
+or as a formal parameter, with "__rcu", which tells sparse to complain if
+this pointer is accessed directly.  It will also cause sparse to complain
+if a pointer not marked with "__rcu" is accessed using rcu_dereference()
+and friends.  For example, ->rcu_protected_pointer might be declared as
+follows:
+
+	struct foo __rcu *rcu_protected_pointer;
+
+Use of "__rcu" is opt-in.  If you choose not to use it, then you should
+ignore the sparse warnings.
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index 5d7759071a3e..a2782df69732 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -83,16 +83,15 @@ Pseudo-code using rcu_barrier() is as follows:
    2. Execute rcu_barrier().
    3. Allow the module to be unloaded.
 
-There are also rcu_barrier_bh(), rcu_barrier_sched(), and srcu_barrier()
-functions for the other flavors of RCU, and you of course must match
-the flavor of rcu_barrier() with that of call_rcu().  If your module
-uses multiple flavors of call_rcu(), then it must also use multiple
+There is also an srcu_barrier() function for SRCU, and you of course
+must match the flavor of rcu_barrier() with that of call_rcu().  If your
+module uses multiple flavors of call_rcu(), then it must also use multiple
 flavors of rcu_barrier() when unloading that module.  For example, if
-it uses call_rcu_bh(), call_srcu() on srcu_struct_1, and call_srcu() on
+it uses call_rcu(), call_srcu() on srcu_struct_1, and call_srcu() on
 srcu_struct_2(), then the following three lines of code will be required
 when unloading:
 
- 1 rcu_barrier_bh();
+ 1 rcu_barrier();
  2 srcu_barrier(&srcu_struct_1);
  3 srcu_barrier(&srcu_struct_2);
 
@@ -185,12 +184,12 @@ module invokes call_rcu() from timers, you will need to first cancel all
 the timers, and only then invoke rcu_barrier() to wait for any remaining
 RCU callbacks to complete.
 
-Of course, if you module uses call_rcu_bh(), you will need to invoke
-rcu_barrier_bh() before unloading.  Similarly, if your module uses
-call_rcu_sched(), you will need to invoke rcu_barrier_sched() before
-unloading.  If your module uses call_rcu(), call_rcu_bh(), -and-
-call_rcu_sched(), then you will need to invoke each of rcu_barrier(),
-rcu_barrier_bh(), and rcu_barrier_sched().
+Of course, if you module uses call_rcu(), you will need to invoke
+rcu_barrier() before unloading.  Similarly, if your module uses
+call_srcu(), you will need to invoke srcu_barrier() before unloading,
+and on the same srcu_struct structure.  If your module uses call_rcu()
+-and- call_srcu(), then you will need to invoke rcu_barrier() -and-
+srcu_barrier().
 
 
 Implementing rcu_barrier()
@@ -223,8 +222,8 @@ shown below. Note that the final "1" in on_each_cpu()'s argument list
 ensures that all the calls to rcu_barrier_func() will have completed
 before on_each_cpu() returns. Line 9 then waits for the completion.
 
-This code was rewritten in 2008 to support rcu_barrier_bh() and
-rcu_barrier_sched() in addition to the original rcu_barrier().
+This code was rewritten in 2008 and several times thereafter, but this
+still gives the general idea.
 
 The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
 to post an RCU callback, as follows:
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 1ace20815bb1..981651a8b65d 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -310,7 +310,7 @@ reader, updater, and reclaimer.
 
 
 	    rcu_assign_pointer()
-	    			    +--------+
+	                            +--------+
 	    +---------------------->| reader |---------+
 	    |                       +--------+         |
 	    |                           |              |
@@ -318,12 +318,12 @@ reader, updater, and reclaimer.
 	    |                           |              | rcu_read_lock()
 	    |                           |              | rcu_read_unlock()
 	    |        rcu_dereference()  |              |
-       +---------+                      |              |
-       | updater |<---------------------+              |
-       +---------+                                     V
+	    +---------+                 |              |
+	    | updater |<----------------+              |
+	    +---------+                                V
 	    |                                    +-----------+
 	    +----------------------------------->| reclaimer |
-	    				         +-----------+
+	                                         +-----------+
 	      Defer:
 	      synchronize_rcu() & call_rcu()
 
diff --git a/Documentation/acpi/aml-debugger.txt b/Documentation/acpi/aml-debugger.txt
deleted file mode 100644
index 75ebeb64ab29..000000000000
--- a/Documentation/acpi/aml-debugger.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-The AML Debugger
-
-Copyright (C) 2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
-
-
-This document describes the usage of the AML debugger embedded in the Linux
-kernel.
-
-1. Build the debugger
-
-   The following kernel configuration items are required to enable the AML
-   debugger interface from the Linux kernel:
-
-   CONFIG_ACPI_DEBUGGER=y
-   CONFIG_ACPI_DEBUGGER_USER=m
-
-   The userspace utilities can be built from the kernel source tree using
-   the following commands:
-
-   $ cd tools
-   $ make acpi
-
-   The resultant userspace tool binary is then located at:
-
-     tools/power/acpi/acpidbg
-
-   It can be installed to system directories by running "make install" (as a
-   sufficiently privileged user).
-
-2. Start the userspace debugger interface
-
-   After booting the kernel with the debugger built-in, the debugger can be
-   started by using the following commands:
-
-   # mount -t debugfs none /sys/kernel/debug
-   # modprobe acpi_dbg
-   # tools/power/acpi/acpidbg
-
-   That spawns the interactive AML debugger environment where you can execute
-   debugger commands.
-
-   The commands are documented in the "ACPICA Overview and Programmer Reference"
-   that can be downloaded from
-
-   https://acpica.org/documentation
-
-   The detailed debugger commands reference is located in Chapter 12 "ACPICA
-   Debugger Reference".  The "help" command can be used for a quick reference.
-
-3. Stop the userspace debugger interface
-
-   The interactive debugger interface can be closed by pressing Ctrl+C or using
-   the "quit" or "exit" commands.  When finished, unload the module with:
-
-   # rmmod acpi_dbg
-
-   The module unloading may fail if there is an acpidbg instance running.
-
-4. Run the debugger in a script
-
-   It may be useful to run the AML debugger in a test script. "acpidbg" supports
-   this in a special "batch" mode.  For example, the following command outputs
-   the entire ACPI namespace:
-
-   # acpidbg -b "namespace"
diff --git a/Documentation/acpi/apei/output_format.txt b/Documentation/acpi/apei/output_format.txt
deleted file mode 100644
index 0c49c197c47a..000000000000
--- a/Documentation/acpi/apei/output_format.txt
+++ /dev/null
@@ -1,147 +0,0 @@
-                     APEI output format
-                     ~~~~~~~~~~~~~~~~~~
-
-APEI uses printk as hardware error reporting interface, the output
-format is as follow.
-
-<error record> :=
-APEI generic hardware error status
-severity: <integer>, <severity string>
-section: <integer>, severity: <integer>, <severity string>
-flags: <integer>
-<section flags strings>
-fru_id: <uuid string>
-fru_text: <string>
-section_type: <section type string>
-<section data>
-
-<severity string>* := recoverable | fatal | corrected | info
-
-<section flags strings># :=
-[primary][, containment warning][, reset][, threshold exceeded]\
-[, resource not accessible][, latent error]
-
-<section type string> := generic processor error | memory error | \
-PCIe error | unknown, <uuid string>
-
-<section data> :=
-<generic processor section data> | <memory section data> | \
-<pcie section data> | <null>
-
-<generic processor section data> :=
-[processor_type: <integer>, <proc type string>]
-[processor_isa: <integer>, <proc isa string>]
-[error_type: <integer>
-<proc error type strings>]
-[operation: <integer>, <proc operation string>]
-[flags: <integer>
-<proc flags strings>]
-[level: <integer>]
-[version_info: <integer>]
-[processor_id: <integer>]
-[target_address: <integer>]
-[requestor_id: <integer>]
-[responder_id: <integer>]
-[IP: <integer>]
-
-<proc type string>* := IA32/X64 | IA64
-
-<proc isa string>* := IA32 | IA64 | X64
-
-<processor error type strings># :=
-[cache error][, TLB error][, bus error][, micro-architectural error]
-
-<proc operation string>* := unknown or generic | data read | data write | \
-instruction execution
-
-<proc flags strings># :=
-[restartable][, precise IP][, overflow][, corrected]
-
-<memory section data> :=
-[error_status: <integer>]
-[physical_address: <integer>]
-[physical_address_mask: <integer>]
-[node: <integer>]
-[card: <integer>]
-[module: <integer>]
-[bank: <integer>]
-[device: <integer>]
-[row: <integer>]
-[column: <integer>]
-[bit_position: <integer>]
-[requestor_id: <integer>]
-[responder_id: <integer>]
-[target_id: <integer>]
-[error_type: <integer>, <mem error type string>]
-
-<mem error type string>* :=
-unknown | no error | single-bit ECC | multi-bit ECC | \
-single-symbol chipkill ECC | multi-symbol chipkill ECC | master abort | \
-target abort | parity error | watchdog timeout | invalid address | \
-mirror Broken | memory sparing | scrub corrected error | \
-scrub uncorrected error
-
-<pcie section data> :=
-[port_type: <integer>, <pcie port type string>]
-[version: <integer>.<integer>]
-[command: <integer>, status: <integer>]
-[device_id: <integer>:<integer>:<integer>.<integer>
-slot: <integer>
-secondary_bus: <integer>
-vendor_id: <integer>, device_id: <integer>
-class_code: <integer>]
-[serial number: <integer>, <integer>]
-[bridge: secondary_status: <integer>, control: <integer>]
-[aer_status: <integer>, aer_mask: <integer>
-<aer status string>
-[aer_uncor_severity: <integer>]
-aer_layer=<aer layer string>, aer_agent=<aer agent string>
-aer_tlp_header: <integer> <integer> <integer> <integer>]
-
-<pcie port type string>* := PCIe end point | legacy PCI end point | \
-unknown | unknown | root port | upstream switch port | \
-downstream switch port | PCIe to PCI/PCI-X bridge | \
-PCI/PCI-X to PCIe bridge | root complex integrated endpoint device | \
-root complex event collector
-
-if section severity is fatal or recoverable
-<aer status string># :=
-unknown | unknown | unknown | unknown | Data Link Protocol | \
-unknown | unknown | unknown | unknown | unknown | unknown | unknown | \
-Poisoned TLP | Flow Control Protocol | Completion Timeout | \
-Completer Abort | Unexpected Completion | Receiver Overflow | \
-Malformed TLP | ECRC | Unsupported Request
-else
-<aer status string># :=
-Receiver Error | unknown | unknown | unknown | unknown | unknown | \
-Bad TLP | Bad DLLP | RELAY_NUM Rollover | unknown | unknown | unknown | \
-Replay Timer Timeout | Advisory Non-Fatal
-fi
-
-<aer layer string> :=
-Physical Layer | Data Link Layer | Transaction Layer
-
-<aer agent string> :=
-Receiver ID | Requester ID | Completer ID | Transmitter ID
-
-Where, [] designate corresponding content is optional
-
-All <field string> description with * has the following format:
-
-field: <integer>, <field string>
-
-Where value of <integer> should be the position of "string" in <field
-string> description. Otherwise, <field string> will be "unknown".
-
-All <field strings> description with # has the following format:
-
-field: <integer>
-<field strings>
-
-Where each string in <fields strings> corresponding to one set bit of
-<integer>. The bit position is the position of "string" in <field
-strings> description.
-
-For more detailed explanation of every field, please refer to UEFI
-specification version 2.3 or later, section Appendix N: Common
-Platform Error Record.
diff --git a/Documentation/acpi/i2c-muxes.txt b/Documentation/acpi/i2c-muxes.txt
deleted file mode 100644
index 9fcc4f0b885e..000000000000
--- a/Documentation/acpi/i2c-muxes.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-ACPI I2C Muxes
---------------
-
-Describing an I2C device hierarchy that includes I2C muxes requires an ACPI
-Device () scope per mux channel.
-
-Consider this topology:
-
-+------+   +------+
-| SMB1 |-->| MUX0 |--CH00--> i2c client A (0x50)
-|      |   | 0x70 |--CH01--> i2c client B (0x50)
-+------+   +------+
-
-which corresponds to the following ASL:
-
-Device (SMB1)
-{
-    Name (_HID, ...)
-    Device (MUX0)
-    {
-        Name (_HID, ...)
-        Name (_CRS, ResourceTemplate () {
-            I2cSerialBus (0x70, ControllerInitiated, I2C_SPEED,
-                          AddressingMode7Bit, "^SMB1", 0x00,
-                          ResourceConsumer,,)
-        }
-
-        Device (CH00)
-        {
-            Name (_ADR, 0)
-
-            Device (CLIA)
-            {
-                Name (_HID, ...)
-                Name (_CRS, ResourceTemplate () {
-                    I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                  AddressingMode7Bit, "^CH00", 0x00,
-                                  ResourceConsumer,,)
-                }
-            }
-        }
-
-        Device (CH01)
-        {
-            Name (_ADR, 1)
-
-            Device (CLIB)
-            {
-                Name (_HID, ...)
-                Name (_CRS, ResourceTemplate () {
-                    I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                  AddressingMode7Bit, "^CH01", 0x00,
-                                  ResourceConsumer,,)
-                }
-            }
-        }
-    }
-}
diff --git a/Documentation/acpi/initrd_table_override.txt b/Documentation/acpi/initrd_table_override.txt
deleted file mode 100644
index 30437a6db373..000000000000
--- a/Documentation/acpi/initrd_table_override.txt
+++ /dev/null
@@ -1,111 +0,0 @@
-Upgrading ACPI tables via initrd
-================================
-
-1) Introduction (What is this about)
-2) What is this for
-3) How does it work
-4) References (Where to retrieve userspace tools)
-
-1) What is this about
----------------------
-
-If the ACPI_TABLE_UPGRADE compile option is true, it is possible to
-upgrade the ACPI execution environment that is defined by the ACPI tables
-via upgrading the ACPI tables provided by the BIOS with an instrumented,
-modified, more recent version one, or installing brand new ACPI tables.
-
-When building initrd with kernel in a single image, option
-ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this
-feature to work.
-
-For a full list of ACPI tables that can be upgraded/installed, take a look
-at the char *table_sigs[MAX_ACPI_SIGNATURE]; definition in
-drivers/acpi/tables.c.
-All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
-be overridable, except:
-   - ACPI_SIG_RSDP (has a signature of 6 bytes)
-   - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
-Both could get implemented as well.
-
-
-2) What is this for
--------------------
-
-Complain to your platform/BIOS vendor if you find a bug which is so severe
-that a workaround is not accepted in the Linux kernel. And this facility
-allows you to upgrade the buggy tables before your platform/BIOS vendor
-releases an upgraded BIOS binary.
-
-This facility can be used by platform/BIOS vendors to provide a Linux
-compatible environment without modifying the underlying platform firmware.
-
-This facility also provides a powerful feature to easily debug and test
-ACPI BIOS table compatibility with the Linux kernel by modifying old
-platform provided ACPI tables or inserting new ACPI tables.
-
-It can and should be enabled in any kernel because there is no functional
-change with not instrumented initrds.
-
-
-3) How does it work
--------------------
-
-# Extract the machine's ACPI tables:
-cd /tmp
-acpidump >acpidump
-acpixtract -a acpidump
-# Disassemble, modify and recompile them:
-iasl -d *.dat
-# For example add this statement into a _PRT (PCI Routing Table) function
-# of the DSDT:
-Store("HELLO WORLD", debug)
-# And increase the OEM Revision. For example, before modification:
-DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000000)
-# After modification:
-DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000001)
-iasl -sa dsdt.dsl
-# Add the raw ACPI tables to an uncompressed cpio archive.
-# They must be put into a /kernel/firmware/acpi directory inside the cpio
-# archive. Note that if the table put here matches a platform table
-# (similar Table Signature, and similar OEMID, and similar OEM Table ID)
-# with a more recent OEM Revision, the platform table will be upgraded by
-# this table. If the table put here doesn't match a platform table
-# (dissimilar Table Signature, or dissimilar OEMID, or dissimilar OEM Table
-# ID), this table will be appended.
-mkdir -p kernel/firmware/acpi
-cp dsdt.aml kernel/firmware/acpi
-# A maximum of "NR_ACPI_INITRD_TABLES (64)" tables are currently allowed
-# (see osl.c):
-iasl -sa facp.dsl
-iasl -sa ssdt1.dsl
-cp facp.aml kernel/firmware/acpi
-cp ssdt1.aml kernel/firmware/acpi
-# The uncompressed cpio archive must be the first. Other, typically
-# compressed cpio archives, must be concatenated on top of the uncompressed
-# one. Following command creates the uncompressed cpio archive and
-# concatenates the original initrd on top:
-find kernel | cpio -H newc --create > /boot/instrumented_initrd
-cat /boot/initrd >>/boot/instrumented_initrd
-# reboot with increased acpi debug level, e.g. boot params:
-acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
-# and check your syslog:
-[    1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
-[    1.272091] [ACPI Debug]  String [0x0B] "HELLO WORLD"
-
-iasl is able to disassemble and recompile quite a lot different,
-also static ACPI tables.
-
-
-4) Where to retrieve userspace tools
-------------------------------------
-
-iasl and acpixtract are part of Intel's ACPICA project:
-http://acpica.org/
-and should be packaged by distributions (for example in the acpica package
-on SUSE).
-
-acpidump can be found in Len Browns pmtools:
-ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
-This tool is also part of the acpica package on SUSE.
-Alternatively, used ACPI tables can be retrieved via sysfs in latest kernels:
-/sys/firmware/acpi/tables
diff --git a/Documentation/acpi/method-customizing.txt b/Documentation/acpi/method-customizing.txt
deleted file mode 100644
index 7235da975f23..000000000000
--- a/Documentation/acpi/method-customizing.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-Linux ACPI Custom Control Method How To
-=======================================
-
-Written by Zhang Rui <rui.zhang@intel.com>
-
-
-Linux supports customizing ACPI control methods at runtime.
-
-Users can use this to
-1. override an existing method which may not work correctly,
-   or just for debugging purposes.
-2. insert a completely new method in order to create a missing
-   method such as _OFF, _ON, _STA, _INI, etc.
-For these cases, it is far simpler to dynamically install a single
-control method rather than override the entire DSDT, because kernel
-rebuild/reboot is not needed and test result can be got in minutes.
-
-Note: Only ACPI METHOD can be overridden, any other object types like
-      "Device", "OperationRegion", are not recognized. Methods
-      declared inside scope operators are also not supported.
-Note: The same ACPI control method can be overridden for many times,
-      and it's always the latest one that used by Linux/kernel.
-Note: To get the ACPI debug object output (Store (AAAA, Debug)),
-      please run "echo 1 > /sys/module/acpi/parameters/aml_debug_output".
-
-1. override an existing method
-   a) get the ACPI table via ACPI sysfs I/F. e.g. to get the DSDT,
-      just run "cat /sys/firmware/acpi/tables/DSDT > /tmp/dsdt.dat"
-   b) disassemble the table by running "iasl -d dsdt.dat".
-   c) rewrite the ASL code of the method and save it in a new file,
-   d) package the new file (psr.asl) to an ACPI table format.
-      Here is an example of a customized \_SB._AC._PSR method,
-
-      DefinitionBlock ("", "SSDT", 1, "", "", 0x20080715)
-      {
-	Method (\_SB_.AC._PSR, 0, NotSerialized)
-	{
-		Store ("In AC _PSR", Debug)
-		Return (ACON)
-	}
-      }
-      Note that the full pathname of the method in ACPI namespace
-      should be used.
-   e) assemble the file to generate the AML code of the method.
-      e.g. "iasl -vw 6084 psr.asl" (psr.aml is generated as a result)
-      If parameter "-vw 6084" is not supported by your iASL compiler,
-      please try a newer version.
-   f) mount debugfs by "mount -t debugfs none /sys/kernel/debug"
-   g) override the old method via the debugfs by running
-      "cat /tmp/psr.aml > /sys/kernel/debug/acpi/custom_method"
-
-2. insert a new method
-   This is easier than overriding an existing method.
-   We just need to create the ASL code of the method we want to
-   insert and then follow the step c) ~ g) in section 1.
-
-3. undo your changes
-   The "undo" operation is not supported for a new inserted method
-   right now, i.e. we can not remove a method currently.
-   For an overridden method, in order to undo your changes, please
-   save a copy of the method original ASL code in step c) section 1,
-   and redo step c) ~ g) to override the method with the original one.
-
-
-Note: We can use a kernel with multiple custom ACPI method running,
-      But each individual write to debugfs can implement a SINGLE
-      method override. i.e. if we want to insert/override multiple
-      ACPI methods, we need to redo step c) ~ g) for multiple times.
-
-Note: Be aware that root can mis-use this driver to modify arbitrary
-      memory and gain additional rights, if root's privileges got
-      restricted (for example if root is not allowed to load additional
-      modules after boot).
diff --git a/Documentation/acpi/method-tracing.txt b/Documentation/acpi/method-tracing.txt
deleted file mode 100644
index 0aba14c8f459..000000000000
--- a/Documentation/acpi/method-tracing.txt
+++ /dev/null
@@ -1,192 +0,0 @@
-ACPICA Trace Facility
-
-Copyright (C) 2015, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
-
-
-Abstract:
-
-This document describes the functions and the interfaces of the method
-tracing facility.
-
-1. Functionalities and usage examples:
-
-   ACPICA provides method tracing capability. And two functions are
-   currently implemented using this capability.
-
-   A. Log reducer
-   ACPICA subsystem provides debugging outputs when CONFIG_ACPI_DEBUG is
-   enabled. The debugging messages which are deployed via
-   ACPI_DEBUG_PRINT() macro can be reduced at 2 levels - per-component
-   level (known as debug layer, configured via
-   /sys/module/acpi/parameters/debug_layer) and per-type level (known as
-   debug level, configured via /sys/module/acpi/parameters/debug_level).
-
-   But when the particular layer/level is applied to the control method
-   evaluations, the quantity of the debugging outputs may still be too
-   large to be put into the kernel log buffer. The idea thus is worked out
-   to only enable the particular debug layer/level (normally more detailed)
-   logs when the control method evaluation is started, and disable the
-   detailed logging when the control method evaluation is stopped.
-
-   The following command examples illustrate the usage of the "log reducer"
-   functionality:
-   a. Filter out the debug layer/level matched logs when control methods
-      are being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "enable" > trace_state
-   b. Filter out the debug layer/level matched logs when the specified
-      control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method" > /sys/module/acpi/parameters/trace_state
-   c. Filter out the debug layer/level matched logs when the specified
-      control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method-once" > /sys/module/acpi/parameters/trace_state
-   Where:
-      0xXXXXXXXX/0xYYYYYYYY: Refer to Documentation/acpi/debug.txt for
-			     possible debug layer/level masking values.
-      \PPPP.AAAA.TTTT.HHHH: Full path of a control method that can be found
-			    in the ACPI namespace. It needn't be an entry
-			    of a control method evaluation.
-
-   B. AML tracer
-
-   There are special log entries added by the method tracing facility at
-   the "trace points" the AML interpreter starts/stops to execute a control
-   method, or an AML opcode. Note that the format of the log entries are
-   subject to change:
-     [    0.186427]   exdebug-0398 ex_trace_point        : Method Begin [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
-     [    0.186630]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905c88:If] execution.
-     [    0.186820]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:LEqual] execution.
-     [    0.187010]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905a20:-NamePath-] execution.
-     [    0.187214]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905a20:-NamePath-] execution.
-     [    0.187407]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
-     [    0.187594]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
-     [    0.187789]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:LEqual] execution.
-     [    0.187980]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:Return] execution.
-     [    0.188146]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
-     [    0.188334]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
-     [    0.188524]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:Return] execution.
-     [    0.188712]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905c88:If] execution.
-     [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
-
-   Developers can utilize these special log entries to track the AML
-   interpretion, thus can aid issue debugging and performance tuning. Note
-   that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
-   macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
-   "AML tracer" logs.
-
-   The following command examples illustrate the usage of the "AML tracer"
-   functionality:
-   a. Filter out the method start/stop "AML tracer" logs when control
-      methods are being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "enable" > trace_state
-   b. Filter out the method start/stop "AML tracer" when the specified
-      control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method" > trace_state
-   c. Filter out the method start/stop "AML tracer" logs when the specified
-      control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method-once" > trace_state
-   d. Filter out the method/opcode start/stop "AML tracer" when the
-      specified control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "opcode" > trace_state
-   e. Filter out the method/opcode start/stop "AML tracer" when the
-      specified control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "opcode-opcode" > trace_state
-
-  Note that all above method tracing facility related module parameters can
-  be used as the boot parameters, for example:
-      acpi.trace_debug_layer=0x80 acpi.trace_debug_level=0x10 \
-      acpi.trace_method_name=\_SB.LID0._LID acpi.trace_state=opcode-once
-
-2. Interface descriptions:
-
-   All method tracing functions can be configured via ACPI module
-   parameters that are accessible at /sys/module/acpi/parameters/:
-
-   trace_method_name
-	The full path of the AML method that the user wants to trace.
-	Note that the full path shouldn't contain the trailing "_"s in its
-	name segments but may contain "\" to form an absolute path.
-
-   trace_debug_layer
-	The temporary debug_layer used when the tracing feature is enabled.
-	Using ACPI_EXECUTER (0x80) by default, which is the debug_layer
-	used to match all "AML tracer" logs.
-
-   trace_debug_level
-	The temporary debug_level used when the tracing feature is enabled.
-	Using ACPI_LV_TRACE_POINT (0x10) by default, which is the
-	debug_level used to match all "AML tracer" logs.
-
-   trace_state
-	The status of the tracing feature.
-	Users can enable/disable this debug tracing feature by executing
-	the following command:
-	    # echo string > /sys/module/acpi/parameters/trace_state
-	Where "string" should be one of the following:
-	"disable"
-	    Disable the method tracing feature.
-	"enable"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during any method
-	    execution will be logged.
-	"method"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method execution
-	    of "trace_method_name" will be logged.
-	"method-once"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method execution
-	    of "trace_method_name" will be logged only once.
-	"opcode"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method/opcode
-	    execution of "trace_method_name" will be logged.
-	"opcode-once"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method/opcode
-	    execution of "trace_method_name" will be logged only once.
-	Note that, the difference between the "enable" and other feature
-        enabling options are:
-	1. When "enable" is specified, since
-	   "trace_debug_layer/trace_debug_level" shall apply to all control
-	   method evaluations, after configuring "trace_state" to "enable",
-	   "trace_method_name" will be reset to NULL.
-	2. When "method/opcode" is specified, if
-	   "trace_method_name" is NULL when "trace_state" is configured to
-	   these options, the "trace_debug_layer/trace_debug_level" will
-	   apply to all control method evaluations.
diff --git a/Documentation/acpi/ssdt-overlays.txt b/Documentation/acpi/ssdt-overlays.txt
deleted file mode 100644
index 5ae13f161ea2..000000000000
--- a/Documentation/acpi/ssdt-overlays.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-
-In order to support ACPI open-ended hardware configurations (e.g. development
-boards) we need a way to augment the ACPI configuration provided by the firmware
-image. A common example is connecting sensors on I2C / SPI buses on development
-boards.
-
-Although this can be accomplished by creating a kernel platform driver or
-recompiling the firmware image with updated ACPI tables, neither is practical:
-the former proliferates board specific kernel code while the latter requires
-access to firmware tools which are often not publicly available.
-
-Because ACPI supports external references in AML code a more practical
-way to augment firmware ACPI configuration is by dynamically loading
-user defined SSDT tables that contain the board specific information.
-
-For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
-Minnowboard MAX development board exposed via the LSE connector [1], the
-following ASL code can be used:
-
-DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
-{
-    External (\_SB.I2C6, DeviceObj)
-
-    Scope (\_SB.I2C6)
-    {
-        Device (STAC)
-        {
-            Name (_ADR, Zero)
-            Name (_HID, "BMA222E")
-
-            Method (_CRS, 0, Serialized)
-            {
-                Name (RBUF, ResourceTemplate ()
-                {
-                    I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
-                                  AddressingMode7Bit, "\\_SB.I2C6", 0x00,
-                                  ResourceConsumer, ,)
-                    GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
-                             "\\_SB.GPO2", 0x00, ResourceConsumer, , )
-                    { // Pin list
-                        0
-                    }
-                })
-                Return (RBUF)
-            }
-        }
-    }
-}
-
-which can then be compiled to AML binary format:
-
-$ iasl minnowmax.asl
-
-Intel ACPI Component Architecture
-ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
-Copyright (c) 2000 - 2014 Intel Corporation
-
-ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
-AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
-
-[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
-
-The resulting AML code can then be loaded by the kernel using one of the methods
-below.
-
-== Loading ACPI SSDTs from initrd ==
-
-This option allows loading of user defined SSDTs from initrd and it is useful
-when the system does not support EFI or when there is not enough EFI storage.
-
-It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
-aml code must be placed in the first, uncompressed, initrd under the
-"kernel/firmware/acpi" path. Multiple files can be used and this will translate
-in loading multiple tables. Only SSDT and OEM tables are allowed. See
-initrd_table_override.txt for more details.
-
-Here is an example:
-
-# Add the raw ACPI tables to an uncompressed cpio archive.
-# They must be put into a /kernel/firmware/acpi directory inside the
-# cpio archive.
-# The uncompressed cpio archive must be the first.
-# Other, typically compressed cpio archives, must be
-# concatenated on top of the uncompressed one.
-mkdir -p kernel/firmware/acpi
-cp ssdt.aml kernel/firmware/acpi
-
-# Create the uncompressed cpio archive and concatenate the original initrd
-# on top:
-find kernel | cpio -H newc --create > /boot/instrumented_initrd
-cat /boot/initrd >>/boot/instrumented_initrd
-
-== Loading ACPI SSDTs from EFI variables ==
-
-This is the preferred method, when EFI is supported on the platform, because it
-allows a persistent, OS independent way of storing the user defined SSDTs. There
-is also work underway to implement EFI support for loading user defined SSDTs
-and using this method will make it easier to convert to the EFI loading
-mechanism when that will arrive.
-
-In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
-parameter can be used. The argument for the option is the variable name to
-use. If there are multiple variables with the same name but with different
-vendor GUIDs, all of them will be loaded.
-
-In order to store the AML code in an EFI variable the efivarfs filesystem can be
-used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
-recent distribution.
-
-Creating a new file in /sys/firmware/efi/efivars will automatically create a new
-EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
-variable. Please note that the file name needs to be specially formatted as
-"Name-GUID" and that the first 4 bytes in the file (little-endian format)
-represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
-include/linux/efi.h). Writing to the file must also be done with one write
-operation.
-
-For example, you can use the following bash script to create/update an EFI
-variable with the content from a given file:
-
-#!/bin/sh -e
-
-while ! [ -z "$1" ]; do
-        case "$1" in
-        "-f") filename="$2"; shift;;
-        "-g") guid="$2"; shift;;
-        *) name="$1";;
-        esac
-        shift
-done
-
-usage()
-{
-        echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
-        exit 1
-}
-
-[ -n "$name" -a -f "$filename" ] || usage
-
-EFIVARFS="/sys/firmware/efi/efivars"
-
-[ -d "$EFIVARFS" ] || exit 2
-
-if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
-        mount -t efivarfs none $EFIVARFS
-fi
-
-# try to pick up an existing GUID
-[ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
-
-# use a randomly generated GUID
-[ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
-
-# efivarfs expects all of the data in one write
-tmp=$(mktemp)
-/bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
-dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
-rm $tmp
-
-== Loading ACPI SSDTs from configfs ==
-
-This option allows loading of user defined SSDTs from userspace via the configfs
-interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
-mounted. In the following examples, we assume that configfs has been mounted in
-/config.
-
-New tables can be loading by creating new directories in /config/acpi/table/ and
-writing the SSDT aml code in the aml attribute:
-
-cd /config/acpi/table
-mkdir my_ssdt
-cat ~/ssdt.aml > my_ssdt/aml
diff --git a/Documentation/acpi/cppc_sysfs.txt b/Documentation/admin-guide/acpi/cppc_sysfs.rst
index f20fb445135d..a4b99afbe331 100644
--- a/Documentation/acpi/cppc_sysfs.txt
+++ b/Documentation/admin-guide/acpi/cppc_sysfs.rst
@@ -1,5 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-	Collaborative Processor Performance Control (CPPC)
+==================================================
+Collaborative Processor Performance Control (CPPC)
+==================================================
+
+CPPC
+====
 
 CPPC defined in the ACPI spec describes a mechanism for the OS to manage the
 performance of a logical processor on a contigious and abstract performance
@@ -10,31 +16,28 @@ For more details on CPPC please refer to the ACPI specification at:
 
 http://uefi.org/specifications
 
-Some of the CPPC registers are exposed via sysfs under:
-
-/sys/devices/system/cpu/cpuX/acpi_cppc/
-
-for each cpu X
+Some of the CPPC registers are exposed via sysfs under::
 
---------------------------------------------------------------------------------
+  /sys/devices/system/cpu/cpuX/acpi_cppc/
 
-$ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
-/sys/devices/system/cpu/cpu0/acpi_cppc/:
-total 0
--r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
--r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
--r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
+for each cpu X::
 
---------------------------------------------------------------------------------
+  $ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
+  /sys/devices/system/cpu/cpu0/acpi_cppc/:
+  total 0
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
 
 * highest_perf : Highest performance of this processor (abstract scale).
-* nominal_perf : Highest sustained performance of this processor (abstract scale).
+* nominal_perf : Highest sustained performance of this processor
+  (abstract scale).
 * lowest_nonlinear_perf : Lowest performance of this processor with nonlinear
   power savings (abstract scale).
 * lowest_perf : Lowest performance of this processor (abstract scale).
@@ -48,22 +51,26 @@ total 0
 * feedback_ctrs : Includes both Reference and delivered performance counter.
   Reference counter ticks up proportional to processor's reference performance.
   Delivered counter ticks up proportional to processor's delivered performance.
-* wraparound_time: Minimum time for the feedback counters to wraparound (seconds).
+* wraparound_time: Minimum time for the feedback counters to wraparound
+  (seconds).
 * reference_perf : Performance level at which reference performance counter
   accumulates (abstract scale).
 
---------------------------------------------------------------------------------
 
-		Computing Average Delivered Performance
+Computing Average Delivered Performance
+=======================================
+
+Below describes the steps to compute the average performance delivered by
+taking two different snapshots of feedback counters at time T1 and T2.
+
+  T1: Read feedback_ctrs as fbc_t1
+      Wait or run some workload
 
-Below describes the steps to compute the average performance delivered by taking
-two different snapshots of feedback counters at time T1 and T2.
+  T2: Read feedback_ctrs as fbc_t2
 
-T1: Read feedback_ctrs as fbc_t1
-    Wait or run some workload
-T2: Read feedback_ctrs as fbc_t2
+::
 
-delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
-reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
+  delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
+  reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
 
-delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
+  delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/acpi/dsdt-override.txt b/Documentation/admin-guide/acpi/dsdt-override.rst
index 784841caa6e6..50bd7f194bf4 100644
--- a/Documentation/acpi/dsdt-override.txt
+++ b/Documentation/admin-guide/acpi/dsdt-override.rst
@@ -1,6 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Overriding DSDT
+===============
+
 Linux supports a method of overriding the BIOS DSDT:
 
-CONFIG_ACPI_CUSTOM_DSDT builds the image into the kernel.
+CONFIG_ACPI_CUSTOM_DSDT - builds the image into the kernel.
 
 When to use this method is described in detail on the
 Linux/ACPI home page:
diff --git a/Documentation/admin-guide/acpi/index.rst b/Documentation/admin-guide/acpi/index.rst
new file mode 100644
index 000000000000..4d13eeea1eca
--- /dev/null
+++ b/Documentation/admin-guide/acpi/index.rst
@@ -0,0 +1,14 @@
+============
+ACPI Support
+============
+
+Here we document in detail how to interact with various mechanisms in
+the Linux ACPI support.
+
+.. toctree::
+   :maxdepth: 1
+
+   initrd_table_override
+   dsdt-override
+   ssdt-overlays
+   cppc_sysfs
diff --git a/Documentation/admin-guide/acpi/initrd_table_override.rst b/Documentation/admin-guide/acpi/initrd_table_override.rst
new file mode 100644
index 000000000000..cbd768207631
--- /dev/null
+++ b/Documentation/admin-guide/acpi/initrd_table_override.rst
@@ -0,0 +1,115 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
+Upgrading ACPI tables via initrd
+================================
+
+What is this about
+==================
+
+If the ACPI_TABLE_UPGRADE compile option is true, it is possible to
+upgrade the ACPI execution environment that is defined by the ACPI tables
+via upgrading the ACPI tables provided by the BIOS with an instrumented,
+modified, more recent version one, or installing brand new ACPI tables.
+
+When building initrd with kernel in a single image, option
+ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this
+feature to work.
+
+For a full list of ACPI tables that can be upgraded/installed, take a look
+at the char `*table_sigs[MAX_ACPI_SIGNATURE];` definition in
+drivers/acpi/tables.c.
+
+All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
+be overridable, except:
+
+  - ACPI_SIG_RSDP (has a signature of 6 bytes)
+  - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
+
+Both could get implemented as well.
+
+
+What is this for
+================
+
+Complain to your platform/BIOS vendor if you find a bug which is so severe
+that a workaround is not accepted in the Linux kernel. And this facility
+allows you to upgrade the buggy tables before your platform/BIOS vendor
+releases an upgraded BIOS binary.
+
+This facility can be used by platform/BIOS vendors to provide a Linux
+compatible environment without modifying the underlying platform firmware.
+
+This facility also provides a powerful feature to easily debug and test
+ACPI BIOS table compatibility with the Linux kernel by modifying old
+platform provided ACPI tables or inserting new ACPI tables.
+
+It can and should be enabled in any kernel because there is no functional
+change with not instrumented initrds.
+
+
+How does it work
+================
+::
+
+  # Extract the machine's ACPI tables:
+  cd /tmp
+  acpidump >acpidump
+  acpixtract -a acpidump
+  # Disassemble, modify and recompile them:
+  iasl -d *.dat
+  # For example add this statement into a _PRT (PCI Routing Table) function
+  # of the DSDT:
+  Store("HELLO WORLD", debug)
+  # And increase the OEM Revision. For example, before modification:
+  DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000000)
+  # After modification:
+  DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000001)
+  iasl -sa dsdt.dsl
+  # Add the raw ACPI tables to an uncompressed cpio archive.
+  # They must be put into a /kernel/firmware/acpi directory inside the cpio
+  # archive. Note that if the table put here matches a platform table
+  # (similar Table Signature, and similar OEMID, and similar OEM Table ID)
+  # with a more recent OEM Revision, the platform table will be upgraded by
+  # this table. If the table put here doesn't match a platform table
+  # (dissimilar Table Signature, or dissimilar OEMID, or dissimilar OEM Table
+  # ID), this table will be appended.
+  mkdir -p kernel/firmware/acpi
+  cp dsdt.aml kernel/firmware/acpi
+  # A maximum of "NR_ACPI_INITRD_TABLES (64)" tables are currently allowed
+  # (see osl.c):
+  iasl -sa facp.dsl
+  iasl -sa ssdt1.dsl
+  cp facp.aml kernel/firmware/acpi
+  cp ssdt1.aml kernel/firmware/acpi
+  # The uncompressed cpio archive must be the first. Other, typically
+  # compressed cpio archives, must be concatenated on top of the uncompressed
+  # one. Following command creates the uncompressed cpio archive and
+  # concatenates the original initrd on top:
+  find kernel | cpio -H newc --create > /boot/instrumented_initrd
+  cat /boot/initrd >>/boot/instrumented_initrd
+  # reboot with increased acpi debug level, e.g. boot params:
+  acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
+  # and check your syslog:
+  [    1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
+  [    1.272091] [ACPI Debug]  String [0x0B] "HELLO WORLD"
+
+iasl is able to disassemble and recompile quite a lot different,
+also static ACPI tables.
+
+
+Where to retrieve userspace tools
+=================================
+
+iasl and acpixtract are part of Intel's ACPICA project:
+http://acpica.org/
+
+and should be packaged by distributions (for example in the acpica package
+on SUSE).
+
+acpidump can be found in Len Browns pmtools:
+ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
+
+This tool is also part of the acpica package on SUSE.
+Alternatively, used ACPI tables can be retrieved via sysfs in latest kernels:
+/sys/firmware/acpi/tables
diff --git a/Documentation/admin-guide/acpi/ssdt-overlays.rst b/Documentation/admin-guide/acpi/ssdt-overlays.rst
new file mode 100644
index 000000000000..da37455f96c9
--- /dev/null
+++ b/Documentation/admin-guide/acpi/ssdt-overlays.rst
@@ -0,0 +1,180 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+SSDT Overlays
+=============
+
+In order to support ACPI open-ended hardware configurations (e.g. development
+boards) we need a way to augment the ACPI configuration provided by the firmware
+image. A common example is connecting sensors on I2C / SPI buses on development
+boards.
+
+Although this can be accomplished by creating a kernel platform driver or
+recompiling the firmware image with updated ACPI tables, neither is practical:
+the former proliferates board specific kernel code while the latter requires
+access to firmware tools which are often not publicly available.
+
+Because ACPI supports external references in AML code a more practical
+way to augment firmware ACPI configuration is by dynamically loading
+user defined SSDT tables that contain the board specific information.
+
+For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
+Minnowboard MAX development board exposed via the LSE connector [1], the
+following ASL code can be used::
+
+    DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
+    {
+        External (\_SB.I2C6, DeviceObj)
+
+        Scope (\_SB.I2C6)
+        {
+            Device (STAC)
+            {
+                Name (_ADR, Zero)
+                Name (_HID, "BMA222E")
+
+                Method (_CRS, 0, Serialized)
+                {
+                    Name (RBUF, ResourceTemplate ()
+                    {
+                        I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
+                                    AddressingMode7Bit, "\\_SB.I2C6", 0x00,
+                                    ResourceConsumer, ,)
+                        GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
+                                "\\_SB.GPO2", 0x00, ResourceConsumer, , )
+                        { // Pin list
+                            0
+                        }
+                    })
+                    Return (RBUF)
+                }
+            }
+        }
+    }
+
+which can then be compiled to AML binary format::
+
+    $ iasl minnowmax.asl
+
+    Intel ACPI Component Architecture
+    ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
+    Copyright (c) 2000 - 2014 Intel Corporation
+
+    ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
+    AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
+
+[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
+
+The resulting AML code can then be loaded by the kernel using one of the methods
+below.
+
+Loading ACPI SSDTs from initrd
+==============================
+
+This option allows loading of user defined SSDTs from initrd and it is useful
+when the system does not support EFI or when there is not enough EFI storage.
+
+It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
+aml code must be placed in the first, uncompressed, initrd under the
+"kernel/firmware/acpi" path. Multiple files can be used and this will translate
+in loading multiple tables. Only SSDT and OEM tables are allowed. See
+initrd_table_override.txt for more details.
+
+Here is an example::
+
+    # Add the raw ACPI tables to an uncompressed cpio archive.
+    # They must be put into a /kernel/firmware/acpi directory inside the
+    # cpio archive.
+    # The uncompressed cpio archive must be the first.
+    # Other, typically compressed cpio archives, must be
+    # concatenated on top of the uncompressed one.
+    mkdir -p kernel/firmware/acpi
+    cp ssdt.aml kernel/firmware/acpi
+
+    # Create the uncompressed cpio archive and concatenate the original initrd
+    # on top:
+    find kernel | cpio -H newc --create > /boot/instrumented_initrd
+    cat /boot/initrd >>/boot/instrumented_initrd
+
+Loading ACPI SSDTs from EFI variables
+=====================================
+
+This is the preferred method, when EFI is supported on the platform, because it
+allows a persistent, OS independent way of storing the user defined SSDTs. There
+is also work underway to implement EFI support for loading user defined SSDTs
+and using this method will make it easier to convert to the EFI loading
+mechanism when that will arrive.
+
+In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
+parameter can be used. The argument for the option is the variable name to
+use. If there are multiple variables with the same name but with different
+vendor GUIDs, all of them will be loaded.
+
+In order to store the AML code in an EFI variable the efivarfs filesystem can be
+used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
+recent distribution.
+
+Creating a new file in /sys/firmware/efi/efivars will automatically create a new
+EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
+variable. Please note that the file name needs to be specially formatted as
+"Name-GUID" and that the first 4 bytes in the file (little-endian format)
+represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
+include/linux/efi.h). Writing to the file must also be done with one write
+operation.
+
+For example, you can use the following bash script to create/update an EFI
+variable with the content from a given file::
+
+    #!/bin/sh -e
+
+    while ! [ -z "$1" ]; do
+            case "$1" in
+            "-f") filename="$2"; shift;;
+            "-g") guid="$2"; shift;;
+            *) name="$1";;
+            esac
+            shift
+    done
+
+    usage()
+    {
+            echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
+            exit 1
+    }
+
+    [ -n "$name" -a -f "$filename" ] || usage
+
+    EFIVARFS="/sys/firmware/efi/efivars"
+
+    [ -d "$EFIVARFS" ] || exit 2
+
+    if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
+            mount -t efivarfs none $EFIVARFS
+    fi
+
+    # try to pick up an existing GUID
+    [ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
+
+    # use a randomly generated GUID
+    [ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
+
+    # efivarfs expects all of the data in one write
+    tmp=$(mktemp)
+    /bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
+    dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
+    rm $tmp
+
+Loading ACPI SSDTs from configfs
+================================
+
+This option allows loading of user defined SSDTs from userspace via the configfs
+interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
+mounted. In the following examples, we assume that configfs has been mounted in
+/config.
+
+New tables can be loading by creating new directories in /config/acpi/table/ and
+writing the SSDT aml code in the aml attribute::
+
+    cd /config/acpi/table
+    mkdir my_ssdt
+    cat ~/ssdt.aml > my_ssdt/aml
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 0a491676685e..5b8286fdd91b 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -77,6 +77,7 @@ configure specific aspects of kernel behavior to your liking.
    LSM/index
    mm/index
    perf-security
+   acpi/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index b8d0bc07ed0a..0124980dca2d 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -88,6 +88,7 @@ parameter is applicable::
 	APIC	APIC support is enabled.
 	APM	Advanced Power Management support is enabled.
 	ARM	ARM architecture is enabled.
+	ARM64	ARM64 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	CLK	Common clock infrastructure is enabled.
 	CMA	Contiguous Memory Area support is enabled.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2b8ee90bb644..fd03e2b629bb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -704,8 +704,11 @@
 			upon panic. This parameter reserves the physical
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
-			is selected automatically. Check
-			Documentation/kdump/kdump.txt for further details.
+			is selected automatically.
+			[KNL, x86_64] select a region under 4G first, and
+			fall back to reserve region above 4G when '@offset'
+			hasn't been specified.
+			See Documentation/kdump/kdump.txt for further details.
 
 	crashkernel=range1:size1[,range2:size2,...][@offset]
 			[KNL] Same as above, but depends on the memory
@@ -2544,6 +2547,40 @@
 			in the "bleeding edge" mini2440 support kernel at
 			http://repo.or.cz/w/linux-2.6/mini2440.git
 
+	mitigations=
+			[X86,PPC,S390,ARM64] Control optional mitigations for
+			CPU vulnerabilities.  This is a set of curated,
+			arch-independent options, each of which is an
+			aggregation of existing arch-specific options.
+
+			off
+				Disable all optional CPU mitigations.  This
+				improves system performance, but it may also
+				expose users to several CPU vulnerabilities.
+				Equivalent to: nopti [X86,PPC]
+					       kpti=0 [ARM64]
+					       nospectre_v1 [PPC]
+					       nobp=0 [S390]
+					       nospectre_v2 [X86,PPC,S390,ARM64]
+					       spectre_v2_user=off [X86]
+					       spec_store_bypass_disable=off [X86,PPC]
+					       ssbd=force-off [ARM64]
+					       l1tf=off [X86]
+
+			auto (default)
+				Mitigate all CPU vulnerabilities, but leave SMT
+				enabled, even if it's vulnerable.  This is for
+				users who don't want to be surprised by SMT
+				getting disabled across kernel upgrades, or who
+				have other ways of avoiding SMT-based attacks.
+				Equivalent to: (default behavior)
+
+			auto,nosmt
+				Mitigate all CPU vulnerabilities, disabling SMT
+				if needed.  This is for users who always want to
+				be fully mitigated, even if it means losing SMT.
+				Equivalent to: l1tf=flush,nosmt [X86]
+
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
 			parameter allows control of the logging verbosity for
@@ -2873,10 +2910,10 @@
 			check bypass). With this option data leaks are possible
 			in the system.
 
-	nospectre_v2	[X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2
-			(indirect branch prediction) vulnerability. System may
-			allow data leaks with this option, which is equivalent
-			to spectre_v2=off.
+	nospectre_v2	[X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
+			the Spectre variant 2 (indirect branch prediction)
+			vulnerability. System may allow data leaks with this
+			option.
 
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
@@ -3394,6 +3431,8 @@
 				bridges without forcing it upstream. Note:
 				this removes isolation between devices and
 				may put more devices in an IOMMU group.
+		force_floating	[S390] Force usage of floating interrupts.
+		nomio		[S390] Do not use MIO instructions.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
@@ -3623,7 +3662,9 @@
 				see CONFIG_RAS_CEC help text.
 
 	rcu_nocbs=	[KNL]
-			The argument is a cpu list, as described above.
+			The argument is a cpu list, as described above,
+			except that the string "all" can be used to
+			specify every CPU on the system.
 
 			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
 			the specified list of CPUs to be no-callback CPUs.
@@ -4703,6 +4744,10 @@
 			[x86] unstable: mark the TSC clocksource as unstable, this
 			marks the TSC unconditionally unstable at bootup and
 			avoids any further wobbles once the TSC watchdog notices.
+			[x86] nowatchdog: disable clocksource watchdog. Used
+			in situations with strict latency requirements (where
+			interruptions from clocksource watchdog are not
+			acceptable).
 
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
diff --git a/Documentation/arm64/cpu-feature-registers.txt b/Documentation/arm64/cpu-feature-registers.txt
index d4b4dd1fe786..684a0da39378 100644
--- a/Documentation/arm64/cpu-feature-registers.txt
+++ b/Documentation/arm64/cpu-feature-registers.txt
@@ -209,6 +209,22 @@ infrastructure:
      | AT                           | [35-32] |    y    |
      x--------------------------------------------------x
 
+  6) ID_AA64ZFR0_EL1 - SVE feature ID register 0
+
+     x--------------------------------------------------x
+     | Name                         |  bits   | visible |
+     |--------------------------------------------------|
+     | SM4                          | [43-40] |    y    |
+     |--------------------------------------------------|
+     | SHA3                         | [35-32] |    y    |
+     |--------------------------------------------------|
+     | BitPerm                      | [19-16] |    y    |
+     |--------------------------------------------------|
+     | AES                          | [7-4]   |    y    |
+     |--------------------------------------------------|
+     | SVEVer                       | [3-0]   |    y    |
+     x--------------------------------------------------x
+
 Appendix I: Example
 ---------------------------
 
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt
index 13d6691b37be..b73a2519ecf2 100644
--- a/Documentation/arm64/elf_hwcaps.txt
+++ b/Documentation/arm64/elf_hwcaps.txt
@@ -13,9 +13,9 @@ architected discovery mechanism available to userspace code at EL0. The
 kernel exposes the presence of these features to userspace through a set
 of flags called hwcaps, exposed in the auxilliary vector.
 
-Userspace software can test for features by acquiring the AT_HWCAP entry
-of the auxilliary vector, and testing whether the relevant flags are
-set, e.g.
+Userspace software can test for features by acquiring the AT_HWCAP or
+AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant
+flags are set, e.g.
 
 bool floating_point_is_present(void)
 {
@@ -135,6 +135,10 @@ HWCAP_DCPOP
 
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
 
+HWCAP2_DCPODP
+
+    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
+
 HWCAP_SHA3
 
     Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
@@ -159,6 +163,30 @@ HWCAP_SVE
 
     Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
 
+HWCAP2_SVE2
+
+    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+
+HWCAP2_SVEAES
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
+
+HWCAP2_SVEPMULL
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
+
+HWCAP2_SVEBITPERM
+
+    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
+
+HWCAP2_SVESHA3
+
+    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
+
+HWCAP2_SVESM4
+
+    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
+
 HWCAP_ASIMDFHM
 
    Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
@@ -194,3 +222,10 @@ HWCAP_PACG
     Functionality implied by ID_AA64ISAR1_EL1.GPA == 0b0001 or
     ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
     Documentation/arm64/pointer-authentication.txt.
+
+
+4. Unused AT_HWCAP bits
+-----------------------
+
+For interoperation with userspace, the kernel guarantees that bits 62
+and 63 of AT_HWCAP will always be returned as 0.
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index d1e2bb801e1b..68d9b74fd751 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -61,6 +61,7 @@ stable kernels.
 | ARM            | Cortex-A76      | #1188873        | ARM64_ERRATUM_1188873       |
 | ARM            | Cortex-A76      | #1165522        | ARM64_ERRATUM_1165522       |
 | ARM            | Cortex-A76      | #1286807        | ARM64_ERRATUM_1286807       |
+| ARM            | Neoverse-N1     | #1188873        | ARM64_ERRATUM_1188873       |
 | ARM            | MMU-500         | #841119,#826419 | N/A                         |
 |                |                 |                 |                             |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375        |
@@ -77,6 +78,7 @@ stable kernels.
 | Hisilicon      | Hip0{5,6,7}     | #161010101      | HISILICON_ERRATUM_161010101 |
 | Hisilicon      | Hip0{6,7}       | #161010701      | N/A                         |
 | Hisilicon      | Hip07           | #161600802      | HISILICON_ERRATUM_161600802 |
+| Hisilicon      | Hip08 SMMU PMCG | #162001800      | N/A                         |
 |                |                 |                 |                             |
 | Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
diff --git a/Documentation/arm64/sve.txt b/Documentation/arm64/sve.txt
index 7169a0ec41d8..9940e924a47e 100644
--- a/Documentation/arm64/sve.txt
+++ b/Documentation/arm64/sve.txt
@@ -34,6 +34,23 @@ model features for SVE is included in Appendix A.
   following sections: software that needs to verify that those interfaces are
   present must check for HWCAP_SVE instead.
 
+* On hardware that supports the SVE2 extensions, HWCAP2_SVE2 will also
+  be reported in the AT_HWCAP2 aux vector entry.  In addition to this,
+  optional extensions to SVE2 may be reported by the presence of:
+
+	HWCAP2_SVE2
+	HWCAP2_SVEAES
+	HWCAP2_SVEPMULL
+	HWCAP2_SVEBITPERM
+	HWCAP2_SVESHA3
+	HWCAP2_SVESM4
+
+  This list may be extended over time as the SVE architecture evolves.
+
+  These extensions are also reported via the CPU ID register ID_AA64ZFR0_EL1,
+  which userspace can read using an MRS instruction.  See elf_hwcaps.txt and
+  cpu-feature-registers.txt for details.
+
 * Debuggers should restrict themselves to interacting with the target via the
   NT_ARM_SVE regset.  The recommended way of detecting support for this regset
   is to connect to a target process first and then attempt a
diff --git a/Documentation/atomic_t.txt b/Documentation/atomic_t.txt
index 913396ac5824..dca3fb0554db 100644
--- a/Documentation/atomic_t.txt
+++ b/Documentation/atomic_t.txt
@@ -56,6 +56,23 @@ Barriers:
   smp_mb__{before,after}_atomic()
 
 
+TYPES (signed vs unsigned)
+-----
+
+While atomic_t, atomic_long_t and atomic64_t use int, long and s64
+respectively (for hysterical raisins), the kernel uses -fno-strict-overflow
+(which implies -fwrapv) and defines signed overflow to behave like
+2s-complement.
+
+Therefore, an explicitly unsigned variant of the atomic ops is strictly
+unnecessary and we can simply cast, there is no UB.
+
+There was a bug in UBSAN prior to GCC-8 that would generate UB warnings for
+signed types.
+
+With this we also conform to the C/C++ _Atomic behaviour and things like
+P1236R1.
+
 
 SEMANTICS
 ---------
diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst
index 6eb9d3f090cd..93cb65d52720 100644
--- a/Documentation/core-api/cachetlb.rst
+++ b/Documentation/core-api/cachetlb.rst
@@ -101,16 +101,6 @@ changes occur:
 	translations for software managed TLB configurations.
 	The sparc64 port currently does this.
 
-6) ``void tlb_migrate_finish(struct mm_struct *mm)``
-
-	This interface is called at the end of an explicit
-	process migration. This interface provides a hook
-	to allow a platform to update TLB or context-specific
-	information for the address space.
-
-	The ia64 sn2 platform is one example of a platform
-	that uses this interface.
-
 Next, we have the cache flushing interfaces.  In general, when Linux
 is changing an existing virtual-->physical mapping to a new value,
 the sequence will be in one of the following forms::
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index c6e7e9196a8b..cb61277e2308 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -3,79 +3,79 @@ How CPU topology info is exported via sysfs
 ===========================================
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo output of some architectures:
+to /proc/cpuinfo output of some architectures.  They reside in
+/sys/devices/system/cpu/cpuX/topology/:
 
-1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
+physical_package_id:
 
 	physical package id of cpuX. Typically corresponds to a physical
 	socket number, but the actual value is architecture and platform
 	dependent.
 
-2) /sys/devices/system/cpu/cpuX/topology/core_id:
+core_id:
 
 	the CPU core ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/book_id:
+book_id:
 
 	the book ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-4) /sys/devices/system/cpu/cpuX/topology/drawer_id:
+drawer_id:
 
 	the drawer ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-5) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	core as cpuX.
 
-6) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+thread_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	core as cpuX.
 
-7) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-8) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+core_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	physical_package_id.
 
-9) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
-10) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+book_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	book_id.
 
-11) /sys/devices/system/cpu/cpuX/topology/drawer_siblings:
+drawer_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	drawer_id.
 
-12) /sys/devices/system/cpu/cpuX/topology/drawer_siblings_list:
+drawer_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	drawer_id.
 
-To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 6 to 12 attributes. The book
-and drawer related sysfs files will only be created if CONFIG_SCHED_BOOK
-and CONFIG_SCHED_DRAWER are selected.
+Architecture-neutral, drivers/base/topology.c, exports these attributes.
+However, the book and drawer related sysfs files will only be created if
+CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively.
 
-CONFIG_SCHED_BOOK and CONFIG_DRAWER are currently only used on s390, where
-they reflect the cpu and cache hierarchy.
+CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390,
+where they reflect the cpu and cache hierarchy.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h::
@@ -98,10 +98,10 @@ To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
 
-1) physical_package_id: -1
-2) core_id: 0
-3) sibling_cpumask: just the given CPU
-4) core_cpumask: just the given CPU
+1) topology_physical_package_id: -1
+2) topology_core_id: 0
+3) topology_sibling_cpumask: just the given CPU
+4) topology_core_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().
diff --git a/Documentation/driver-api/acpi/index.rst b/Documentation/driver-api/acpi/index.rst
new file mode 100644
index 000000000000..ace0008e54c2
--- /dev/null
+++ b/Documentation/driver-api/acpi/index.rst
@@ -0,0 +1,9 @@
+============
+ACPI Support
+============
+
+.. toctree::
+   :maxdepth: 2
+
+   linuxized-acpica
+   scan_handlers
diff --git a/Documentation/acpi/linuxized-acpica.txt b/Documentation/driver-api/acpi/linuxized-acpica.rst
index 3ad7b0dfb083..0ca8f1538519 100644
--- a/Documentation/acpi/linuxized-acpica.txt
+++ b/Documentation/driver-api/acpi/linuxized-acpica.rst
@@ -1,31 +1,37 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+============================================================
 Linuxized ACPICA - Introduction to ACPICA Release Automation
+============================================================
 
-Copyright (C) 2013-2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
+:Copyright: |copy| 2013-2016, Intel Corporation
 
+:Author: Lv Zheng <lv.zheng@intel.com>
 
-Abstract:
 
+Abstract
+========
 This document describes the ACPICA project and the relationship between
 ACPICA and Linux.  It also describes how ACPICA code in drivers/acpi/acpica,
 include/acpi and tools/power/acpi is automatically updated to follow the
 upstream.
 
+ACPICA Project
+==============
 
-1. ACPICA Project
-
-   The ACPI Component Architecture (ACPICA) project provides an operating
-   system (OS)-independent reference implementation of the Advanced
-   Configuration and Power Interface Specification (ACPI).  It has been
-   adapted by various host OSes.  By directly integrating ACPICA, Linux can
-   also benefit from the application experiences of ACPICA from other host
-   OSes.
+The ACPI Component Architecture (ACPICA) project provides an operating
+system (OS)-independent reference implementation of the Advanced
+Configuration and Power Interface Specification (ACPI).  It has been
+adapted by various host OSes.  By directly integrating ACPICA, Linux can
+also benefit from the application experiences of ACPICA from other host
+OSes.
 
-   The homepage of ACPICA project is: www.acpica.org, it is maintained and
-   supported by Intel Corporation.
+The homepage of ACPICA project is: www.acpica.org, it is maintained and
+supported by Intel Corporation.
 
-   The following figure depicts the Linux ACPI subsystem where the ACPICA
-   adaptation is included:
+The following figure depicts the Linux ACPI subsystem where the ACPICA
+adaptation is included::
 
       +---------------------------------------------------------+
       |                                                         |
@@ -71,21 +77,27 @@ upstream.
 
                  Figure 1. Linux ACPI Software Components
 
-   NOTE:
+.. note::
     A. OS Service Layer - Provided by Linux to offer OS dependent
        implementation of the predefined ACPICA interfaces (acpi_os_*).
+       ::
+
          include/acpi/acpiosxf.h
          drivers/acpi/osl.c
          include/acpi/platform
          include/asm/acenv.h
     B. ACPICA Functionality - Released from ACPICA code base to offer
        OS independent implementation of the ACPICA interfaces (acpi_*).
+       ::
+
          drivers/acpi/acpica
          include/acpi/ac*.h
          tools/power/acpi
     C. Linux/ACPI Functionality - Providing Linux specific ACPI
        functionality to the other Linux kernel subsystems and user space
        programs.
+       ::
+
          drivers/acpi
          include/linux/acpi.h
          include/linux/acpi*.h
@@ -95,24 +107,27 @@ upstream.
        ACPI subsystem to offer architecture specific implementation of the
        ACPI interfaces.  They are Linux specific components and are out of
        the scope of this document.
+       ::
+
          include/asm/acpi.h
          include/asm/acpi*.h
          arch/*/acpi
 
-2. ACPICA Release
+ACPICA Release
+==============
 
-   The ACPICA project maintains its code base at the following repository URL:
-   https://github.com/acpica/acpica.git. As a rule, a release is made every
-   month.
+The ACPICA project maintains its code base at the following repository URL:
+https://github.com/acpica/acpica.git. As a rule, a release is made every
+month.
 
-   As the coding style adopted by the ACPICA project is not acceptable by
-   Linux, there is a release process to convert the ACPICA git commits into
-   Linux patches.  The patches generated by this process are referred to as
-   "linuxized ACPICA patches".  The release process is carried out on a local
-   copy the ACPICA git repository.  Each commit in the monthly release is
-   converted into a linuxized ACPICA patch.  Together, they form the monthly
-   ACPICA release patchset for the Linux ACPI community.  This process is
-   illustrated in the following figure:
+As the coding style adopted by the ACPICA project is not acceptable by
+Linux, there is a release process to convert the ACPICA git commits into
+Linux patches.  The patches generated by this process are referred to as
+"linuxized ACPICA patches".  The release process is carried out on a local
+copy the ACPICA git repository.  Each commit in the monthly release is
+converted into a linuxized ACPICA patch.  Together, they form the monthly
+ACPICA release patchset for the Linux ACPI community.  This process is
+illustrated in the following figure::
 
     +-----------------------------+
     | acpica / master (-) commits |
@@ -153,7 +168,7 @@ upstream.
 
                 Figure 2. ACPICA -> Linux Upstream Process
 
-   NOTE:
+.. note::
     A. Linuxize Utilities - Provided by the ACPICA repository, including a
        utility located in source/tools/acpisrc folder and a number of
        scripts located in generate/linux folder.
@@ -170,19 +185,20 @@ upstream.
    following kernel configuration options:
    CONFIG_ACPI/CONFIG_ACPI_DEBUG/CONFIG_ACPI_DEBUGGER
 
-3. ACPICA Divergences
+ACPICA Divergences
+==================
 
-   Ideally, all of the ACPICA commits should be converted into Linux patches
-   automatically without manual modifications, the "linux / master" tree should
-   contain the ACPICA code that exactly corresponds to the ACPICA code
-   contained in "new linuxized acpica" tree and it should be possible to run
-   the release process fully automatically.
+Ideally, all of the ACPICA commits should be converted into Linux patches
+automatically without manual modifications, the "linux / master" tree should
+contain the ACPICA code that exactly corresponds to the ACPICA code
+contained in "new linuxized acpica" tree and it should be possible to run
+the release process fully automatically.
 
-   As a matter of fact, however, there are source code differences between
-   the ACPICA code in Linux and the upstream ACPICA code, referred to as
-   "ACPICA Divergences".
+As a matter of fact, however, there are source code differences between
+the ACPICA code in Linux and the upstream ACPICA code, referred to as
+"ACPICA Divergences".
 
-   The various sources of ACPICA divergences include:
+The various sources of ACPICA divergences include:
    1. Legacy divergences - Before the current ACPICA release process was
       established, there already had been divergences between Linux and
       ACPICA. Over the past several years those divergences have been greatly
@@ -213,11 +229,12 @@ upstream.
       rebased on the ACPICA side in order to offer better solutions, new ACPICA
       divergences are generated.
 
-4. ACPICA Development
+ACPICA Development
+==================
 
-   This paragraph guides Linux developers to use the ACPICA upstream release
-   utilities to obtain Linux patches corresponding to upstream ACPICA commits
-   before they become available from the ACPICA release process.
+This paragraph guides Linux developers to use the ACPICA upstream release
+utilities to obtain Linux patches corresponding to upstream ACPICA commits
+before they become available from the ACPICA release process.
 
    1. Cherry-pick an ACPICA commit
 
@@ -225,7 +242,7 @@ upstream.
    you want to cherry pick must be committed into the local repository.
 
    Then the gen-patch.sh command can help to cherry-pick an ACPICA commit
-   from the ACPICA local repository:
+   from the ACPICA local repository::
 
    $ git clone https://github.com/acpica/acpica
    $ cd acpica
@@ -240,7 +257,7 @@ upstream.
    changes that haven't been applied to Linux yet.
 
    You can generate the ACPICA release series yourself and rebase your code on
-   top of the generated ACPICA release patches:
+   top of the generated ACPICA release patches::
 
    $ git clone https://github.com/acpica/acpica
    $ cd acpica
@@ -254,7 +271,7 @@ upstream.
    3. Inspect the current divergences
 
    If you have local copies of both Linux and upstream ACPICA, you can generate
-   a diff file indicating the state of the current divergences:
+   a diff file indicating the state of the current divergences::
 
    # git clone https://github.com/acpica/acpica
    # git clone http://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/Documentation/acpi/scan_handlers.txt b/Documentation/driver-api/acpi/scan_handlers.rst
index 3246ccf15992..7a197b3a33fc 100644
--- a/Documentation/acpi/scan_handlers.txt
+++ b/Documentation/driver-api/acpi/scan_handlers.rst
@@ -1,7 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+==================
 ACPI Scan Handlers
+==================
+
+:Copyright: |copy| 2012, Intel Corporation
 
-Copyright (C) 2012, Intel Corporation
-Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 During system initialization and ACPI-based device hot-add, the ACPI namespace
 is scanned in search of device objects that generally represent various pieces
@@ -30,14 +36,14 @@ to configure that link so that the kernel can use it.
 Those additional configuration tasks usually depend on the type of the hardware
 component represented by the given device node which can be determined on the
 basis of the device node's hardware ID (HID).  They are performed by objects
-called ACPI scan handlers represented by the following structure:
+called ACPI scan handlers represented by the following structure::
 
-struct acpi_scan_handler {
-	const struct acpi_device_id *ids;
-	struct list_head list_node;
-	int (*attach)(struct acpi_device *dev, const struct acpi_device_id *id);
-	void (*detach)(struct acpi_device *dev);
-};
+	struct acpi_scan_handler {
+		const struct acpi_device_id *ids;
+		struct list_head list_node;
+		int (*attach)(struct acpi_device *dev, const struct acpi_device_id *id);
+		void (*detach)(struct acpi_device *dev);
+	};
 
 where ids is the list of IDs of device nodes the given handler is supposed to
 take care of, list_node is the hook to the global list of ACPI scan handlers
diff --git a/Documentation/driver-api/device-io.rst b/Documentation/driver-api/device-io.rst
index b00b23903078..0e389378f71d 100644
--- a/Documentation/driver-api/device-io.rst
+++ b/Documentation/driver-api/device-io.rst
@@ -103,51 +103,6 @@ continuing execution::
         ha->flags.ints_enabled = 0;
     }
 
-In addition to write posting, on some large multiprocessing systems
-(e.g. SGI Challenge, Origin and Altix machines) posted writes won't be
-strongly ordered coming from different CPUs. Thus it's important to
-properly protect parts of your driver that do memory-mapped writes with
-locks and use the :c:func:`mmiowb()` to make sure they arrive in the
-order intended. Issuing a regular readX() will also ensure write ordering,
-but should only be used when the 
-driver has to be sure that the write has actually arrived at the device
-(not that it's simply ordered with respect to other writes), since a
-full readX() is a relatively expensive operation.
-
-Generally, one should use :c:func:`mmiowb()` prior to releasing a spinlock
-that protects regions using :c:func:`writeb()` or similar functions that
-aren't surrounded by readb() calls, which will ensure ordering
-and flushing. The following pseudocode illustrates what might occur if
-write ordering isn't guaranteed via :c:func:`mmiowb()` or one of the
-readX() functions::
-
-    CPU A:  spin_lock_irqsave(&dev_lock, flags)
-    CPU A:  ...
-    CPU A:  writel(newval, ring_ptr);
-    CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-            ...
-    CPU B:  spin_lock_irqsave(&dev_lock, flags)
-    CPU B:  writel(newval2, ring_ptr);
-    CPU B:  ...
-    CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-
-In the case above, newval2 could be written to ring_ptr before newval.
-Fixing it is easy though::
-
-    CPU A:  spin_lock_irqsave(&dev_lock, flags)
-    CPU A:  ...
-    CPU A:  writel(newval, ring_ptr);
-    CPU A:  mmiowb(); /* ensure no other writes beat us to the device */
-    CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-            ...
-    CPU B:  spin_lock_irqsave(&dev_lock, flags)
-    CPU B:  writel(newval2, ring_ptr);
-    CPU B:  ...
-    CPU B:  mmiowb();
-    CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-
-See tg3.c for a real world example of how to use :c:func:`mmiowb()`
-
 PCI ordering rules also guarantee that PIO read responses arrive after any
 outstanding DMA writes from that bus, since for some devices the result of
 a readb() call may signal to the driver that a DMA transaction is
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index c0b600ed9961..aa87075c7846 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -56,6 +56,7 @@ available subsections can be seen below.
    slimbus
    soundwire/index
    fpga/index
+   acpi/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst
index 6d85b5a2598d..44deb52beeb4 100644
--- a/Documentation/driver-api/pci/p2pdma.rst
+++ b/Documentation/driver-api/pci/p2pdma.rst
@@ -132,10 +132,6 @@ precludes passing these pages to userspace.
 P2P memory is also technically IO memory but should never have any side
 effects behind it. Thus, the order of loads and stores should not be important
 and ioreadX(), iowriteX() and friends should not be necessary.
-However, as the memory is not cache coherent, if access ever needs to
-be protected by a spinlock then :c:func:`mmiowb()` must be used before
-unlocking the lock. (See ACQUIRES VS I/O ACCESSES in
-Documentation/memory-barriers.txt)
 
 
 P2P DMA Support Library
diff --git a/Documentation/driver-api/usb/power-management.rst b/Documentation/driver-api/usb/power-management.rst
index 79beb807996b..4a74cf6f2797 100644
--- a/Documentation/driver-api/usb/power-management.rst
+++ b/Documentation/driver-api/usb/power-management.rst
@@ -370,11 +370,15 @@ autosuspend the interface's device.  When the usage counter is = 0
 then the interface is considered to be idle, and the kernel may
 autosuspend the device.
 
-Drivers need not be concerned about balancing changes to the usage
-counter; the USB core will undo any remaining "get"s when a driver
-is unbound from its interface.  As a corollary, drivers must not call
-any of the ``usb_autopm_*`` functions after their ``disconnect``
-routine has returned.
+Drivers must be careful to balance their overall changes to the usage
+counter.  Unbalanced "get"s will remain in effect when a driver is
+unbound from its interface, preventing the device from going into
+runtime suspend should the interface be bound to a driver again.  On
+the other hand, drivers are allowed to achieve this balance by calling
+the ``usb_autopm_*`` functions even after their ``disconnect`` routine
+has returned -- say from within a work-queue routine -- provided they
+retain an active reference to the interface (via ``usb_get_intf`` and
+``usb_put_intf``).
 
 Drivers using the async routines are responsible for their own
 synchronization and mutual exclusion.
diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
index 2855dfe2464d..1d46da165b75 100644
--- a/Documentation/features/time/modern-timekeeping/arch-support.txt
+++ b/Documentation/features/time/modern-timekeeping/arch-support.txt
@@ -15,7 +15,7 @@
     |       h8300: |  ok  |
     |     hexagon: |  ok  |
     |        ia64: |  ok  |
-    |        m68k: | TODO |
+    |        m68k: |  ok  |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
     |       nds32: |  ok  |
diff --git a/Documentation/acpi/DSD-properties-rules.txt b/Documentation/firmware-guide/acpi/DSD-properties-rules.rst
index 3e4862bdad98..4306f29b6103 100644
--- a/Documentation/acpi/DSD-properties-rules.txt
+++ b/Documentation/firmware-guide/acpi/DSD-properties-rules.rst
@@ -1,8 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
 _DSD Device Properties Usage Rules
-----------------------------------
+==================================
 
 Properties, Property Sets and Property Subsets
-----------------------------------------------
+==============================================
 
 The _DSD (Device Specific Data) configuration object, introduced in ACPI 5.1,
 allows any type of device configuration data to be provided via the ACPI
@@ -18,7 +21,7 @@ specific type) associated with it.
 
 In the ACPI _DSD context it is an element of the sub-package following the
 generic Device Properties UUID in the _DSD return package as specified in the
-Device Properties UUID definition document [1].
+Device Properties UUID definition document [1]_.
 
 It also may be regarded as the definition of a key and the associated data type
 that can be returned by _DSD in the Device Properties UUID sub-package for a
@@ -33,14 +36,14 @@ Property subsets are nested collections of properties.  Each of them is
 associated with an additional key (name) allowing the subset to be referred
 to as a whole (and to be treated as a separate entity).  The canonical
 representation of property subsets is via the mechanism specified in the
-Hierarchical Properties Extension UUID definition document [2].
+Hierarchical Properties Extension UUID definition document [2]_.
 
 Property sets may be hierarchical.  That is, a property set may contain
 multiple property subsets that each may contain property subsets of its
 own and so on.
 
 General Validity Rule for Property Sets
----------------------------------------
+=======================================
 
 Valid property sets must follow the guidance given by the Device Properties UUID
 definition document [1].
@@ -73,7 +76,7 @@ suitable for the ACPI environment and consequently they cannot belong to a valid
 property set.
 
 Property Sets and Device Tree Bindings
---------------------------------------
+======================================
 
 It often is useful to make _DSD return property sets that follow Device Tree
 bindings.
@@ -91,7 +94,7 @@ expected to automatically work in the ACPI environment regardless of their
 contents.
 
 References
-----------
+==========
 
-[1] http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf
-[2] http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf
+.. [1] http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf
+.. [2] http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf
diff --git a/Documentation/acpi/acpi-lid.txt b/Documentation/firmware-guide/acpi/acpi-lid.rst
index effe7af3a5af..874ce0ed340d 100644
--- a/Documentation/acpi/acpi-lid.txt
+++ b/Documentation/firmware-guide/acpi/acpi-lid.rst
@@ -1,13 +1,18 @@
-Special Usage Model of the ACPI Control Method Lid Device
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
 
-Copyright (C) 2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
+=========================================================
+Special Usage Model of the ACPI Control Method Lid Device
+=========================================================
 
+:Copyright: |copy| 2016, Intel Corporation
 
-Abstract:
+:Author: Lv Zheng <lv.zheng@intel.com>
 
-Platforms containing lids convey lid state (open/close) to OSPMs using a
-control method lid device. To implement this, the AML tables issue
+Abstract
+========
+Platforms containing lids convey lid state (open/close) to OSPMs
+using a control method lid device. To implement this, the AML tables issue
 Notify(lid_device, 0x80) to notify the OSPMs whenever the lid state has
 changed. The _LID control method for the lid device must be implemented to
 report the "current" state of the lid as either "opened" or "closed".
@@ -19,7 +24,8 @@ taken into account. This document describes the restrictions and the
 expections of the Linux ACPI lid device driver.
 
 
-1. Restrictions of the returning value of the _LID control method
+Restrictions of the returning value of the _LID control method
+==============================================================
 
 The _LID control method is described to return the "current" lid state.
 However the word of "current" has ambiguity, some buggy AML tables return
@@ -30,7 +36,8 @@ initial returning value. When the AML tables implement this control method
 with cached value, the initial returning value is likely not reliable.
 There are platforms always retun "closed" as initial lid state.
 
-2. Restrictions of the lid state change notifications
+Restrictions of the lid state change notifications
+==================================================
 
 There are buggy AML tables never notifying when the lid device state is
 changed to "opened". Thus the "opened" notification is not guaranteed. But
@@ -39,18 +46,22 @@ state is changed to "closed". The "closed" notification is normally used to
 trigger some system power saving operations on Windows. Since it is fully
 tested, it is reliable from all AML tables.
 
-3. Expections for the userspace users of the ACPI lid device driver
+Expections for the userspace users of the ACPI lid device driver
+================================================================
 
 The ACPI button driver exports the lid state to the userspace via the
-following file:
+following file::
+
   /proc/acpi/button/lid/LID0/state
+
 This file actually calls the _LID control method described above. And given
 the previous explanation, it is not reliable enough on some platforms. So
 it is advised for the userspace program to not to solely rely on this file
 to determine the actual lid state.
 
 The ACPI button driver emits the following input event to the userspace:
-  SW_LID
+  * SW_LID
+
 The ACPI lid device driver is implemented to try to deliver the platform
 triggered events to the userspace. However, given the fact that the buggy
 firmware cannot make sure "opened"/"closed" events are paired, the ACPI
@@ -59,20 +70,25 @@ button driver uses the following 3 modes in order not to trigger issues.
 If the userspace hasn't been prepared to ignore the unreliable "opened"
 events and the unreliable initial state notification, Linux users can use
 the following kernel parameters to handle the possible issues:
+
 A. button.lid_init_state=method:
    When this option is specified, the ACPI button driver reports the
    initial lid state using the returning value of the _LID control method
    and whether the "opened"/"closed" events are paired fully relies on the
    firmware implementation.
+
    This option can be used to fix some platforms where the returning value
    of the _LID control method is reliable but the initial lid state
    notification is missing.
+
    This option is the default behavior during the period the userspace
    isn't ready to handle the buggy AML tables.
+
 B. button.lid_init_state=open:
    When this option is specified, the ACPI button driver always reports the
    initial lid state as "opened" and whether the "opened"/"closed" events
    are paired fully relies on the firmware implementation.
+
    This may fix some platforms where the returning value of the _LID
    control method is not reliable and the initial lid state notification is
    missing.
@@ -80,6 +96,7 @@ B. button.lid_init_state=open:
 If the userspace has been prepared to ignore the unreliable "opened" events
 and the unreliable initial state notification, Linux users should always
 use the following kernel parameter:
+
 C. button.lid_init_state=ignore:
    When this option is specified, the ACPI button driver never reports the
    initial lid state and there is a compensation mechanism implemented to
@@ -89,6 +106,7 @@ C. button.lid_init_state=ignore:
    notifications can be delivered to the userspace when the lid is actually
    opens given that some AML tables do not send "opened" notifications
    reliably.
+
    In this mode, if everything is correctly implemented by the platform
    firmware, the old userspace programs should still work. Otherwise, the
    new userspace programs are required to work with the ACPI button driver.
diff --git a/Documentation/firmware-guide/acpi/aml-debugger.rst b/Documentation/firmware-guide/acpi/aml-debugger.rst
new file mode 100644
index 000000000000..a889d43bc6c5
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/aml-debugger.rst
@@ -0,0 +1,75 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+================
+The AML Debugger
+================
+
+:Copyright: |copy| 2016, Intel Corporation
+:Author: Lv Zheng <lv.zheng@intel.com>
+
+
+This document describes the usage of the AML debugger embedded in the Linux
+kernel.
+
+1. Build the debugger
+=====================
+
+The following kernel configuration items are required to enable the AML
+debugger interface from the Linux kernel::
+
+   CONFIG_ACPI_DEBUGGER=y
+   CONFIG_ACPI_DEBUGGER_USER=m
+
+The userspace utilities can be built from the kernel source tree using
+the following commands::
+
+   $ cd tools
+   $ make acpi
+
+The resultant userspace tool binary is then located at::
+
+   tools/power/acpi/acpidbg
+
+It can be installed to system directories by running "make install" (as a
+sufficiently privileged user).
+
+2. Start the userspace debugger interface
+=========================================
+
+After booting the kernel with the debugger built-in, the debugger can be
+started by using the following commands::
+
+   # mount -t debugfs none /sys/kernel/debug
+   # modprobe acpi_dbg
+   # tools/power/acpi/acpidbg
+
+That spawns the interactive AML debugger environment where you can execute
+debugger commands.
+
+The commands are documented in the "ACPICA Overview and Programmer Reference"
+that can be downloaded from
+
+https://acpica.org/documentation
+
+The detailed debugger commands reference is located in Chapter 12 "ACPICA
+Debugger Reference".  The "help" command can be used for a quick reference.
+
+3. Stop the userspace debugger interface
+========================================
+
+The interactive debugger interface can be closed by pressing Ctrl+C or using
+the "quit" or "exit" commands.  When finished, unload the module with::
+
+   # rmmod acpi_dbg
+
+The module unloading may fail if there is an acpidbg instance running.
+
+4. Run the debugger in a script
+===============================
+
+It may be useful to run the AML debugger in a test script. "acpidbg" supports
+this in a special "batch" mode.  For example, the following command outputs
+the entire ACPI namespace::
+
+   # acpidbg -b "namespace"
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/firmware-guide/acpi/apei/einj.rst
index e550c8b98139..e588bccf5158 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/firmware-guide/acpi/apei/einj.rst
@@ -1,13 +1,16 @@
-			APEI Error INJection
-			~~~~~~~~~~~~~~~~~~~~
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+APEI Error INJection
+====================
 
 EINJ provides a hardware error injection mechanism. It is very useful
 for debugging and testing APEI and RAS features in general.
 
 You need to check whether your BIOS supports EINJ first. For that, look
-for early boot messages similar to this one:
+for early boot messages similar to this one::
 
-ACPI: EINJ 0x000000007370A000 000150 (v01 INTEL           00000001 INTL 00000001)
+  ACPI: EINJ 0x000000007370A000 000150 (v01 INTEL           00000001 INTL 00000001)
 
 which shows that the BIOS is exposing an EINJ table - it is the
 mechanism through which the injection is done.
@@ -23,11 +26,11 @@ order to see the APEI,EINJ,... functionality supported and exposed by
 the BIOS menu.
 
 To use EINJ, make sure the following are options enabled in your kernel
-configuration:
+configuration::
 
-CONFIG_DEBUG_FS
-CONFIG_ACPI_APEI
-CONFIG_ACPI_APEI_EINJ
+  CONFIG_DEBUG_FS
+  CONFIG_ACPI_APEI
+  CONFIG_ACPI_APEI_EINJ
 
 The EINJ user interface is in <debugfs mount point>/apei/einj.
 
@@ -37,20 +40,22 @@ The following files belong to it:
 
   This file shows which error types are supported:
 
+  ================  ===================================
   Error Type Value	Error Description
-  ================	=================
-  0x00000001		Processor Correctable
-  0x00000002		Processor Uncorrectable non-fatal
-  0x00000004		Processor Uncorrectable fatal
-  0x00000008		Memory Correctable
-  0x00000010		Memory Uncorrectable non-fatal
-  0x00000020		Memory Uncorrectable fatal
-  0x00000040		PCI Express Correctable
-  0x00000080		PCI Express Uncorrectable fatal
-  0x00000100		PCI Express Uncorrectable non-fatal
-  0x00000200		Platform Correctable
-  0x00000400		Platform Uncorrectable non-fatal
-  0x00000800		Platform Uncorrectable fatal
+  ================  ===================================
+  0x00000001        Processor Correctable
+  0x00000002        Processor Uncorrectable non-fatal
+  0x00000004        Processor Uncorrectable fatal
+  0x00000008        Memory Correctable
+  0x00000010        Memory Uncorrectable non-fatal
+  0x00000020        Memory Uncorrectable fatal
+  0x00000040        PCI Express Correctable
+  0x00000080        PCI Express Uncorrectable fatal
+  0x00000100        PCI Express Uncorrectable non-fatal
+  0x00000200        Platform Correctable
+  0x00000400        Platform Uncorrectable non-fatal
+  0x00000800        Platform Uncorrectable fatal
+  ================  ===================================
 
   The format of the file contents are as above, except present are only
   the available error types.
@@ -73,9 +78,12 @@ The following files belong to it:
   injection. Value is a bitmask as specified in ACPI5.0 spec for the
   SET_ERROR_TYPE_WITH_ADDRESS data structure:
 
-	Bit 0 - Processor APIC field valid (see param3 below).
-	Bit 1 - Memory address and mask valid (param1 and param2).
-	Bit 2 - PCIe (seg,bus,dev,fn) valid (see param4 below).
+    Bit 0
+      Processor APIC field valid (see param3 below).
+    Bit 1
+      Memory address and mask valid (param1 and param2).
+    Bit 2
+      PCIe (seg,bus,dev,fn) valid (see param4 below).
 
   If set to zero, legacy behavior is mimicked where the type of
   injection specifies just one bit set, and param1 is multiplexed.
@@ -121,7 +129,7 @@ BIOS versions based on the ACPI 5.0 specification have more control over
 the target of the injection. For processor-related errors (type 0x1, 0x2
 and 0x4), you can set flags to 0x3 (param3 for bit 0, and param1 and
 param2 for bit 1) so that you have more information added to the error
-signature being injected. The actual data passed is this:
+signature being injected. The actual data passed is this::
 
 	memory_address = param1;
 	memory_address_range = param2;
@@ -131,7 +139,7 @@ signature being injected. The actual data passed is this:
 For memory errors (type 0x8, 0x10 and 0x20) the address is set using
 param1 with a mask in param2 (0x0 is equivalent to all ones). For PCI
 express errors (type 0x40, 0x80 and 0x100) the segment, bus, device and
-function are specified using param1:
+function are specified using param1::
 
          31     24 23    16 15    11 10      8  7        0
 	+-------------------------------------------------+
@@ -152,26 +160,26 @@ documentation for details (and expect changes to this API if vendors
 creativity in using this feature expands beyond our expectations).
 
 
-An error injection example:
+An error injection example::
 
-# cd /sys/kernel/debug/apei/einj
-# cat available_error_type		# See which errors can be injected
-0x00000002	Processor Uncorrectable non-fatal
-0x00000008	Memory Correctable
-0x00000010	Memory Uncorrectable non-fatal
-# echo 0x12345000 > param1		# Set memory address for injection
-# echo $((-1 << 12)) > param2		# Mask 0xfffffffffffff000 - anywhere in this page
-# echo 0x8 > error_type			# Choose correctable memory error
-# echo 1 > error_inject			# Inject now
+  # cd /sys/kernel/debug/apei/einj
+  # cat available_error_type		# See which errors can be injected
+  0x00000002	Processor Uncorrectable non-fatal
+  0x00000008	Memory Correctable
+  0x00000010	Memory Uncorrectable non-fatal
+  # echo 0x12345000 > param1		# Set memory address for injection
+  # echo $((-1 << 12)) > param2		# Mask 0xfffffffffffff000 - anywhere in this page
+  # echo 0x8 > error_type			# Choose correctable memory error
+  # echo 1 > error_inject			# Inject now
 
-You should see something like this in dmesg:
+You should see something like this in dmesg::
 
-[22715.830801] EDAC sbridge MC3: HANDLING MCE MEMORY ERROR
-[22715.834759] EDAC sbridge MC3: CPU 0: Machine Check Event: 0 Bank 7: 8c00004000010090
-[22715.834759] EDAC sbridge MC3: TSC 0
-[22715.834759] EDAC sbridge MC3: ADDR 12345000 EDAC sbridge MC3: MISC 144780c86
-[22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0
-[22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 -  area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0)
+  [22715.830801] EDAC sbridge MC3: HANDLING MCE MEMORY ERROR
+  [22715.834759] EDAC sbridge MC3: CPU 0: Machine Check Event: 0 Bank 7: 8c00004000010090
+  [22715.834759] EDAC sbridge MC3: TSC 0
+  [22715.834759] EDAC sbridge MC3: ADDR 12345000 EDAC sbridge MC3: MISC 144780c86
+  [22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0
+  [22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 -  area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0)
 
 For more information about EINJ, please refer to ACPI specification
 version 4.0, section 17.5 and ACPI 5.0, section 18.6.
diff --git a/Documentation/firmware-guide/acpi/apei/output_format.rst b/Documentation/firmware-guide/acpi/apei/output_format.rst
new file mode 100644
index 000000000000..c2e7ebddb529
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/apei/output_format.rst
@@ -0,0 +1,150 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+APEI output format
+==================
+
+APEI uses printk as hardware error reporting interface, the output
+format is as follow::
+
+        <error record> :=
+        APEI generic hardware error status
+        severity: <integer>, <severity string>
+        section: <integer>, severity: <integer>, <severity string>
+        flags: <integer>
+        <section flags strings>
+        fru_id: <uuid string>
+        fru_text: <string>
+        section_type: <section type string>
+        <section data>
+
+        <severity string>* := recoverable | fatal | corrected | info
+
+        <section flags strings># :=
+        [primary][, containment warning][, reset][, threshold exceeded]\
+        [, resource not accessible][, latent error]
+
+        <section type string> := generic processor error | memory error | \
+        PCIe error | unknown, <uuid string>
+
+        <section data> :=
+        <generic processor section data> | <memory section data> | \
+        <pcie section data> | <null>
+
+        <generic processor section data> :=
+        [processor_type: <integer>, <proc type string>]
+        [processor_isa: <integer>, <proc isa string>]
+        [error_type: <integer>
+        <proc error type strings>]
+        [operation: <integer>, <proc operation string>]
+        [flags: <integer>
+        <proc flags strings>]
+        [level: <integer>]
+        [version_info: <integer>]
+        [processor_id: <integer>]
+        [target_address: <integer>]
+        [requestor_id: <integer>]
+        [responder_id: <integer>]
+        [IP: <integer>]
+
+        <proc type string>* := IA32/X64 | IA64
+
+        <proc isa string>* := IA32 | IA64 | X64
+
+        <processor error type strings># :=
+        [cache error][, TLB error][, bus error][, micro-architectural error]
+
+        <proc operation string>* := unknown or generic | data read | data write | \
+        instruction execution
+
+        <proc flags strings># :=
+        [restartable][, precise IP][, overflow][, corrected]
+
+        <memory section data> :=
+        [error_status: <integer>]
+        [physical_address: <integer>]
+        [physical_address_mask: <integer>]
+        [node: <integer>]
+        [card: <integer>]
+        [module: <integer>]
+        [bank: <integer>]
+        [device: <integer>]
+        [row: <integer>]
+        [column: <integer>]
+        [bit_position: <integer>]
+        [requestor_id: <integer>]
+        [responder_id: <integer>]
+        [target_id: <integer>]
+        [error_type: <integer>, <mem error type string>]
+
+        <mem error type string>* :=
+        unknown | no error | single-bit ECC | multi-bit ECC | \
+        single-symbol chipkill ECC | multi-symbol chipkill ECC | master abort | \
+        target abort | parity error | watchdog timeout | invalid address | \
+        mirror Broken | memory sparing | scrub corrected error | \
+        scrub uncorrected error
+
+        <pcie section data> :=
+        [port_type: <integer>, <pcie port type string>]
+        [version: <integer>.<integer>]
+        [command: <integer>, status: <integer>]
+        [device_id: <integer>:<integer>:<integer>.<integer>
+        slot: <integer>
+        secondary_bus: <integer>
+        vendor_id: <integer>, device_id: <integer>
+        class_code: <integer>]
+        [serial number: <integer>, <integer>]
+        [bridge: secondary_status: <integer>, control: <integer>]
+        [aer_status: <integer>, aer_mask: <integer>
+        <aer status string>
+        [aer_uncor_severity: <integer>]
+        aer_layer=<aer layer string>, aer_agent=<aer agent string>
+        aer_tlp_header: <integer> <integer> <integer> <integer>]
+
+        <pcie port type string>* := PCIe end point | legacy PCI end point | \
+        unknown | unknown | root port | upstream switch port | \
+        downstream switch port | PCIe to PCI/PCI-X bridge | \
+        PCI/PCI-X to PCIe bridge | root complex integrated endpoint device | \
+        root complex event collector
+
+        if section severity is fatal or recoverable
+        <aer status string># :=
+        unknown | unknown | unknown | unknown | Data Link Protocol | \
+        unknown | unknown | unknown | unknown | unknown | unknown | unknown | \
+        Poisoned TLP | Flow Control Protocol | Completion Timeout | \
+        Completer Abort | Unexpected Completion | Receiver Overflow | \
+        Malformed TLP | ECRC | Unsupported Request
+        else
+        <aer status string># :=
+        Receiver Error | unknown | unknown | unknown | unknown | unknown | \
+        Bad TLP | Bad DLLP | RELAY_NUM Rollover | unknown | unknown | unknown | \
+        Replay Timer Timeout | Advisory Non-Fatal
+        fi
+
+        <aer layer string> :=
+        Physical Layer | Data Link Layer | Transaction Layer
+
+        <aer agent string> :=
+        Receiver ID | Requester ID | Completer ID | Transmitter ID
+
+Where, [] designate corresponding content is optional
+
+All <field string> description with * has the following format::
+
+        field: <integer>, <field string>
+
+Where value of <integer> should be the position of "string" in <field
+string> description. Otherwise, <field string> will be "unknown".
+
+All <field strings> description with # has the following format::
+
+        field: <integer>
+        <field strings>
+
+Where each string in <fields strings> corresponding to one set bit of
+<integer>. The bit position is the position of "string" in <field
+strings> description.
+
+For more detailed explanation of every field, please refer to UEFI
+specification version 2.3 or later, section Appendix N: Common
+Platform Error Record.
diff --git a/Documentation/acpi/debug.txt b/Documentation/firmware-guide/acpi/debug.rst
index 65bf47c46b6d..1a152dd1d765 100644
--- a/Documentation/acpi/debug.txt
+++ b/Documentation/firmware-guide/acpi/debug.rst
@@ -1,18 +1,21 @@
-			ACPI Debug Output
+.. SPDX-License-Identifier: GPL-2.0
 
+=================
+ACPI Debug Output
+=================
 
 The ACPI CA, the Linux ACPI core, and some ACPI drivers can generate debug
 output.  This document describes how to use this facility.
 
 Compile-time configuration
---------------------------
+==========================
 
 ACPI debug output is globally enabled by CONFIG_ACPI_DEBUG.  If this config
 option is turned off, the debug messages are not even built into the
 kernel.
 
 Boot- and run-time configuration
---------------------------------
+================================
 
 When CONFIG_ACPI_DEBUG=y, you can select the component and level of messages
 you're interested in.  At boot-time, use the acpi.debug_layer and
@@ -21,7 +24,7 @@ debug_layer and debug_level files in /sys/module/acpi/parameters/ to control
 the debug messages.
 
 debug_layer (component)
------------------------
+=======================
 
 The "debug_layer" is a mask that selects components of interest, e.g., a
 specific driver or part of the ACPI interpreter.  To build the debug_layer
@@ -33,7 +36,7 @@ to /sys/module/acpi/parameters/debug_layer.
 
 The possible components are defined in include/acpi/acoutput.h and
 include/acpi/acpi_drivers.h.  Reading /sys/module/acpi/parameters/debug_layer
-shows the supported mask values, currently these:
+shows the supported mask values, currently these::
 
     ACPI_UTILITIES                  0x00000001
     ACPI_HARDWARE                   0x00000002
@@ -65,7 +68,7 @@ shows the supported mask values, currently these:
     ACPI_PROCESSOR_COMPONENT        0x20000000
 
 debug_level
------------
+===========
 
 The "debug_level" is a mask that selects different types of messages, e.g.,
 those related to initialization, method execution, informational messages, etc.
@@ -81,7 +84,7 @@ to /sys/module/acpi/parameters/debug_level.
 
 The possible levels are defined in include/acpi/acoutput.h.  Reading
 /sys/module/acpi/parameters/debug_level shows the supported mask values,
-currently these:
+currently these::
 
     ACPI_LV_INIT                    0x00000001
     ACPI_LV_DEBUG_OBJECT            0x00000002
@@ -113,9 +116,9 @@ currently these:
     ACPI_LV_EVENTS                  0x80000000
 
 Examples
---------
+========
 
-For example, drivers/acpi/bus.c contains this:
+For example, drivers/acpi/bus.c contains this::
 
     #define _COMPONENT              ACPI_BUS_COMPONENT
     ...
@@ -127,22 +130,22 @@ statement uses ACPI_DB_INFO, which is macro based on the ACPI_LV_INFO
 definition.)
 
 Enable all AML "Debug" output (stores to the Debug object while interpreting
-AML) during boot:
+AML) during boot::
 
     acpi.debug_layer=0xffffffff acpi.debug_level=0x2
 
-Enable PCI and PCI interrupt routing debug messages:
+Enable PCI and PCI interrupt routing debug messages::
 
     acpi.debug_layer=0x400000 acpi.debug_level=0x4
 
-Enable all ACPI hardware-related messages:
+Enable all ACPI hardware-related messages::
 
     acpi.debug_layer=0x2 acpi.debug_level=0xffffffff
 
-Enable all ACPI_DB_INFO messages after boot:
+Enable all ACPI_DB_INFO messages after boot::
 
     # echo 0x4 > /sys/module/acpi/parameters/debug_level
 
-Show all valid component values:
+Show all valid component values::
 
     # cat /sys/module/acpi/parameters/debug_layer
diff --git a/Documentation/acpi/dsd/data-node-references.txt b/Documentation/firmware-guide/acpi/dsd/data-node-references.rst
index c3871565c8cf..1351984e767c 100644
--- a/Documentation/acpi/dsd/data-node-references.txt
+++ b/Documentation/firmware-guide/acpi/dsd/data-node-references.rst
@@ -1,9 +1,12 @@
-Copyright (C) 2018 Intel Corporation
-Author: Sakari Ailus <sakari.ailus@linux.intel.com>
-
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
 
+===================================
 Referencing hierarchical data nodes
------------------------------------
+===================================
+
+:Copyright: |copy| 2018 Intel Corporation
+:Author: Sakari Ailus <sakari.ailus@linux.intel.com>
 
 ACPI in general allows referring to device objects in the tree only.
 Hierarchical data extension nodes may not be referred to directly, hence this
@@ -28,13 +31,14 @@ extension key.
 
 
 Example
--------
+=======
 
-	In the ASL snippet below, the "reference" _DSD property [2] contains a
-	device object reference to DEV0 and under that device object, a
-	hierarchical data extension key "node@1" referring to the NOD1 object
-	and lastly, a hierarchical data extension key "anothernode" referring to
-	the ANOD object which is also the final target node of the reference.
+In the ASL snippet below, the "reference" _DSD property [2] contains a
+device object reference to DEV0 and under that device object, a
+hierarchical data extension key "node@1" referring to the NOD1 object
+and lastly, a hierarchical data extension key "anothernode" referring to
+the ANOD object which is also the final target node of the reference.
+::
 
 	Device (DEV0)
 	{
@@ -75,15 +79,15 @@ Example
 	    })
 	}
 
-Please also see a graph example in graph.txt .
+Please also see a graph example in :doc:`graph`.
 
 References
-----------
+==========
 
 [1] Hierarchical Data Extension UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
-    referenced 2018-07-17.
+<http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+referenced 2018-07-17.
 
 [2] Device Properties UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
-    referenced 2016-10-04.
+<http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+referenced 2016-10-04.
diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/firmware-guide/acpi/dsd/graph.rst
index b9ce910781dc..e0baed35b037 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/firmware-guide/acpi/dsd/graph.rst
@@ -1,8 +1,11 @@
-Graphs
+.. SPDX-License-Identifier: GPL-2.0
 
+======
+Graphs
+======
 
 _DSD
-----
+====
 
 _DSD (Device Specific Data) [7] is a predefined ACPI device
 configuration object that can be used to convey information on
@@ -30,7 +33,7 @@ hierarchical data extension array on each depth.
 
 
 Ports and endpoints
--------------------
+===================
 
 The port and endpoint concepts are very similar to those in Devicetree
 [3]. A port represents an interface in a device, and an endpoint
@@ -38,9 +41,9 @@ represents a connection to that interface.
 
 All port nodes are located under the device's "_DSD" node in the hierarchical
 data extension tree. The data extension related to each port node must begin
-with "port" and must be followed by the "@" character and the number of the port
-as its key. The target object it refers to should be called "PRTX", where "X" is
-the number of the port. An example of such a package would be:
+with "port" and must be followed by the "@" character and the number of the
+port as its key. The target object it refers to should be called "PRTX", where
+"X" is the number of the port. An example of such a package would be::
 
     Package() { "port@4", PRT4 }
 
@@ -49,7 +52,7 @@ data extension key of the endpoint nodes must begin with
 "endpoint" and must be followed by the "@" character and the number of the
 endpoint. The object it refers to should be called "EPXY", where "X" is the
 number of the port and "Y" is the number of the endpoint. An example of such a
-package would be:
+package would be::
 
     Package() { "endpoint@0", EP40 }
 
@@ -62,85 +65,85 @@ of that port shall be zero. Similarly, if a port may only have a single
 endpoint, the number of that endpoint shall be zero.
 
 The endpoint reference uses property extension with "remote-endpoint" property
-name followed by a reference in the same package. Such references consist of the
+name followed by a reference in the same package. Such references consist of
 the remote device reference, the first package entry of the port data extension
 reference under the device and finally the first package entry of the endpoint
-data extension reference under the port. Individual references thus appear as:
+data extension reference under the port. Individual references thus appear as::
 
     Package() { device, "port@X", "endpoint@Y" }
 
-In the above example, "X" is the number of the port and "Y" is the number of the
-endpoint.
+In the above example, "X" is the number of the port and "Y" is the number of
+the endpoint.
 
 The references to endpoints must be always done both ways, to the
 remote endpoint and back from the referred remote endpoint node.
 
-A simple example of this is show below:
+A simple example of this is show below::
 
     Scope (\_SB.PCI0.I2C2)
     {
-	Device (CAM0)
-	{
-	    Name (_DSD, Package () {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "compatible", Package () { "nokia,smia" } },
-		},
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "port@0", PRT0 },
-		}
-	    })
-	    Name (PRT0, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 0 },
-		},
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "endpoint@0", EP00 },
-		}
-	    })
-	    Name (EP00, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 0 },
-		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, "port@4", "endpoint@0" } },
-		}
-	    })
-	}
+        Device (CAM0)
+        {
+            Name (_DSD, Package () {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "compatible", Package () { "nokia,smia" } },
+                },
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "port@0", PRT0 },
+                }
+            })
+            Name (PRT0, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 0 },
+                },
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "endpoint@0", EP00 },
+                }
+            })
+            Name (EP00, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 0 },
+                    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, "port@4", "endpoint@0" } },
+                }
+            })
+        }
     }
 
     Scope (\_SB.PCI0)
     {
-	Device (ISP)
-	{
-	    Name (_DSD, Package () {
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "port@4", PRT4 },
-		}
-	    })
-
-	    Name (PRT4, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 4 }, /* CSI-2 port number */
-		},
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "endpoint@0", EP40 },
-		}
-	    })
-
-	    Name (EP40, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 0 },
-		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, "port@0", "endpoint@0" } },
-		}
-	    })
-	}
+        Device (ISP)
+        {
+            Name (_DSD, Package () {
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "port@4", PRT4 },
+                }
+            })
+
+            Name (PRT4, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 4 }, /* CSI-2 port number */
+                },
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "endpoint@0", EP40 },
+                }
+            })
+
+            Name (EP40, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 0 },
+                    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, "port@0", "endpoint@0" } },
+                }
+            })
+        }
     }
 
 Here, the port 0 of the "CAM0" device is connected to the port 4 of
@@ -148,27 +151,27 @@ the "ISP" device and vice versa.
 
 
 References
-----------
+==========
 
 [1] _DSD (Device Specific Data) Implementation Guide.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel-1_1.htm>,
+    http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel-1_1.htm,
     referenced 2016-10-03.
 
-[2] Devicetree. <URL:http://www.devicetree.org>, referenced 2016-10-03.
+[2] Devicetree. http://www.devicetree.org, referenced 2016-10-03.
 
 [3] Documentation/devicetree/bindings/graph.txt
 
 [4] Device Properties UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+    http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf,
     referenced 2016-10-04.
 
 [5] Hierarchical Data Extension UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+    http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf,
     referenced 2016-10-04.
 
 [6] Advanced Configuration and Power Interface Specification.
-    <URL:http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf>,
+    http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf,
     referenced 2016-10-04.
 
 [7] _DSD Device Properties Usage Rules.
-    Documentation/acpi/DSD-properties-rules.txt
+    :doc:`../DSD-properties-rules`
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/firmware-guide/acpi/enumeration.rst
index 7bcf9c3d9fbe..6b32b7be8c85 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/firmware-guide/acpi/enumeration.rst
@@ -1,5 +1,9 @@
-ACPI based device enumeration
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+.. SPDX-License-Identifier: GPL-2.0
+
+=============================
+ACPI Based Device Enumeration
+=============================
+
 ACPI 5 introduced a set of new resources (UartTSerialBus, I2cSerialBus,
 SpiSerialBus, GpioIo and GpioInt) which can be used in enumerating slave
 devices behind serial bus controllers.
@@ -11,12 +15,12 @@ that are accessed through memory-mapped registers.
 In order to support this and re-use the existing drivers as much as
 possible we decided to do following:
 
-	o Devices that have no bus connector resource are represented as
-	  platform devices.
+  - Devices that have no bus connector resource are represented as
+    platform devices.
 
-	o Devices behind real busses where there is a connector resource
-	  are represented as struct spi_device or struct i2c_device
-	  (standard UARTs are not busses so there is no struct uart_device).
+  - Devices behind real busses where there is a connector resource
+    are represented as struct spi_device or struct i2c_device
+    (standard UARTs are not busses so there is no struct uart_device).
 
 As both ACPI and Device Tree represent a tree of devices (and their
 resources) this implementation follows the Device Tree way as much as
@@ -31,7 +35,8 @@ enumerated from ACPI namespace. This handle can be used to extract other
 device-specific configuration. There is an example of this below.
 
 Platform bus support
-~~~~~~~~~~~~~~~~~~~~
+====================
+
 Since we are using platform devices to represent devices that are not
 connected to any physical bus we only need to implement a platform driver
 for the device and add supported ACPI IDs. If this same IP-block is used on
@@ -39,7 +44,7 @@ some other non-ACPI platform, the driver might work out of the box or needs
 some minor changes.
 
 Adding ACPI support for an existing driver should be pretty
-straightforward. Here is the simplest example:
+straightforward. Here is the simplest example::
 
 	#ifdef CONFIG_ACPI
 	static const struct acpi_device_id mydrv_acpi_match[] = {
@@ -61,12 +66,13 @@ configuring GPIOs it can get its ACPI handle and extract this information
 from ACPI tables.
 
 DMA support
-~~~~~~~~~~~
+===========
+
 DMA controllers enumerated via ACPI should be registered in the system to
 provide generic access to their resources. For example, a driver that would
 like to be accessible to slave devices via generic API call
 dma_request_slave_channel() must register itself at the end of the probe
-function like this:
+function like this::
 
 	err = devm_acpi_dma_controller_register(dev, xlate_func, dw);
 	/* Handle the error if it's not a case of !CONFIG_ACPI */
@@ -74,7 +80,7 @@ function like this:
 and implement custom xlate function if needed (usually acpi_dma_simple_xlate()
 is enough) which converts the FixedDMA resource provided by struct
 acpi_dma_spec into the corresponding DMA channel. A piece of code for that case
-could look like:
+could look like::
 
 	#ifdef CONFIG_ACPI
 	struct filter_args {
@@ -114,7 +120,7 @@ provided by struct acpi_dma.
 Clients must call dma_request_slave_channel() with the string parameter that
 corresponds to a specific FixedDMA resource. By default "tx" means the first
 entry of the FixedDMA resource array, "rx" means the second entry. The table
-below shows a layout:
+below shows a layout::
 
 	Device (I2C0)
 	{
@@ -138,12 +144,13 @@ acpi_dma_request_slave_chan_by_index() directly and therefore choose the
 specific FixedDMA resource by its index.
 
 SPI serial bus support
-~~~~~~~~~~~~~~~~~~~~~~
+======================
+
 Slave devices behind SPI bus have SpiSerialBus resource attached to them.
 This is extracted automatically by the SPI core and the slave devices are
 enumerated once spi_register_master() is called by the bus driver.
 
-Here is what the ACPI namespace for a SPI slave might look like:
+Here is what the ACPI namespace for a SPI slave might look like::
 
 	Device (EEP0)
 	{
@@ -163,7 +170,7 @@ Here is what the ACPI namespace for a SPI slave might look like:
 
 The SPI device drivers only need to add ACPI IDs in a similar way than with
 the platform device drivers. Below is an example where we add ACPI support
-to at25 SPI eeprom driver (this is meant for the above ACPI snippet):
+to at25 SPI eeprom driver (this is meant for the above ACPI snippet)::
 
 	#ifdef CONFIG_ACPI
 	static const struct acpi_device_id at25_acpi_match[] = {
@@ -182,7 +189,7 @@ to at25 SPI eeprom driver (this is meant for the above ACPI snippet):
 
 Note that this driver actually needs more information like page size of the
 eeprom etc. but at the time writing this there is no standard way of
-passing those. One idea is to return this in _DSM method like:
+passing those. One idea is to return this in _DSM method like::
 
 	Device (EEP0)
 	{
@@ -202,7 +209,7 @@ passing those. One idea is to return this in _DSM method like:
 		}
 
 Then the at25 SPI driver can get this configuration by calling _DSM on its
-ACPI handle like:
+ACPI handle like::
 
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct acpi_object_list input;
@@ -220,14 +227,15 @@ ACPI handle like:
 	kfree(output.pointer);
 
 I2C serial bus support
-~~~~~~~~~~~~~~~~~~~~~~
+======================
+
 The slaves behind I2C bus controller only need to add the ACPI IDs like
 with the platform and SPI drivers. The I2C core automatically enumerates
 any slave devices behind the controller device once the adapter is
 registered.
 
 Below is an example of how to add ACPI support to the existing mpu3050
-input driver:
+input driver::
 
 	#ifdef CONFIG_ACPI
 	static const struct acpi_device_id mpu3050_acpi_match[] = {
@@ -251,56 +259,57 @@ input driver:
 	};
 
 GPIO support
-~~~~~~~~~~~~
+============
+
 ACPI 5 introduced two new resources to describe GPIO connections: GpioIo
 and GpioInt. These resources can be used to pass GPIO numbers used by
 the device to the driver. ACPI 5.1 extended this with _DSD (Device
 Specific Data) which made it possible to name the GPIOs among other things.
 
-For example:
+For example::
 
-Device (DEV)
-{
-	Method (_CRS, 0, NotSerialized)
+	Device (DEV)
 	{
-		Name (SBUF, ResourceTemplate()
+		Method (_CRS, 0, NotSerialized)
 		{
-			...
-			// Used to power on/off the device
-			GpioIo (Exclusive, PullDefault, 0x0000, 0x0000,
-				IoRestrictionOutputOnly, "\\_SB.PCI0.GPI0",
-				0x00, ResourceConsumer,,)
+			Name (SBUF, ResourceTemplate()
 			{
-				// Pin List
-				0x0055
-			}
+				...
+				// Used to power on/off the device
+				GpioIo (Exclusive, PullDefault, 0x0000, 0x0000,
+					IoRestrictionOutputOnly, "\\_SB.PCI0.GPI0",
+					0x00, ResourceConsumer,,)
+				{
+					// Pin List
+					0x0055
+				}
+
+				// Interrupt for the device
+				GpioInt (Edge, ActiveHigh, ExclusiveAndWake, PullNone,
+					0x0000, "\\_SB.PCI0.GPI0", 0x00, ResourceConsumer,,)
+				{
+					// Pin list
+					0x0058
+				}
+
+				...
 
-			// Interrupt for the device
-			GpioInt (Edge, ActiveHigh, ExclusiveAndWake, PullNone,
-				 0x0000, "\\_SB.PCI0.GPI0", 0x00, ResourceConsumer,,)
-			{
-				// Pin list
-				0x0058
 			}
 
-			...
-
+			Return (SBUF)
 		}
 
-		Return (SBUF)
-	}
-
-	// ACPI 5.1 _DSD used for naming the GPIOs
-	Name (_DSD, Package ()
-	{
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package ()
+		// ACPI 5.1 _DSD used for naming the GPIOs
+		Name (_DSD, Package ()
 		{
-			Package () {"power-gpios", Package() {^DEV, 0, 0, 0 }},
-			Package () {"irq-gpios", Package() {^DEV, 1, 0, 0 }},
-		}
-	})
-	...
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package ()
+			{
+				Package () {"power-gpios", Package() {^DEV, 0, 0, 0 }},
+				Package () {"irq-gpios", Package() {^DEV, 1, 0, 0 }},
+			}
+		})
+		...
 
 These GPIO numbers are controller relative and path "\\_SB.PCI0.GPI0"
 specifies the path to the controller. In order to use these GPIOs in Linux
@@ -310,7 +319,7 @@ There is a standard GPIO API for that and is documented in
 Documentation/gpio/.
 
 In the above example we can get the corresponding two GPIO descriptors with
-a code like this:
+a code like this::
 
 	#include <linux/gpio/consumer.h>
 	...
@@ -334,21 +343,22 @@ See Documentation/acpi/gpio-properties.txt for more information about the
 _DSD binding related to GPIOs.
 
 MFD devices
-~~~~~~~~~~~
+===========
+
 The MFD devices register their children as platform devices. For the child
 devices there needs to be an ACPI handle that they can use to reference
 parts of the ACPI namespace that relate to them. In the Linux MFD subsystem
 we provide two ways:
 
-	o The children share the parent ACPI handle.
-	o The MFD cell can specify the ACPI id of the device.
+  - The children share the parent ACPI handle.
+  - The MFD cell can specify the ACPI id of the device.
 
 For the first case, the MFD drivers do not need to do anything. The
 resulting child platform device will have its ACPI_COMPANION() set to point
 to the parent device.
 
 If the ACPI namespace has a device that we can match using an ACPI id or ACPI
-adr, the cell should be set like:
+adr, the cell should be set like::
 
 	static struct mfd_cell_acpi_match my_subdevice_cell_acpi_match = {
 		.pnpid = "XYZ0001",
@@ -366,7 +376,8 @@ the MFD device and if found, that ACPI companion device is bound to the
 resulting child platform device.
 
 Device Tree namespace link device ID
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+====================================
+
 The Device Tree protocol uses device identification based on the "compatible"
 property whose value is a string or an array of strings recognized as device
 identifiers by drivers and the driver core.  The set of all those strings may be
@@ -410,6 +421,32 @@ Specifically, the device IDs returned by _HID and preceding PRP0001 in the _CID
 return package will be checked first.  Also in that case the bus type the device
 will be enumerated to depends on the device ID returned by _HID.
 
+For example, the following ACPI sample might be used to enumerate an lm75-type
+I2C temperature sensor and match it to the driver using the Device Tree
+namespace link:
+
+	Device (TMP0)
+	{
+		Name (_HID, "PRP0001")
+		Name (_DSD, Package() {
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package () {
+				Package (2) { "compatible", "ti,tmp75" },
+			}
+		})
+		Method (_CRS, 0, Serialized)
+		{
+			Name (SBUF, ResourceTemplate ()
+			{
+				I2cSerialBusV2 (0x48, ControllerInitiated,
+					400000, AddressingMode7Bit,
+					"\\_SB.PCI0.I2C1", 0x00,
+					ResourceConsumer, , Exclusive,)
+			})
+			Return (SBUF)
+		}
+	}
+
 It is valid to define device objects with a _HID returning PRP0001 and without
 the "compatible" property in the _DSD or a _CID as long as one of their
 ancestors provides a _DSD with a valid "compatible" property.  Such device
@@ -423,4 +460,4 @@ the _DSD of the device object itself or the _DSD of its ancestor in the
 Otherwise, the _DSD itself is regarded as invalid and therefore the "compatible"
 property returned by it is meaningless.
 
-Refer to DSD-properties-rules.txt for more information.
+Refer to :doc:`DSD-properties-rules` for more information.
diff --git a/Documentation/acpi/gpio-properties.txt b/Documentation/firmware-guide/acpi/gpio-properties.rst
index 88c65cb5bf0a..bb6d74f23ee0 100644
--- a/Documentation/acpi/gpio-properties.txt
+++ b/Documentation/firmware-guide/acpi/gpio-properties.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================================
 _DSD Device Properties Related to GPIO
---------------------------------------
+======================================
 
 With the release of ACPI 5.1, the _DSD configuration object finally
 allows names to be given to GPIOs (and other things as well) returned
@@ -8,7 +11,7 @@ the corresponding GPIO, which is pretty error prone (it depends on
 the _CRS output ordering, for example).
 
 With _DSD we can now query GPIOs using a name instead of an integer
-index, like the ASL example below shows:
+index, like the ASL example below shows::
 
   // Bluetooth device with reset and shutdown GPIOs
   Device (BTH)
@@ -34,15 +37,19 @@ index, like the ASL example below shows:
       })
   }
 
-The format of the supported GPIO property is:
+The format of the supported GPIO property is::
 
   Package () { "name", Package () { ref, index, pin, active_low }}
 
-  ref - The device that has _CRS containing GpioIo()/GpioInt() resources,
-        typically this is the device itself (BTH in our case).
-  index - Index of the GpioIo()/GpioInt() resource in _CRS starting from zero.
-  pin - Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
-  active_low - If 1 the GPIO is marked as active_low.
+ref
+  The device that has _CRS containing GpioIo()/GpioInt() resources,
+  typically this is the device itself (BTH in our case).
+index
+  Index of the GpioIo()/GpioInt() resource in _CRS starting from zero.
+pin
+  Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
+active_low
+  If 1 the GPIO is marked as active_low.
 
 Since ACPI GpioIo() resource does not have a field saying whether it is
 active low or high, the "active_low" argument can be used here.  Setting
@@ -55,7 +62,7 @@ It is possible to leave holes in the array of GPIOs. This is useful in
 cases like with SPI host controllers where some chip selects may be
 implemented as GPIOs and some as native signals. For example a SPI host
 controller can have chip selects 0 and 2 implemented as GPIOs and 1 as
-native:
+native::
 
   Package () {
       "cs-gpios",
@@ -67,7 +74,7 @@ native:
   }
 
 Other supported properties
---------------------------
+==========================
 
 Following Device Tree compatible device properties are also supported by
 _DSD device properties for GPIO controllers:
@@ -78,7 +85,7 @@ _DSD device properties for GPIO controllers:
 - input
 - line-name
 
-Example:
+Example::
 
   Name (_DSD, Package () {
       // _DSD Hierarchical Properties Extension UUID
@@ -100,7 +107,7 @@ Example:
 
 - gpio-line-names
 
-Example:
+Example::
 
   Package () {
       "gpio-line-names",
@@ -114,7 +121,7 @@ See Documentation/devicetree/bindings/gpio/gpio.txt for more information
 about these properties.
 
 ACPI GPIO Mappings Provided by Drivers
---------------------------------------
+======================================
 
 There are systems in which the ACPI tables do not contain _DSD but provide _CRS
 with GpioIo()/GpioInt() resources and device drivers still need to work with
@@ -139,16 +146,16 @@ line in that resource starting from zero, and the active-low flag for that line,
 respectively, in analogy with the _DSD GPIO property format specified above.
 
 For the example Bluetooth device discussed previously the data structures in
-question would look like this:
+question would look like this::
 
-static const struct acpi_gpio_params reset_gpio = { 1, 1, false };
-static const struct acpi_gpio_params shutdown_gpio = { 0, 0, false };
+  static const struct acpi_gpio_params reset_gpio = { 1, 1, false };
+  static const struct acpi_gpio_params shutdown_gpio = { 0, 0, false };
 
-static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
-  { "reset-gpios", &reset_gpio, 1 },
-  { "shutdown-gpios", &shutdown_gpio, 1 },
-  { },
-};
+  static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
+    { "reset-gpios", &reset_gpio, 1 },
+    { "shutdown-gpios", &shutdown_gpio, 1 },
+    { },
+  };
 
 Next, the mapping table needs to be passed as the second argument to
 acpi_dev_add_driver_gpios() that will register it with the ACPI device object
@@ -158,12 +165,12 @@ calling acpi_dev_remove_driver_gpios() on the ACPI device object where that
 table was previously registered.
 
 Using the _CRS fallback
------------------------
+=======================
 
 If a device does not have _DSD or the driver does not create ACPI GPIO
 mapping, the Linux GPIO framework refuses to return any GPIOs. This is
 because the driver does not know what it actually gets. For example if we
-have a device like below:
+have a device like below::
 
   Device (BTH)
   {
@@ -177,7 +184,7 @@ have a device like below:
       })
   }
 
-The driver might expect to get the right GPIO when it does:
+The driver might expect to get the right GPIO when it does::
 
   desc = gpiod_get(dev, "reset", GPIOD_OUT_LOW);
 
@@ -193,22 +200,25 @@ the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain
 objects, as listed in the above chapter, of the device in question.
 
 Getting GPIO descriptor
------------------------
+=======================
+
+There are two main approaches to get GPIO resource from ACPI::
 
-There are two main approaches to get GPIO resource from ACPI:
-	desc = gpiod_get(dev, connection_id, flags);
-	desc = gpiod_get_index(dev, connection_id, index, flags);
+  desc = gpiod_get(dev, connection_id, flags);
+  desc = gpiod_get_index(dev, connection_id, index, flags);
 
 We may consider two different cases here, i.e. when connection ID is
 provided and otherwise.
 
-Case 1:
-	desc = gpiod_get(dev, "non-null-connection-id", flags);
-	desc = gpiod_get_index(dev, "non-null-connection-id", index, flags);
+Case 1::
+
+  desc = gpiod_get(dev, "non-null-connection-id", flags);
+  desc = gpiod_get_index(dev, "non-null-connection-id", index, flags);
+
+Case 2::
 
-Case 2:
-	desc = gpiod_get(dev, NULL, flags);
-	desc = gpiod_get_index(dev, NULL, index, flags);
+  desc = gpiod_get(dev, NULL, flags);
+  desc = gpiod_get_index(dev, NULL, index, flags);
 
 Case 1 assumes that corresponding ACPI device description must have
 defined device properties and will prevent to getting any GPIO resources
diff --git a/Documentation/firmware-guide/acpi/i2c-muxes.rst b/Documentation/firmware-guide/acpi/i2c-muxes.rst
new file mode 100644
index 000000000000..3a8997ccd7c4
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/i2c-muxes.rst
@@ -0,0 +1,61 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+ACPI I2C Muxes
+==============
+
+Describing an I2C device hierarchy that includes I2C muxes requires an ACPI
+Device () scope per mux channel.
+
+Consider this topology::
+
+    +------+   +------+
+    | SMB1 |-->| MUX0 |--CH00--> i2c client A (0x50)
+    |      |   | 0x70 |--CH01--> i2c client B (0x50)
+    +------+   +------+
+
+which corresponds to the following ASL::
+
+    Device (SMB1)
+    {
+        Name (_HID, ...)
+        Device (MUX0)
+        {
+            Name (_HID, ...)
+            Name (_CRS, ResourceTemplate () {
+                I2cSerialBus (0x70, ControllerInitiated, I2C_SPEED,
+                            AddressingMode7Bit, "^SMB1", 0x00,
+                            ResourceConsumer,,)
+            }
+
+            Device (CH00)
+            {
+                Name (_ADR, 0)
+
+                Device (CLIA)
+                {
+                    Name (_HID, ...)
+                    Name (_CRS, ResourceTemplate () {
+                        I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
+                                    AddressingMode7Bit, "^CH00", 0x00,
+                                    ResourceConsumer,,)
+                    }
+                }
+            }
+
+            Device (CH01)
+            {
+                Name (_ADR, 1)
+
+                Device (CLIB)
+                {
+                    Name (_HID, ...)
+                    Name (_CRS, ResourceTemplate () {
+                        I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
+                                    AddressingMode7Bit, "^CH01", 0x00,
+                                    ResourceConsumer,,)
+                    }
+                }
+            }
+        }
+    }
diff --git a/Documentation/firmware-guide/acpi/index.rst b/Documentation/firmware-guide/acpi/index.rst
new file mode 100644
index 000000000000..ae609eec4679
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/index.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+ACPI Support
+============
+
+.. toctree::
+   :maxdepth: 1
+
+   namespace
+   dsd/graph
+   dsd/data-node-references
+   enumeration
+   osi
+   method-customizing
+   method-tracing
+   DSD-properties-rules
+   debug
+   aml-debugger
+   apei/output_format
+   apei/einj
+   gpio-properties
+   i2c-muxes
+   acpi-lid
+   lpit
+   video_extension
diff --git a/Documentation/acpi/lpit.txt b/Documentation/firmware-guide/acpi/lpit.rst
index b426398d2e97..aca928fab027 100644
--- a/Documentation/acpi/lpit.txt
+++ b/Documentation/firmware-guide/acpi/lpit.rst
@@ -1,3 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+Low Power Idle Table (LPIT)
+===========================
+
 To enumerate platform Low Power Idle states, Intel platforms are using
 “Low Power Idle Table� (LPIT). More details about this table can be
 downloaded from:
@@ -8,13 +14,15 @@ Residencies for each low power state can be read via FFH
 
 On platforms supporting S0ix sleep states, there can be two types of
 residencies:
-- CPU PKG C10 (Read via FFH interface)
-- Platform Controller Hub (PCH) SLP_S0 (Read via memory mapped interface)
+
+  - CPU PKG C10 (Read via FFH interface)
+  - Platform Controller Hub (PCH) SLP_S0 (Read via memory mapped interface)
 
 The following attributes are added dynamically to the cpuidle
-sysfs attribute group:
-	/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
-	/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
+sysfs attribute group::
+
+  /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
+  /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
 
 The "low_power_idle_cpu_residency_us" attribute shows time spent
 by the CPU package in PKG C10
diff --git a/Documentation/firmware-guide/acpi/method-customizing.rst b/Documentation/firmware-guide/acpi/method-customizing.rst
new file mode 100644
index 000000000000..de3ebcaed4cf
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/method-customizing.rst
@@ -0,0 +1,89 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+Linux ACPI Custom Control Method How To
+=======================================
+
+:Author: Zhang Rui <rui.zhang@intel.com>
+
+
+Linux supports customizing ACPI control methods at runtime.
+
+Users can use this to:
+
+1. override an existing method which may not work correctly,
+   or just for debugging purposes.
+2. insert a completely new method in order to create a missing
+   method such as _OFF, _ON, _STA, _INI, etc.
+
+For these cases, it is far simpler to dynamically install a single
+control method rather than override the entire DSDT, because kernel
+rebuild/reboot is not needed and test result can be got in minutes.
+
+.. note::
+
+  - Only ACPI METHOD can be overridden, any other object types like
+    "Device", "OperationRegion", are not recognized. Methods
+    declared inside scope operators are also not supported.
+
+  - The same ACPI control method can be overridden for many times,
+    and it's always the latest one that used by Linux/kernel.
+
+  - To get the ACPI debug object output (Store (AAAA, Debug)),
+    please run::
+
+      echo 1 > /sys/module/acpi/parameters/aml_debug_output
+
+
+1. override an existing method
+==============================
+a) get the ACPI table via ACPI sysfs I/F. e.g. to get the DSDT,
+   just run "cat /sys/firmware/acpi/tables/DSDT > /tmp/dsdt.dat"
+b) disassemble the table by running "iasl -d dsdt.dat".
+c) rewrite the ASL code of the method and save it in a new file,
+d) package the new file (psr.asl) to an ACPI table format.
+   Here is an example of a customized \_SB._AC._PSR method::
+
+      DefinitionBlock ("", "SSDT", 1, "", "", 0x20080715)
+      {
+         Method (\_SB_.AC._PSR, 0, NotSerialized)
+         {
+            Store ("In AC _PSR", Debug)
+            Return (ACON)
+         }
+      }
+
+   Note that the full pathname of the method in ACPI namespace
+   should be used.
+e) assemble the file to generate the AML code of the method.
+   e.g. "iasl -vw 6084 psr.asl" (psr.aml is generated as a result)
+   If parameter "-vw 6084" is not supported by your iASL compiler,
+   please try a newer version.
+f) mount debugfs by "mount -t debugfs none /sys/kernel/debug"
+g) override the old method via the debugfs by running
+   "cat /tmp/psr.aml > /sys/kernel/debug/acpi/custom_method"
+
+2. insert a new method
+======================
+This is easier than overriding an existing method.
+We just need to create the ASL code of the method we want to
+insert and then follow the step c) ~ g) in section 1.
+
+3. undo your changes
+====================
+The "undo" operation is not supported for a new inserted method
+right now, i.e. we can not remove a method currently.
+For an overridden method, in order to undo your changes, please
+save a copy of the method original ASL code in step c) section 1,
+and redo step c) ~ g) to override the method with the original one.
+
+
+.. note:: We can use a kernel with multiple custom ACPI method running,
+   But each individual write to debugfs can implement a SINGLE
+   method override. i.e. if we want to insert/override multiple
+   ACPI methods, we need to redo step c) ~ g) for multiple times.
+
+.. note:: Be aware that root can mis-use this driver to modify arbitrary
+   memory and gain additional rights, if root's privileges got
+   restricted (for example if root is not allowed to load additional
+   modules after boot).
diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst
new file mode 100644
index 000000000000..d0b077b73f5f
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/method-tracing.rst
@@ -0,0 +1,238 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+=====================
+ACPICA Trace Facility
+=====================
+
+:Copyright: |copy| 2015, Intel Corporation
+:Author: Lv Zheng <lv.zheng@intel.com>
+
+
+Abstract
+========
+This document describes the functions and the interfaces of the
+method tracing facility.
+
+Functionalities and usage examples
+==================================
+
+ACPICA provides method tracing capability. And two functions are
+currently implemented using this capability.
+
+Log reducer
+-----------
+
+ACPICA subsystem provides debugging outputs when CONFIG_ACPI_DEBUG is
+enabled. The debugging messages which are deployed via
+ACPI_DEBUG_PRINT() macro can be reduced at 2 levels - per-component
+level (known as debug layer, configured via
+/sys/module/acpi/parameters/debug_layer) and per-type level (known as
+debug level, configured via /sys/module/acpi/parameters/debug_level).
+
+But when the particular layer/level is applied to the control method
+evaluations, the quantity of the debugging outputs may still be too
+large to be put into the kernel log buffer. The idea thus is worked out
+to only enable the particular debug layer/level (normally more detailed)
+logs when the control method evaluation is started, and disable the
+detailed logging when the control method evaluation is stopped.
+
+The following command examples illustrate the usage of the "log reducer"
+functionality:
+
+a. Filter out the debug layer/level matched logs when control methods
+   are being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "enable" > trace_state
+
+b. Filter out the debug layer/level matched logs when the specified
+   control method is being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method" > /sys/module/acpi/parameters/trace_state
+
+c. Filter out the debug layer/level matched logs when the specified
+   control method is being evaluated for the first time::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method-once" > /sys/module/acpi/parameters/trace_state
+
+Where:
+   0xXXXXXXXX/0xYYYYYYYY
+     Refer to Documentation/acpi/debug.txt for possible debug layer/level
+     masking values.
+   \PPPP.AAAA.TTTT.HHHH
+     Full path of a control method that can be found in the ACPI namespace.
+     It needn't be an entry of a control method evaluation.
+
+AML tracer
+----------
+
+There are special log entries added by the method tracing facility at
+the "trace points" the AML interpreter starts/stops to execute a control
+method, or an AML opcode. Note that the format of the log entries are
+subject to change::
+
+   [    0.186427]   exdebug-0398 ex_trace_point        : Method Begin [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
+   [    0.186630]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905c88:If] execution.
+   [    0.186820]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:LEqual] execution.
+   [    0.187010]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905a20:-NamePath-] execution.
+   [    0.187214]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905a20:-NamePath-] execution.
+   [    0.187407]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
+   [    0.187594]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
+   [    0.187789]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:LEqual] execution.
+   [    0.187980]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:Return] execution.
+   [    0.188146]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
+   [    0.188334]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
+   [    0.188524]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:Return] execution.
+   [    0.188712]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905c88:If] execution.
+   [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
+
+Developers can utilize these special log entries to track the AML
+interpretion, thus can aid issue debugging and performance tuning. Note
+that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
+macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
+"AML tracer" logs.
+
+The following command examples illustrate the usage of the "AML tracer"
+functionality:
+
+a. Filter out the method start/stop "AML tracer" logs when control
+   methods are being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "enable" > trace_state
+
+b. Filter out the method start/stop "AML tracer" when the specified
+   control method is being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method" > trace_state
+
+c. Filter out the method start/stop "AML tracer" logs when the specified
+   control method is being evaluated for the first time::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method-once" > trace_state
+
+d. Filter out the method/opcode start/stop "AML tracer" when the
+   specified control method is being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "opcode" > trace_state
+
+e. Filter out the method/opcode start/stop "AML tracer" when the
+   specified control method is being evaluated for the first time::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "opcode-opcode" > trace_state
+
+Note that all above method tracing facility related module parameters can
+be used as the boot parameters, for example::
+
+   acpi.trace_debug_layer=0x80 acpi.trace_debug_level=0x10 \
+   acpi.trace_method_name=\_SB.LID0._LID acpi.trace_state=opcode-once
+
+
+Interface descriptions
+======================
+
+All method tracing functions can be configured via ACPI module
+parameters that are accessible at /sys/module/acpi/parameters/:
+
+trace_method_name
+  The full path of the AML method that the user wants to trace.
+
+  Note that the full path shouldn't contain the trailing "_"s in its
+  name segments but may contain "\" to form an absolute path.
+
+trace_debug_layer
+  The temporary debug_layer used when the tracing feature is enabled.
+
+  Using ACPI_EXECUTER (0x80) by default, which is the debug_layer
+  used to match all "AML tracer" logs.
+
+trace_debug_level
+  The temporary debug_level used when the tracing feature is enabled.
+
+  Using ACPI_LV_TRACE_POINT (0x10) by default, which is the
+  debug_level used to match all "AML tracer" logs.
+
+trace_state
+  The status of the tracing feature.
+
+  Users can enable/disable this debug tracing feature by executing
+  the following command::
+
+   # echo string > /sys/module/acpi/parameters/trace_state
+
+Where "string" should be one of the following:
+
+"disable"
+  Disable the method tracing feature.
+
+"enable"
+  Enable the method tracing feature.
+  
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during any method execution will be logged.
+
+"method"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method execution of "trace_method_name" will be logged.
+
+"method-once"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method execution of "trace_method_name" will be logged only once.
+
+"opcode"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method/opcode execution of "trace_method_name" will be logged.
+
+"opcode-once"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method/opcode execution of "trace_method_name" will be logged only
+  once.
+
+Note that, the difference between the "enable" and other feature
+enabling options are:
+
+1. When "enable" is specified, since
+   "trace_debug_layer/trace_debug_level" shall apply to all control
+   method evaluations, after configuring "trace_state" to "enable",
+   "trace_method_name" will be reset to NULL.
+2. When "method/opcode" is specified, if
+   "trace_method_name" is NULL when "trace_state" is configured to
+   these options, the "trace_debug_layer/trace_debug_level" will
+   apply to all control method evaluations.
diff --git a/Documentation/acpi/namespace.txt b/Documentation/firmware-guide/acpi/namespace.rst
index 1860cb3865c6..835521baeb89 100644
--- a/Documentation/acpi/namespace.txt
+++ b/Documentation/firmware-guide/acpi/namespace.rst
@@ -1,85 +1,90 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+===================================================
 ACPI Device Tree - Representation of ACPI Namespace
+===================================================
 
-Copyright (C) 2013, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
+:Copyright: |copy| 2013, Intel Corporation
 
+:Author: Lv Zheng <lv.zheng@intel.com>
 
-Abstract:
+:Credit:   Thanks for the help from Zhang Rui <rui.zhang@intel.com> and
+           Rafael J.Wysocki <rafael.j.wysocki@intel.com>.
 
+Abstract
+========
 The Linux ACPI subsystem converts ACPI namespace objects into a Linux
 device tree under the /sys/devices/LNXSYSTEM:00 and updates it upon
-receiving ACPI hotplug notification events.  For each device object in this
-hierarchy there is a corresponding symbolic link in the
+receiving ACPI hotplug notification events.  For each device object
+in this hierarchy there is a corresponding symbolic link in the
 /sys/bus/acpi/devices.
+
 This document illustrates the structure of the ACPI device tree.
 
+ACPI Definition Blocks
+======================
+
+The ACPI firmware sets up RSDP (Root System Description Pointer) in the
+system memory address space pointing to the XSDT (Extended System
+Description Table).  The XSDT always points to the FADT (Fixed ACPI
+Description Table) using its first entry, the data within the FADT
+includes various fixed-length entries that describe fixed ACPI features
+of the hardware.  The FADT contains a pointer to the DSDT
+(Differentiated System Descripition Table).  The XSDT also contains
+entries pointing to possibly multiple SSDTs (Secondary System
+Description Table).
+
+The DSDT and SSDT data is organized in data structures called definition
+blocks that contain definitions of various objects, including ACPI
+control methods, encoded in AML (ACPI Machine Language).  The data block
+of the DSDT along with the contents of SSDTs represents a hierarchical
+data structure called the ACPI namespace whose topology reflects the
+structure of the underlying hardware platform.
+
+The relationships between ACPI System Definition Tables described above
+are illustrated in the following diagram::
+
+   +---------+    +-------+    +--------+    +------------------------+
+   |  RSDP   | +->| XSDT  | +->|  FADT  |    |  +-------------------+ |
+   +---------+ |  +-------+ |  +--------+  +-|->|       DSDT        | |
+   | Pointer | |  | Entry |-+  | ...... |  | |  +-------------------+ |
+   +---------+ |  +-------+    | X_DSDT |--+ |  | Definition Blocks | |
+   | Pointer |-+  | ..... |    | ...... |    |  +-------------------+ |
+   +---------+    +-------+    +--------+    |  +-------------------+ |
+                  | Entry |------------------|->|       SSDT        | |
+                  +- - - -+                  |  +-------------------| |
+                  | Entry | - - - - - - - -+ |  | Definition Blocks | |
+                  +- - - -+                | |  +-------------------+ |
+                                          | |  +- - - - - - - - - -+ |
+                                          +-|->|       SSDT        | |
+                                             |  +-------------------+ |
+                                             |  | Definition Blocks | |
+                                             |  +- - - - - - - - - -+ |
+                                             +------------------------+
+                                                         |
+                                             OSPM Loading |
+                                                         \|/
+                                                   +----------------+
+                                                   | ACPI Namespace |
+                                                   +----------------+
+
+                  Figure 1. ACPI Definition Blocks
+
+.. note:: RSDP can also contain a pointer to the RSDT (Root System
+   Description Table).  Platforms provide RSDT to enable
+   compatibility with ACPI 1.0 operating systems.  The OS is expected
+   to use XSDT, if present.
+
+
+Example ACPI Namespace
+======================
+
+All definition blocks are loaded into a single namespace.  The namespace
+is a hierarchy of objects identified by names and paths.
+The following naming conventions apply to object names in the ACPI
+namespace:
 
-Credit:
-
-Thanks for the help from Zhang Rui <rui.zhang@intel.com> and Rafael J.
-Wysocki <rafael.j.wysocki@intel.com>.
-
-
-1. ACPI Definition Blocks
-
-   The ACPI firmware sets up RSDP (Root System Description Pointer) in the
-   system memory address space pointing to the XSDT (Extended System
-   Description Table).  The XSDT always points to the FADT (Fixed ACPI
-   Description Table) using its first entry, the data within the FADT
-   includes various fixed-length entries that describe fixed ACPI features
-   of the hardware.  The FADT contains a pointer to the DSDT
-   (Differentiated System Descripition Table).  The XSDT also contains
-   entries pointing to possibly multiple SSDTs (Secondary System
-   Description Table).
-
-   The DSDT and SSDT data is organized in data structures called definition
-   blocks that contain definitions of various objects, including ACPI
-   control methods, encoded in AML (ACPI Machine Language).  The data block
-   of the DSDT along with the contents of SSDTs represents a hierarchical
-   data structure called the ACPI namespace whose topology reflects the
-   structure of the underlying hardware platform.
-
-   The relationships between ACPI System Definition Tables described above
-   are illustrated in the following diagram.
-
-     +---------+    +-------+    +--------+    +------------------------+
-     |  RSDP   | +->| XSDT  | +->|  FADT  |    |  +-------------------+ |
-     +---------+ |  +-------+ |  +--------+  +-|->|       DSDT        | |
-     | Pointer | |  | Entry |-+  | ...... |  | |  +-------------------+ |
-     +---------+ |  +-------+    | X_DSDT |--+ |  | Definition Blocks | |
-     | Pointer |-+  | ..... |    | ...... |    |  +-------------------+ |
-     +---------+    +-------+    +--------+    |  +-------------------+ |
-                    | Entry |------------------|->|       SSDT        | |
-                    +- - - -+                  |  +-------------------| |
-                    | Entry | - - - - - - - -+ |  | Definition Blocks | |
-                    +- - - -+                | |  +-------------------+ |
-                                             | |  +- - - - - - - - - -+ |
-                                             +-|->|       SSDT        | |
-                                               |  +-------------------+ |
-                                               |  | Definition Blocks | |
-                                               |  +- - - - - - - - - -+ |
-                                               +------------------------+
-                                                           |
-                                              OSPM Loading |
-                                                          \|/
-                                                    +----------------+
-                                                    | ACPI Namespace |
-                                                    +----------------+
-
-                     Figure 1. ACPI Definition Blocks
-
-   NOTE: RSDP can also contain a pointer to the RSDT (Root System
-         Description Table).  Platforms provide RSDT to enable
-         compatibility with ACPI 1.0 operating systems.  The OS is expected
-         to use XSDT, if present.
-
-
-2. Example ACPI Namespace
-
-   All definition blocks are loaded into a single namespace.  The namespace
-   is a hierarchy of objects identified by names and paths.
-   The following naming conventions apply to object names in the ACPI
-   namespace:
    1. All names are 32 bits long.
    2. The first byte of a name must be one of 'A' - 'Z', '_'.
    3. Each of the remaining bytes of a name must be one of 'A' - 'Z', '0'
@@ -91,7 +96,7 @@ Wysocki <rafael.j.wysocki@intel.com>.
       (i.e. names prepended with '^' are relative to the parent of the
       current namespace node).
 
-   The figure below shows an example ACPI namespace.
+The figure below shows an example ACPI namespace::
 
    +------+
    | \    |                     Root
@@ -184,19 +189,20 @@ Wysocki <rafael.j.wysocki@intel.com>.
                      Figure 2. Example ACPI Namespace
 
 
-3. Linux ACPI Device Objects
+Linux ACPI Device Objects
+=========================
 
-   The Linux kernel's core ACPI subsystem creates struct acpi_device
-   objects for ACPI namespace objects representing devices, power resources
-   processors, thermal zones.  Those objects are exported to user space via
-   sysfs as directories in the subtree under /sys/devices/LNXSYSTM:00.  The
-   format of their names is <bus_id:instance>, where 'bus_id' refers to the
-   ACPI namespace representation of the given object and 'instance' is used
-   for distinguishing different object of the same 'bus_id' (it is
-   two-digit decimal representation of an unsigned integer).
+The Linux kernel's core ACPI subsystem creates struct acpi_device
+objects for ACPI namespace objects representing devices, power resources
+processors, thermal zones.  Those objects are exported to user space via
+sysfs as directories in the subtree under /sys/devices/LNXSYSTM:00.  The
+format of their names is <bus_id:instance>, where 'bus_id' refers to the
+ACPI namespace representation of the given object and 'instance' is used
+for distinguishing different object of the same 'bus_id' (it is
+two-digit decimal representation of an unsigned integer).
 
-   The value of 'bus_id' depends on the type of the object whose name it is
-   part of as listed in the table below.
+The value of 'bus_id' depends on the type of the object whose name it is
+part of as listed in the table below::
 
                 +---+-----------------+-------+----------+
                 |   | Object/Feature  | Table | bus_id   |
@@ -226,10 +232,11 @@ Wysocki <rafael.j.wysocki@intel.com>.
 
                  Table 1. ACPI Namespace Objects Mapping
 
-   The following rules apply when creating struct acpi_device objects on
-   the basis of the contents of ACPI System Description Tables (as
-   indicated by the letter in the first column and the notation in the
-   second column of the table above):
+The following rules apply when creating struct acpi_device objects on
+the basis of the contents of ACPI System Description Tables (as
+indicated by the letter in the first column and the notation in the
+second column of the table above):
+
    N:
       The object's source is an ACPI namespace node (as indicated by the
       named object's type in the second column).  In that case the object's
@@ -249,13 +256,14 @@ Wysocki <rafael.j.wysocki@intel.com>.
       struct acpi_device object with LNXVIDEO 'bus_id' will be created for
       it.
 
-   The third column of the above table indicates which ACPI System
-   Description Tables contain information used for the creation of the
-   struct acpi_device objects represented by the given row (xSDT means DSDT
-   or SSDT).
+The third column of the above table indicates which ACPI System
+Description Tables contain information used for the creation of the
+struct acpi_device objects represented by the given row (xSDT means DSDT
+or SSDT).
+
+The forth column of the above table indicates the 'bus_id' generation
+rule of the struct acpi_device object:
 
-   The forth column of the above table indicates the 'bus_id' generation
-   rule of the struct acpi_device object:
    _HID:
       _HID in the last column of the table means that the object's bus_id
       is derived from the _HID/_CID identification objects present under
@@ -275,45 +283,47 @@ Wysocki <rafael.j.wysocki@intel.com>.
       object's bus_id.
 
 
-4. Linux ACPI Physical Device Glue
-
-   ACPI device (i.e. struct acpi_device) objects may be linked to other
-   objects in the Linux' device hierarchy that represent "physical" devices
-   (for example, devices on the PCI bus).  If that happens, it means that
-   the ACPI device object is a "companion" of a device otherwise
-   represented in a different way and is used (1) to provide configuration
-   information on that device which cannot be obtained by other means and
-   (2) to do specific things to the device with the help of its ACPI
-   control methods.  One ACPI device object may be linked this way to
-   multiple "physical" devices.
-
-   If an ACPI device object is linked to a "physical" device, its sysfs
-   directory contains the "physical_node" symbolic link to the sysfs
-   directory of the target device object.  In turn, the target device's
-   sysfs directory will then contain the "firmware_node" symbolic link to
-   the sysfs directory of the companion ACPI device object.
-   The linking mechanism relies on device identification provided by the
-   ACPI namespace.  For example, if there's an ACPI namespace object
-   representing a PCI device (i.e. a device object under an ACPI namespace
-   object representing a PCI bridge) whose _ADR returns 0x00020000 and the
-   bus number of the parent PCI bridge is 0, the sysfs directory
-   representing the struct acpi_device object created for that ACPI
-   namespace object will contain the 'physical_node' symbolic link to the
-   /sys/devices/pci0000:00/0000:00:02:0/ sysfs directory of the
-   corresponding PCI device.
-
-   The linking mechanism is generally bus-specific.  The core of its
-   implementation is located in the drivers/acpi/glue.c file, but there are
-   complementary parts depending on the bus types in question located
-   elsewhere.  For example, the PCI-specific part of it is located in
-   drivers/pci/pci-acpi.c.
-
-
-5. Example Linux ACPI Device Tree
-
-   The sysfs hierarchy of struct acpi_device objects corresponding to the
-   example ACPI namespace illustrated in Figure 2 with the addition of
-   fixed PWR_BUTTON/SLP_BUTTON devices is shown below.
+Linux ACPI Physical Device Glue
+===============================
+
+ACPI device (i.e. struct acpi_device) objects may be linked to other
+objects in the Linux' device hierarchy that represent "physical" devices
+(for example, devices on the PCI bus).  If that happens, it means that
+the ACPI device object is a "companion" of a device otherwise
+represented in a different way and is used (1) to provide configuration
+information on that device which cannot be obtained by other means and
+(2) to do specific things to the device with the help of its ACPI
+control methods.  One ACPI device object may be linked this way to
+multiple "physical" devices.
+
+If an ACPI device object is linked to a "physical" device, its sysfs
+directory contains the "physical_node" symbolic link to the sysfs
+directory of the target device object.  In turn, the target device's
+sysfs directory will then contain the "firmware_node" symbolic link to
+the sysfs directory of the companion ACPI device object.
+The linking mechanism relies on device identification provided by the
+ACPI namespace.  For example, if there's an ACPI namespace object
+representing a PCI device (i.e. a device object under an ACPI namespace
+object representing a PCI bridge) whose _ADR returns 0x00020000 and the
+bus number of the parent PCI bridge is 0, the sysfs directory
+representing the struct acpi_device object created for that ACPI
+namespace object will contain the 'physical_node' symbolic link to the
+/sys/devices/pci0000:00/0000:00:02:0/ sysfs directory of the
+corresponding PCI device.
+
+The linking mechanism is generally bus-specific.  The core of its
+implementation is located in the drivers/acpi/glue.c file, but there are
+complementary parts depending on the bus types in question located
+elsewhere.  For example, the PCI-specific part of it is located in
+drivers/pci/pci-acpi.c.
+
+
+Example Linux ACPI Device Tree
+=================================
+
+The sysfs hierarchy of struct acpi_device objects corresponding to the
+example ACPI namespace illustrated in Figure 2 with the addition of
+fixed PWR_BUTTON/SLP_BUTTON devices is shown below::
 
    +--------------+---+-----------------+
    | LNXSYSTEM:00 | \ | acpi:LNXSYSTEM: |
@@ -377,12 +387,14 @@ Wysocki <rafael.j.wysocki@intel.com>.
 
                   Figure 3. Example Linux ACPI Device Tree
 
-   NOTE: Each node is represented as "object/path/modalias", where:
-         1. 'object' is the name of the object's directory in sysfs.
-         2. 'path' is the ACPI namespace path of the corresponding
-            ACPI namespace object, as returned by the object's 'path'
-            sysfs attribute.
-         3. 'modalias' is the value of the object's 'modalias' sysfs
-            attribute (as described earlier in this document).
-   NOTE: N/A indicates the device object does not have the 'path' or the
-         'modalias' attribute.
+.. note:: Each node is represented as "object/path/modalias", where:
+
+   1. 'object' is the name of the object's directory in sysfs.
+   2. 'path' is the ACPI namespace path of the corresponding
+      ACPI namespace object, as returned by the object's 'path'
+      sysfs attribute.
+   3. 'modalias' is the value of the object's 'modalias' sysfs
+      attribute (as described earlier in this document).
+
+.. note:: N/A indicates the device object does not have the 'path' or the
+   'modalias' attribute.
diff --git a/Documentation/acpi/osi.txt b/Documentation/firmware-guide/acpi/osi.rst
index 50cde0ceb9b0..29e9ef79ebc0 100644
--- a/Documentation/acpi/osi.txt
+++ b/Documentation/firmware-guide/acpi/osi.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
 ACPI _OSI and _REV methods
---------------------------
+==========================
 
 An ACPI BIOS can use the "Operating System Interfaces" method (_OSI)
 to find out what the operating system supports. Eg. If BIOS
@@ -14,7 +17,7 @@ This document explains how and why the BIOS and Linux should use these methods.
 It also explains how and why they are widely misused.
 
 How to use _OSI
----------------
+===============
 
 Linux runs on two groups of machines -- those that are tested by the OEM
 to be compatible with Linux, and those that were never tested with Linux,
@@ -62,7 +65,7 @@ the string when that support is added to the kernel.
 That was easy.  Read on, to find out how to do it wrong.
 
 Before _OSI, there was _OS
---------------------------
+==========================
 
 ACPI 1.0 specified "_OS" as an
 "object that evaluates to a string that identifies the operating system."
@@ -96,7 +99,7 @@ That is the *only* viable strategy, as that is what modern Windows does,
 and so doing otherwise could steer the BIOS down an untested path.
 
 _OSI is born, and immediately misused
---------------------------------------
+=====================================
 
 With _OSI, the *BIOS* provides the string describing an interface,
 and asks the OS: "YES/NO, are you compatible with this interface?"
@@ -144,7 +147,7 @@ catastrophic failure resulting from the BIOS taking paths that
 were never validated under *any* OS.
 
 Do not use _REV
----------------
+===============
 
 Since _OSI("Linux") went away, some BIOS writers used _REV
 to support Linux and Windows differences in the same BIOS.
@@ -164,7 +167,7 @@ from mid-2015 onward.  The ACPI specification will also be updated
 to reflect that _REV is deprecated, and always returns 2.
 
 Apple Mac and _OSI("Darwin")
-----------------------------
+============================
 
 On Apple's Mac platforms, the ACPI BIOS invokes _OSI("Darwin")
 to determine if the machine is running Apple OSX.
diff --git a/Documentation/acpi/video_extension.txt b/Documentation/firmware-guide/acpi/video_extension.rst
index 79bf6a4921be..099b8607e07b 100644
--- a/Documentation/acpi/video_extension.txt
+++ b/Documentation/firmware-guide/acpi/video_extension.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
 ACPI video extensions
-~~~~~~~~~~~~~~~~~~~~~
+=====================
 
 This driver implement the ACPI Extensions For Display Adapters for
 integrated graphics devices on motherboard, as specified in ACPI 2.0
@@ -8,9 +11,10 @@ defining the video POST device, retrieving EDID information or to
 setup a video output, etc.  Note that this is an ref. implementation
 only.  It may or may not work for your integrated video device.
 
-The ACPI video driver does 3 things regarding backlight control:
+The ACPI video driver does 3 things regarding backlight control.
 
-1 Export a sysfs interface for user space to control backlight level
+Export a sysfs interface for user space to control backlight level
+==================================================================
 
 If the ACPI table has a video device, and acpi_backlight=vendor kernel
 command line is not present, the driver will register a backlight device
@@ -22,36 +26,41 @@ The backlight sysfs interface has a standard definition here:
 Documentation/ABI/stable/sysfs-class-backlight.
 
 And what ACPI video driver does is:
-actual_brightness: on read, control method _BQC will be evaluated to
-get the brightness level the firmware thinks it is at;
-bl_power: not implemented, will set the current brightness instead;
-brightness: on write, control method _BCM will run to set the requested
-brightness level;
-max_brightness: Derived from the _BCL package(see below);
-type: firmware
+
+actual_brightness:
+  on read, control method _BQC will be evaluated to
+  get the brightness level the firmware thinks it is at;
+bl_power:
+  not implemented, will set the current brightness instead;
+brightness:
+  on write, control method _BCM will run to set the requested brightness level;
+max_brightness:
+  Derived from the _BCL package(see below);
+type:
+  firmware
 
 Note that ACPI video backlight driver will always use index for
 brightness, actual_brightness and max_brightness. So if we have
-the following _BCL package:
+the following _BCL package::
 
-Method (_BCL, 0, NotSerialized)
-{
-	Return (Package (0x0C)
+	Method (_BCL, 0, NotSerialized)
 	{
-		0x64,
-		0x32,
-		0x0A,
-		0x14,
-		0x1E,
-		0x28,
-		0x32,
-		0x3C,
-		0x46,
-		0x50,
-		0x5A,
-		0x64
-	})
-}
+		Return (Package (0x0C)
+		{
+			0x64,
+			0x32,
+			0x0A,
+			0x14,
+			0x1E,
+			0x28,
+			0x32,
+			0x3C,
+			0x46,
+			0x50,
+			0x5A,
+			0x64
+		})
+	}
 
 The first two levels are for when laptop are on AC or on battery and are
 not used by Linux currently. The remaining 10 levels are supported levels
@@ -62,13 +71,15 @@ as a "brightness level" indicator. Thus from the user space perspective
 the range of available brightness levels is from 0 to 9 (max_brightness)
 inclusive.
 
-2 Notify user space about hotkey event
+Notify user space about hotkey event
+====================================
 
 There are generally two cases for hotkey event reporting:
+
 i) For some laptops, when user presses the hotkey, a scancode will be
    generated and sent to user space through the input device created by
    the keyboard driver as a key type input event, with proper remap, the
-   following key code will appear to user space:
+   following key code will appear to user space::
 
 	EV_KEY, KEY_BRIGHTNESSUP
 	EV_KEY, KEY_BRIGHTNESSDOWN
@@ -84,23 +95,27 @@ ii) For some laptops, the press of the hotkey will not generate the
     notify value it received and send the event to user space through the
     input device it created:
 
+	=====		==================
 	event		keycode
+	=====		==================
 	0x86		KEY_BRIGHTNESSUP
 	0x87		KEY_BRIGHTNESSDOWN
 	etc.
+	=====		==================
 
 so this would lead to the same effect as case i) now.
 
 Once user space tool receives this event, it can modify the backlight
 level through the sysfs interface.
 
-3 Change backlight level in the kernel
+Change backlight level in the kernel
+====================================
 
 This works for machines covered by case ii) in Section 2. Once the driver
 received a notification, it will set the backlight level accordingly. This does
 not affect the sending of event to user space, they are always sent to user
 space regardless of whether or not the video module controls the backlight level
 directly. This behaviour can be controlled through the brightness_switch_enabled
-module parameter as documented in admin-guide/kernel-parameters.rst. It is recommended to
-disable this behaviour once a GUI environment starts up and wants to have full
-control of the backlight level.
+module parameter as documented in admin-guide/kernel-parameters.rst. It is
+recommended to disable this behaviour once a GUI environment starts up and
+wants to have full control of the backlight level.
diff --git a/Documentation/firmware-guide/index.rst b/Documentation/firmware-guide/index.rst
new file mode 100644
index 000000000000..5355784ca0a2
--- /dev/null
+++ b/Documentation/firmware-guide/index.rst
@@ -0,0 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================
+The Linux kernel firmware guide
+===============================
+
+This section describes the ACPI subsystem in Linux from firmware perspective.
+
+.. toctree::
+   :maxdepth: 1
+
+   acpi/index
+
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 80a421cb935e..fdfa85c56a50 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -35,6 +35,16 @@ trying to get it to work optimally on a given system.
 
    admin-guide/index
 
+Firmware-related documentation
+------------------------------
+The following holds information on the kernel's expectations regarding the
+platform firmwares.
+
+.. toctree::
+   :maxdepth: 2
+
+   firmware-guide/index
+
 Application-developer documentation
 -----------------------------------
 
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 10f4499e677c..ee60e519438a 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -243,10 +243,10 @@ Optimization
 ^^^^^^^^^^^^
 
 The Kprobe-optimizer doesn't insert the jump instruction immediately;
-rather, it calls synchronize_sched() for safety first, because it's
+rather, it calls synchronize_rcu() for safety first, because it's
 possible for a CPU to be interrupted in the middle of executing the
-optimized region [3]_.  As you know, synchronize_sched() can ensure
-that all interruptions that were active when synchronize_sched()
+optimized region [3]_.  As you know, synchronize_rcu() can ensure
+that all interruptions that were active when synchronize_rcu()
 was called are done, but only if CONFIG_PREEMPT=n.  So, this version
 of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 1c22b21ae922..f70ebcdfe592 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1937,21 +1937,6 @@ There are some more advanced barrier functions:
      information on consistent memory.
 
 
-MMIO WRITE BARRIER
-------------------
-
-The Linux kernel also has a special barrier for use with memory-mapped I/O
-writes:
-
-	mmiowb();
-
-This is a variation on the mandatory write barrier that causes writes to weakly
-ordered I/O regions to be partially ordered.  Its effects may go beyond the
-CPU->Hardware interface and actually affect the hardware at some level.
-
-See the subsection "Acquires vs I/O accesses" for more information.
-
-
 ===============================
 IMPLICIT KERNEL MEMORY BARRIERS
 ===============================
@@ -2317,75 +2302,6 @@ But it won't see any of:
 	*E, *F or *G following RELEASE Q
 
 
-
-ACQUIRES VS I/O ACCESSES
-------------------------
-
-Under certain circumstances (especially involving NUMA), I/O accesses within
-two spinlocked sections on two different CPUs may be seen as interleaved by the
-PCI bridge, because the PCI bridge does not necessarily participate in the
-cache-coherence protocol, and is therefore incapable of issuing the required
-read memory barriers.
-
-For example:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	spin_lock(Q)
-	writel(0, ADDR)
-	writel(1, DATA);
-	spin_unlock(Q);
-					spin_lock(Q);
-					writel(4, ADDR);
-					writel(5, DATA);
-					spin_unlock(Q);
-
-may be seen by the PCI bridge as follows:
-
-	STORE *ADDR = 0, STORE *ADDR = 4, STORE *DATA = 1, STORE *DATA = 5
-
-which would probably cause the hardware to malfunction.
-
-
-What is necessary here is to intervene with an mmiowb() before dropping the
-spinlock, for example:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	spin_lock(Q)
-	writel(0, ADDR)
-	writel(1, DATA);
-	mmiowb();
-	spin_unlock(Q);
-					spin_lock(Q);
-					writel(4, ADDR);
-					writel(5, DATA);
-					mmiowb();
-					spin_unlock(Q);
-
-this will ensure that the two stores issued on CPU 1 appear at the PCI bridge
-before either of the stores issued on CPU 2.
-
-
-Furthermore, following a store by a load from the same device obviates the need
-for the mmiowb(), because the load forces the store to complete before the load
-is performed:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	spin_lock(Q)
-	writel(0, ADDR)
-	a = readl(DATA);
-	spin_unlock(Q);
-					spin_lock(Q);
-					writel(4, ADDR);
-					b = readl(DATA);
-					spin_unlock(Q);
-
-
-See Documentation/driver-api/device-io.rst for more information.
-
-
 =================================
 WHERE ARE MEMORY BARRIERS NEEDED?
 =================================
@@ -2532,16 +2448,9 @@ the device to malfunction.
 Inside of the Linux kernel, I/O should be done through the appropriate accessor
 routines - such as inb() or writel() - which know how to make such accesses
 appropriately sequential.  While this, for the most part, renders the explicit
-use of memory barriers unnecessary, there are a couple of situations where they
-might be needed:
-
- (1) On some systems, I/O stores are not strongly ordered across all CPUs, and
-     so for _all_ general drivers locks should be used and mmiowb() must be
-     issued prior to unlocking the critical section.
-
- (2) If the accessor functions are used to refer to an I/O memory window with
-     relaxed memory access properties, then _mandatory_ memory barriers are
-     required to enforce ordering.
+use of memory barriers unnecessary, if the accessor functions are used to refer
+to an I/O memory window with relaxed memory access properties, then _mandatory_
+memory barriers are required to enforce ordering.
 
 See Documentation/driver-api/device-io.rst for more information.
 
@@ -2586,8 +2495,7 @@ explicit barriers are used.
 
 Normally this won't be a problem because the I/O accesses done inside such
 sections will include synchronous load operations on strictly ordered I/O
-registers that form implicit I/O barriers.  If this isn't sufficient then an
-mmiowb() may need to be used explicitly.
+registers that form implicit I/O barriers.
 
 
 A similar situation may occur between an interrupt routine and two routines
@@ -2599,71 +2507,114 @@ likely, then interrupt-disabling locks should be used to guarantee ordering.
 KERNEL I/O BARRIER EFFECTS
 ==========================
 
-When accessing I/O memory, drivers should use the appropriate accessor
-functions:
-
- (*) inX(), outX():
-
-     These are intended to talk to I/O space rather than memory space, but
-     that's primarily a CPU-specific concept.  The i386 and x86_64 processors
-     do indeed have special I/O space access cycles and instructions, but many
-     CPUs don't have such a concept.
-
-     The PCI bus, amongst others, defines an I/O space concept which - on such
-     CPUs as i386 and x86_64 - readily maps to the CPU's concept of I/O
-     space.  However, it may also be mapped as a virtual I/O space in the CPU's
-     memory map, particularly on those CPUs that don't support alternate I/O
-     spaces.
-
-     Accesses to this space may be fully synchronous (as on i386), but
-     intermediary bridges (such as the PCI host bridge) may not fully honour
-     that.
-
-     They are guaranteed to be fully ordered with respect to each other.
-
-     They are not guaranteed to be fully ordered with respect to other types of
-     memory and I/O operation.
+Interfacing with peripherals via I/O accesses is deeply architecture and device
+specific. Therefore, drivers which are inherently non-portable may rely on
+specific behaviours of their target systems in order to achieve synchronization
+in the most lightweight manner possible. For drivers intending to be portable
+between multiple architectures and bus implementations, the kernel offers a
+series of accessor functions that provide various degrees of ordering
+guarantees:
 
  (*) readX(), writeX():
 
-     Whether these are guaranteed to be fully ordered and uncombined with
-     respect to each other on the issuing CPU depends on the characteristics
-     defined for the memory window through which they're accessing.  On later
-     i386 architecture machines, for example, this is controlled by way of the
-     MTRR registers.
+	The readX() and writeX() MMIO accessors take a pointer to the
+	peripheral being accessed as an __iomem * parameter. For pointers
+	mapped with the default I/O attributes (e.g. those returned by
+	ioremap()), the ordering guarantees are as follows:
+
+	1. All readX() and writeX() accesses to the same peripheral are ordered
+	   with respect to each other. This ensures that MMIO register accesses
+	   by the same CPU thread to a particular device will arrive in program
+	   order.
+
+	2. A writeX() issued by a CPU thread holding a spinlock is ordered
+	   before a writeX() to the same peripheral from another CPU thread
+	   issued after a later acquisition of the same spinlock. This ensures
+	   that MMIO register writes to a particular device issued while holding
+	   a spinlock will arrive in an order consistent with acquisitions of
+	   the lock.
+
+	3. A writeX() by a CPU thread to the peripheral will first wait for the
+	   completion of all prior writes to memory either issued by, or
+	   propagated to, the same thread. This ensures that writes by the CPU
+	   to an outbound DMA buffer allocated by dma_alloc_coherent() will be
+	   visible to a DMA engine when the CPU writes to its MMIO control
+	   register to trigger the transfer.
+
+	4. A readX() by a CPU thread from the peripheral will complete before
+	   any subsequent reads from memory by the same thread can begin. This
+	   ensures that reads by the CPU from an incoming DMA buffer allocated
+	   by dma_alloc_coherent() will not see stale data after reading from
+	   the DMA engine's MMIO status register to establish that the DMA
+	   transfer has completed.
+
+	5. A readX() by a CPU thread from the peripheral will complete before
+	   any subsequent delay() loop can begin execution on the same thread.
+	   This ensures that two MMIO register writes by the CPU to a peripheral
+	   will arrive at least 1us apart if the first write is immediately read
+	   back with readX() and udelay(1) is called prior to the second
+	   writeX():
+
+		writel(42, DEVICE_REGISTER_0); // Arrives at the device...
+		readl(DEVICE_REGISTER_0);
+		udelay(1);
+		writel(42, DEVICE_REGISTER_1); // ...at least 1us before this.
+
+	The ordering properties of __iomem pointers obtained with non-default
+	attributes (e.g. those returned by ioremap_wc()) are specific to the
+	underlying architecture and therefore the guarantees listed above cannot
+	generally be relied upon for accesses to these types of mappings.
+
+ (*) readX_relaxed(), writeX_relaxed():
+
+	These are similar to readX() and writeX(), but provide weaker memory
+	ordering guarantees. Specifically, they do not guarantee ordering with
+	respect to locking, normal memory accesses or delay() loops (i.e.
+	bullets 2-5 above) but they are still guaranteed to be ordered with
+	respect to other accesses from the same CPU thread to the same
+	peripheral when operating on __iomem pointers mapped with the default
+	I/O attributes.
+
+ (*) readsX(), writesX():
+
+	The readsX() and writesX() MMIO accessors are designed for accessing
+	register-based, memory-mapped FIFOs residing on peripherals that are not
+	capable of performing DMA. Consequently, they provide only the ordering
+	guarantees of readX_relaxed() and writeX_relaxed(), as documented above.
 
-     Ordinarily, these will be guaranteed to be fully ordered and uncombined,
-     provided they're not accessing a prefetchable device.
+ (*) inX(), outX():
 
-     However, intermediary hardware (such as a PCI bridge) may indulge in
-     deferral if it so wishes; to flush a store, a load from the same location
-     is preferred[*], but a load from the same device or from configuration
-     space should suffice for PCI.
+	The inX() and outX() accessors are intended to access legacy port-mapped
+	I/O peripherals, which may require special instructions on some
+	architectures (notably x86). The port number of the peripheral being
+	accessed is passed as an argument.
 
-     [*] NOTE! attempting to load from the same location as was written to may
-	 cause a malfunction - consider the 16550 Rx/Tx serial registers for
-	 example.
+	Since many CPU architectures ultimately access these peripherals via an
+	internal virtual memory mapping, the portable ordering guarantees
+	provided by inX() and outX() are the same as those provided by readX()
+	and writeX() respectively when accessing a mapping with the default I/O
+	attributes.
 
-     Used with prefetchable I/O memory, an mmiowb() barrier may be required to
-     force stores to be ordered.
+	Device drivers may expect outX() to emit a non-posted write transaction
+	that waits for a completion response from the I/O peripheral before
+	returning. This is not guaranteed by all architectures and is therefore
+	not part of the portable ordering semantics.
 
-     Please refer to the PCI specification for more information on interactions
-     between PCI transactions.
+ (*) insX(), outsX():
 
- (*) readX_relaxed(), writeX_relaxed()
+	As above, the insX() and outsX() accessors provide the same ordering
+	guarantees as readsX() and writesX() respectively when accessing a
+	mapping with the default I/O attributes.
 
-     These are similar to readX() and writeX(), but provide weaker memory
-     ordering guarantees.  Specifically, they do not guarantee ordering with
-     respect to normal memory accesses (e.g. DMA buffers) nor do they guarantee
-     ordering with respect to LOCK or UNLOCK operations.  If the latter is
-     required, an mmiowb() barrier can be used.  Note that relaxed accesses to
-     the same peripheral are guaranteed to be ordered with respect to each
-     other.
+ (*) ioreadX(), iowriteX():
 
- (*) ioreadX(), iowriteX()
+	These will perform appropriately for the type of access they're actually
+	doing, be it inX()/outX() or readX()/writeX().
 
-     These will perform appropriately for the type of access they're actually
-     doing, be it inX()/outX() or readX()/writeX().
+With the exception of the string accessors (insX(), outsX(), readsX() and
+writesX()), all of the above assume that the underlying peripheral is
+little-endian and will therefore perform byte-swapping operations on big-endian
+architectures.
 
 
 ========================================
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e2142fe40cda..c4ac35234f05 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1337,6 +1337,7 @@ tag - INTEGER
 	Default value is 0.
 
 xfrm4_gc_thresh - INTEGER
+	(Obsolete since linux-4.14)
 	The threshold at which we will start garbage collecting for IPv4
 	destination cache entries.  At twice this value the system will
 	refuse new allocations.
@@ -1920,6 +1921,7 @@ echo_ignore_all - BOOLEAN
 	Default: 0
 
 xfrm6_gc_thresh - INTEGER
+	(Obsolete since linux-4.14)
 	The threshold at which we will start garbage collecting for IPv6
 	destination cache entries.  At twice this value the system will
 	refuse new allocations.
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index 8c7a713cf657..642fa963be3c 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -132,7 +132,7 @@ version that should be applied. If there is any doubt, the maintainer
 will reply and ask what should be done.
 
 Q: I made changes to only a few patches in a patch series should I resend only those changed?
---------------------------------------------------------------------------------------------
+---------------------------------------------------------------------------------------------
 A: No, please resend the entire patch series and make sure you do number your
 patches such that it is clear this is the latest and greatest set of patches
 that can be applied.
diff --git a/Documentation/robust-futexes.txt b/Documentation/robust-futexes.txt
index 6c42c75103eb..6361fb01c9c1 100644
--- a/Documentation/robust-futexes.txt
+++ b/Documentation/robust-futexes.txt
@@ -218,5 +218,4 @@ All other architectures should build just fine too - but they won't have
 the new syscalls yet.
 
 Architectures need to implement the new futex_atomic_cmpxchg_inatomic()
-inline function before writing up the syscalls (that function returns
--ENOSYS right now).
+inline function before writing up the syscalls.
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 7f01fb1c1084..db0b9d8619f1 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -493,10 +493,8 @@ CPU �게 기대할 수 있는 최소한� 보장사항 몇가지가 있습니
      � 타입� 오�레�션� 단방향� 투과성 배리어처럼 �작합니다.  ACQUIRE
      오�레�션 뒤� 모든 메모리 오�레�션들� ACQUIRE 오�레�션 후�
      �어난 것으로 시스템� 나머지 컴�넌트들� 보�게 � 것� 보장�니다.
-     LOCK 오�레�션과 smp_load_acquire(), smp_cond_acquire() 오�레�션�
-     ACQUIRE 오�레�션� �함�니다.  smp_cond_acquire() 오�레�션� 컨트롤
-     �존성과 smp_rmb() 를 사용해서 ACQUIRE � �미� 요구사항(semantic)�
-     충족시킵니다.
+     LOCK 오�레�션과 smp_load_acquire(), smp_cond_load_acquire() 오�레�션�
+     ACQUIRE 오�레�션� �함�니다.
 
      ACQUIRE 오�레�션 앞� 메모리 오�레�션들� ACQUIRE 오�레�션 완료 후�
      수행� 것처럼 보� 수 있습니다.
@@ -2146,33 +2144,40 @@ set_current_state() 는 다�� 것들로 �싸질 수� 있습니다:
 	event_indicated = 1;
 	wake_up_process(event_daemon);
 
-wake_up() 류� �해 쓰기 메모리 배리어가 내��니다.  만약 그것들� 뭔가를
-깨운다면요.  � 배리어는 태스� �태가 지워지기 전� 수행�므로, �벤트를
-알리기 위한 STORE 와 태스� �태를 TASK_RUNNING 으로 설정하는 STORE 사��
-위치하게 �니다.
+wake_up() � 무언가를 깨우게 �면, � 함수는 범용 메모리 배리어를 수행합니다.
+� 함수가 아무것� 깨우지 않는다면 메모리 배리어는 수행� 수�, 수행�지 않�
+수� 있습니다; � 경우� 메모리 배리어를 수행할 거� 오해해선 안�니다.  �
+배리어는 태스� �태가 접근�기 전� 수행�는�, �세히 �하면 � �벤트를
+알리기 위한 STORE 와 TASK_RUNNING 으로 �태를 쓰는 STORE 사�� 수행�니다:
 
-	CPU 1				CPU 2
+	CPU 1 (Sleeper)			CPU 2 (Waker)
 	===============================	===============================
 	set_current_state();		STORE event_indicated
 	  smp_store_mb();		wake_up();
-	    STORE current->state	  <쓰기 배리어>
-	    <범용 배리어>		  STORE current->state
-	LOAD event_indicated
+	    STORE current->state	  ...
+	    <범용 배리어>		  <범용 배리어>
+	LOAD event_indicated		  if ((LOAD task->state) & TASK_NORMAL)
+					    STORE task->state
 
-한번� �합니다만, � 쓰기 메모리 배리어는 � 코드가 정�로 뭔가를 깨울 때�만
-실행�니다.  �걸 설명하기 위해, X 와 Y 는 모� 0 으로 초기화 �어 있다는 가정
-하� 아래� �벤트 시퀀스를 ��해 봅시다:
+여기서 "task" 는 깨어나지는 쓰레드�고 CPU 1 � "current" 와 같습니다.
+
+반복하지만, wake_up() � 무언가를 정� 깨운다면 범용 메모리 배리어가 수행�
+것� 보장�지만, 그렇지 않다면 그런 보장� 없습니다.  �걸 �해하기 위해, X 와
+Y 는 모� 0 으로 초기화 �어 있다는 가정 하� 아래� �벤트 시퀀스를 ��해
+봅시다:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	X = 1;				STORE event_indicated
+	X = 1;				Y = 1;
 	smp_mb();			wake_up();
-	Y = 1;				wait_event(wq, Y == 1);
-	wake_up();			  load from Y sees 1, no memory barrier
-					load from X might see 0
+	LOAD Y				LOAD X
+
+정�로 깨우기가 행해졌다면, � 로드 중 (최소한) 하나는 1 � 보게 �니다.
+반면�, 실제 깨우기가 행해지지 않았다면, � 로드 모� 0� 볼 수� 있습니다.
 
-위 예제�서� 경우와 달리 깨우기가 정�로 행해졌다면, CPU 2 � X 로드는 1 �
-본다고 보장� 수 있� �니다.
+wake_up_process() 는 항� 범용 메모리 배리어를 수행합니다.  � 배리어 역시
+태스� �태가 접근�기 전� 수행�니다.  특히, 앞� 예제 코드�서 wake_up() �
+wake_up_process() 로 대체�다면 � 로드 중 하나는 1� 볼 것� 보장�니다.
 
 사용 가능한 깨우기류 함수들로 다�과 같� 것들� 있습니다:
 
@@ -2192,6 +2197,8 @@ wake_up() 류ì—� ì�˜í•´ 쓰기 메모리 배리어가 ë‚´í�¬ë�©ë‹ˆë‹¤.  만약 ê
 	wake_up_poll();
 	wake_up_process();
 
+메모리 순서규칙 관��서, � 함수들� 모� wake_up() 과 같거나 보다 강한 순서
+보장� 제공합니다.
 
 [!] 잠재우는 코드와 깨우는 코드� 내��는 메모리 배리어들� 깨우기 전�
 �루어진 스토어를 잠재우는 코드가 set_current_state() 를 호출한 후� 행하는
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 67068c47c591..64b38dfcc243 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -321,7 +321,7 @@ cpu's hardware control block.
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
 Capability: basic
-Architectures: x86
+Architectures: all
 Type: vm ioctl
 Parameters: struct kvm_dirty_log (in/out)
 Returns: 0 on success, -1 on error
@@ -3810,7 +3810,7 @@ to I/O ports.
 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
 
 Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
-Architectures: x86
+Architectures: x86, arm, arm64, mips
 Type: vm ioctl
 Parameters: struct kvm_dirty_log (in)
 Returns: 0 on success, -1 on error
@@ -3830,8 +3830,9 @@ The ioctl clears the dirty status of pages in a memory slot, according to
 the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
 field.  Bit 0 of the bitmap corresponds to page "first_page" in the
 memory slot, and num_pages is the size in bits of the input bitmap.
-Both first_page and num_pages must be a multiple of 64.  For each bit
-that is set in the input bitmap, the corresponding page is marked "clean"
+first_page must be a multiple of 64; num_pages must also be a multiple of
+64 unless first_page + num_pages is the size of the memory slot.  For each
+bit that is set in the input bitmap, the corresponding page is marked "clean"
 in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
 (for example via write-protection, or by clearing the dirty bit in
 a page table entry).
@@ -4799,7 +4800,7 @@ and injected exceptions.
 
 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
 
-Architectures: all
+Architectures: x86, arm, arm64, mips
 Parameters: args[0] whether feature should be enabled or not
 
 With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
diff --git a/Documentation/x86/kernel-stacks b/Documentation/x86/kernel-stacks
index 9a0aa4d3a866..d1bfb0b95ee0 100644
--- a/Documentation/x86/kernel-stacks
+++ b/Documentation/x86/kernel-stacks
@@ -59,7 +59,7 @@ If that assumption is ever broken then the stacks will become corrupt.
 
 The currently assigned IST stacks are :-
 
-* DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+* ESTACK_DF.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 8 - Double Fault Exception (#DF).
 
@@ -68,7 +68,7 @@ The currently assigned IST stacks are :-
   Using a separate stack allows the kernel to recover from it well enough
   in many cases to still output an oops.
 
-* NMI_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+* ESTACK_NMI.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for non-maskable interrupts (NMI).
 
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :-
   middle of switching stacks.  Using IST for NMI events avoids making
   assumptions about the previous state of the kernel stack.
 
-* DEBUG_STACK.  DEBUG_STKSZ
+* ESTACK_DB.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for hardware debug interrupts (interrupt 1) and for software
   debug interrupts (INT3).
@@ -86,7 +86,12 @@ The currently assigned IST stacks are :-
   avoids making assumptions about the previous state of the kernel
   stack.
 
-* MCE_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+  To handle nested #DB correctly there exist two instances of DB stacks. On
+  #DB entry the IST stackpointer for #DB is switched to the second instance
+  so a nested #DB starts from a clean stack. The nested #DB switches
+  the IST stackpointer to a guard hole to catch triple nesting.
+
+* ESTACK_MCE.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 18 - Machine Check Exception (#MC).
 
diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt
index 2953e3ec9a02..06b3cdbc4048 100644
--- a/Documentation/x86/topology.txt
+++ b/Documentation/x86/topology.txt
@@ -51,7 +51,7 @@ The topology of a system is described in the units of:
     The physical ID of the package. This information is retrieved via CPUID
     and deduced from the APIC IDs of the cores in the package.
 
-  - cpuinfo_x86.logical_id:
+  - cpuinfo_x86.logical_proc_id:
 
     The logical ID of the package. As we do not trust BIOSes to enumerate the
     packages in a consistent way, we introduced the concept of logical package
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 804f9426ed17..6cbe652d7a49 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -72,7 +72,7 @@ Complete virtual memory map with 5-level page tables
 Notes:
 
  - With 56-bit addresses, user-space memory gets expanded by a factor of 512x,
-   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PT starting
+   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PB starting
    offset and many of the regions expand to support the much larger physical
    memory supported.
 
@@ -83,7 +83,7 @@ Notes:
  0000000000000000 |    0       | 00ffffffffffffff |   64 PB | user-space virtual memory, different per mm
 __________________|____________|__________________|_________|___________________________________________________________
                   |            |                  |         |
- 0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
+ 0100000000000000 |  +64    PB | feffffffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
                   |            |                  |         |     virtual memory addresses up to the -64 PB
                   |            |                  |         |     starting offset of kernel mappings.
 __________________|____________|__________________|_________|___________________________________________________________
@@ -99,7 +99,7 @@ ____________________________________________________________|___________________
  ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
  ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
  ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
- ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
+ ffdf000000000000 |   -8.25 PB | fffffbffffffffff |   ~8 PB | KASAN shadow memory
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
                                                             | Identical layout to the 47-bit one from here on:
diff --git a/MAINTAINERS b/MAINTAINERS
index dbb490f2b0a0..bd40a852207b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6463,7 +6463,7 @@ S:	Maintained
 F:	drivers/media/radio/radio-gemtek*
 
 GENERIC GPIO I2C DRIVER
-M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
+M:	Wolfram Sang <wsa+renesas@sang-engineering.com>
 S:	Supported
 F:	drivers/i2c/busses/i2c-gpio.c
 F:	include/linux/platform_data/i2c-gpio.h
@@ -6595,7 +6595,7 @@ M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 L:	linux-gpio@vger.kernel.org
 L:	linux-acpi@vger.kernel.org
 S:	Maintained
-F:	Documentation/acpi/gpio-properties.txt
+F:	Documentation/firmware-guide/acpi/gpio-properties.rst
 F:	drivers/gpio/gpiolib-acpi.c
 
 GPIO IR Transmitter
@@ -8995,7 +8995,7 @@ R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-arch@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	tools/memory-model/
 F:	Documentation/atomic_bitops.txt
 F:	Documentation/atomic_t.txt
@@ -9101,7 +9101,6 @@ F:	arch/*/include/asm/spinlock*.h
 F:	include/linux/rwlock*.h
 F:	include/linux/mutex*.h
 F:	include/linux/rwsem*.h
-F:	arch/*/include/asm/rwsem.h
 F:	include/linux/seqlock.h
 F:	lib/locking*.[ch]
 F:	kernel/locking/
@@ -12177,6 +12176,7 @@ F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
 F:	arch/*/kernel/perf_callchain.c
 F:	arch/*/events/*
+F:	arch/*/events/*/*
 F:	tools/perf/
 
 PERSONALITY HANDLING
@@ -13043,9 +13043,9 @@ M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 R:	Lai Jiangshan <jiangshanlai@gmail.com>
-L:	linux-kernel@vger.kernel.org
+L:	rcu@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	tools/testing/selftests/rcutorture
 
 RDC R-321X SoC
@@ -13091,10 +13091,10 @@ R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 R:	Lai Jiangshan <jiangshanlai@gmail.com>
 R:	Joel Fernandes <joel@joelfernandes.org>
-L:	linux-kernel@vger.kernel.org
+L:	rcu@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	Documentation/RCU/
 X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
@@ -14246,10 +14246,10 @@ M:	"Paul E. McKenney" <paulmck@linux.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-L:	linux-kernel@vger.kernel.org
+L:	rcu@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	include/linux/srcu*.h
 F:	kernel/rcu/srcu*.c
 
@@ -15696,7 +15696,7 @@ M:	"Paul E. McKenney" <paulmck@linux.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	Documentation/RCU/torture.txt
 F:	kernel/torture.c
 F:	kernel/rcu/rcutorture.c
diff --git a/Makefile b/Makefile
index 2b99679148dc..26c92f892d24 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*
@@ -678,6 +678,7 @@ KBUILD_CFLAGS	+= $(call cc-disable-warning,frame-address,)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, format-truncation)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, int-in-bool-context)
+KBUILD_CFLAGS	+= $(call cc-disable-warning, address-of-packed-member)
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS	+= -Os
@@ -719,7 +720,6 @@ ifdef CONFIG_CC_IS_CLANG
 KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
-KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 # Quiet clang warning: comparison of unsigned expression < 0 is always false
 KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
 # CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
diff --git a/arch/Kconfig b/arch/Kconfig
index 33687dddd86a..5e43fcbad4ca 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -249,6 +249,10 @@ config ARCH_HAS_FORTIFY_SOURCE
 config ARCH_HAS_SET_MEMORY
 	bool
 
+# Select if arch has all set_direct_map_invalid/default() functions
+config ARCH_HAS_SET_DIRECT_MAP
+	bool
+
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
        bool
@@ -383,7 +387,13 @@ config HAVE_ARCH_JUMP_LABEL_RELATIVE
 config HAVE_RCU_TABLE_FREE
 	bool
 
-config HAVE_RCU_TABLE_INVALIDATE
+config HAVE_RCU_TABLE_NO_INVALIDATE
+	bool
+
+config HAVE_MMU_GATHER_PAGE_SIZE
+	bool
+
+config HAVE_MMU_GATHER_NO_GATHER
 	bool
 
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -901,6 +911,15 @@ config HAVE_ARCH_PREL32_RELOCATIONS
 config ARCH_USE_MEMREMAP_PROT
 	bool
 
+config LOCK_EVENT_COUNTS
+	bool "Locking event counts collection"
+	depends on DEBUG_FS
+	---help---
+	  Enable light-weight counting of various locking related events
+	  in the system with minimal performance impact. This reduces
+	  the chance of application behavior change because of timing
+	  differences. The counts are reported via debugfs.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 584a6e114853..f7b19b813a70 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -36,6 +36,7 @@ config ALPHA
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
+	select MMU_GATHER_NO_RANGE
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
@@ -49,13 +50,6 @@ config MMU
 	bool
 	default y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config ARCH_HAS_ILOG2_U32
 	bool
 	default n
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 70b783333965..89e87bbc987f 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 4c533fc94d62..ccf9d65166bb 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -513,8 +513,6 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 #define writel_relaxed(b, addr)	__raw_writel(b, addr)
 #define writeq_relaxed(b, addr)	__raw_writeq(b, addr)
 
-#define mmiowb()
-
 /*
  * String version of IO memory access ops:
  */
diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
deleted file mode 100644
index cf8fc8f9a2ed..000000000000
--- a/arch/alpha/include/asm/rwsem.h
+++ /dev/null
@@ -1,211 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ALPHA_RWSEM_H
-#define _ALPHA_RWSEM_H
-
-/*
- * Written by Ivan Kokshaysky <ink@jurassic.park.msu.ru>, 2001.
- * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h
- */
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-
-#define RWSEM_UNLOCKED_VALUE		0x0000000000000000L
-#define RWSEM_ACTIVE_BIAS		0x0000000000000001L
-#define RWSEM_ACTIVE_MASK		0x00000000ffffffffL
-#define RWSEM_WAITING_BIAS		(-0x0000000100000000L)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-static inline int ___down_read(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter += RWSEM_ACTIVE_READ_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	mb\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
-#endif
-	return (oldcount < 0);
-}
-
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_read(sem)))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_read(sem)))
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-
-	return 0;
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long old, new, res;
-
-	res = atomic_long_read(&sem->count);
-	do {
-		new = res + RWSEM_ACTIVE_READ_BIAS;
-		if (new <= 0)
-			break;
-		old = res;
-		res = atomic_long_cmpxchg(&sem->count, old, new);
-	} while (res != old);
-	return res >= 0 ? 1 : 0;
-}
-
-static inline long ___down_write(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	mb\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
-#endif
-	return oldcount;
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_write(sem)))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_write(sem))) {
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	}
-
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
-			   RWSEM_ACTIVE_WRITE_BIAS);
-	if (ret == RWSEM_UNLOCKED_VALUE)
-		return 1;
-	return 0;
-}
-
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter -= RWSEM_ACTIVE_READ_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"	mb\n"
-	"1:	ldq_l	%0,%1\n"
-	"	subq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
-#endif
-	if (unlikely(oldcount < 0))
-		if ((int)oldcount - RWSEM_ACTIVE_READ_BIAS == 0)
-			rwsem_wake(sem);
-}
-
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	long count;
-#ifndef	CONFIG_SMP
-	sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS;
-	count = sem->count.counter;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"	mb\n"
-	"1:	ldq_l	%0,%1\n"
-	"	subq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	subq	%0,%3,%0\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (count), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
-#endif
-	if (unlikely(count))
-		if ((int)count == 0)
-			rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter -= RWSEM_WAITING_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	mb\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (-RWSEM_WAITING_BIAS), "m" (sem->count) : "memory");
-#endif
-	if (unlikely(oldcount < 0))
-		rwsem_downgrade_wake(sem);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ALPHA_RWSEM_H */
diff --git a/arch/alpha/include/asm/tlb.h b/arch/alpha/include/asm/tlb.h
index 8f5042b61875..4f79e331af5e 100644
--- a/arch/alpha/include/asm/tlb.h
+++ b/arch/alpha/include/asm/tlb.h
@@ -2,12 +2,6 @@
 #ifndef _ALPHA_TLB_H
 #define _ALPHA_TLB_H
 
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, addr)	do { } while (0)
-
-#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, address)		pte_free((tlb)->mm, pte)
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index c781e45d1d99..23e063df5d2c 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -63,9 +63,6 @@ config SCHED_OMIT_FRAME_POINTER
 config GENERIC_CSUM
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool n
 
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 69bc1c9e8e50..7425bb0f2d1b 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -18,8 +18,8 @@
 	model = "snps,hsdk";
 	compatible = "snps,hsdk";
 
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	chosen {
 		bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
@@ -105,7 +105,7 @@
 		#size-cells = <1>;
 		interrupt-parent = <&idu_intc>;
 
-		ranges = <0x00000000 0xf0000000 0x10000000>;
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
 
 		cgu_rst: reset-controller@8a0 {
 			compatible = "snps,hsdk-reset";
@@ -269,9 +269,10 @@
 	};
 
 	memory@80000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
+		#address-cells = <2>;
+		#size-cells = <2>;
 		device_type = "memory";
-		reg = <0x80000000 0x40000000>;  /* 1 GiB */
+		reg = <0x0 0x80000000 0x0 0x40000000>;  /* 1 GB lowmem */
+		/*     0x1 0x00000000 0x0 0x40000000>;     1 GB highmem */
 	};
 };
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index decc306a3b52..393d4f5e1450 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += msi.h
 generic-y += parport.h
 generic-y += percpu.h
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
index a9db5f62aaf3..90cac97643a4 100644
--- a/arch/arc/include/asm/tlb.h
+++ b/arch/arc/include/asm/tlb.h
@@ -9,38 +9,6 @@
 #ifndef _ASM_ARC_TLB_H
 #define _ASM_ARC_TLB_H
 
-#define tlb_flush(tlb)				\
-do {						\
-	if (tlb->fullmm)			\
-		flush_tlb_mm((tlb)->mm);	\
-} while (0)
-
-/*
- * This pair is called at time of munmap/exit to flush cache and TLB entries
- * for mappings being torn down.
- * 1) cache-flush part -implemented via tlb_start_vma( ) for VIPT aliasing D$
- * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range
- *
- * Note, read http://lkml.org/lkml/2004/1/15/6
- */
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-#define tlb_start_vma(tlb, vma)
-#else
-#define tlb_start_vma(tlb, vma)						\
-do {									\
-	if (!tlb->fullmm)						\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
-} while(0)
-#endif
-
-#define tlb_end_vma(tlb, vma)						\
-do {									\
-	if (!tlb->fullmm)						\
-		flush_tlb_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, ptep, address)
-
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index f230bb7092fd..b3373f5c88e0 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -30,10 +30,10 @@
 
 #else
 
-.macro PREALLOC_INSTR
+.macro PREALLOC_INSTR	reg, off
 .endm
 
-.macro PREFETCHW_INSTR
+.macro PREFETCHW_INSTR	reg, off
 .endm
 
 #endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 4135abec3fb0..63e6e6504699 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -113,10 +113,24 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	}
 
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
-	if (cbcr.c)
+	if (cbcr.c) {
 		ioc_exists = 1;
-	else
+
+		/*
+		 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+		 * simultaneously. This happens because as of today IOC aperture covers
+		 * only ZONE_NORMAL (low mem) and any dma transactions outside this
+		 * region won't be HW coherent.
+		 * If we want to use both IOC and ZONE_HIGHMEM we can use
+		 * bounce_buffer to handle dma transactions to HIGHMEM.
+		 * Also it is possible to modify dma_direct cache ops or increase IOC
+		 * aperture size if we are planning to use HIGHMEM without PAE.
+		 */
+		if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled())
+			ioc_enable = 0;
+	} else {
 		ioc_enable = 0;
+	}
 
 	/* HS 2.0 didn't have AUX_VOL */
 	if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1158,19 +1172,6 @@ noinline void __init arc_ioc_setup(void)
 	if (!ioc_enable)
 		return;
 
-	/*
-	 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
-	 * simultaneously. This happens because as of today IOC aperture covers
-	 * only ZONE_NORMAL (low mem) and any dma transactions outside this
-	 * region won't be HW coherent.
-	 * If we want to use both IOC and ZONE_HIGHMEM we can use
-	 * bounce_buffer to handle dma transactions to HIGHMEM.
-	 * Also it is possible to modify dma_direct cache ops or increase IOC
-	 * aperture size if we are planning to use HIGHMEM without PAE.
-	 */
-	if (IS_ENABLED(CONFIG_HIGHMEM))
-		panic("IOC and HIGHMEM can't be used simultaneously");
-
 	/* Flush + invalidate + disable L1 dcache */
 	__dc_disable();
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9aed25a6019b..dc9855c4a3b4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -178,10 +178,6 @@ config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default !CPU_V7M
 
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config ARCH_HAS_ILOG2_U32
 	bool
 
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index a8a4eb7f6dae..41deac2451af 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -9,10 +9,10 @@ generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += msi.h
 generic-y += parport.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += seccomp.h
 generic-y += segment.h
 generic-y += serial.h
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 0a8d7bba2cb0..4b66ecd6be99 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -11,6 +11,10 @@
 #include <clocksource/arm_arch_timer.h>
 
 #ifdef CONFIG_ARM_ARCH_TIMER
+/* 32bit ARM doesn't know anything about timer errata... */
+#define has_erratum_handler(h)		(false)
+#define erratum_handler(h)		(arch_timer_##h)
+
 int arch_timer_arch_init(void);
 
 /*
@@ -79,7 +83,7 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }
 
-static inline u64 arch_counter_get_cntpct(void)
+static inline u64 __arch_counter_get_cntpct(void)
 {
 	u64 cval;
 
@@ -88,7 +92,12 @@ static inline u64 arch_counter_get_cntpct(void)
 	return cval;
 }
 
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntpct_stable(void)
+{
+	return __arch_counter_get_cntpct();
+}
+
+static inline u64 __arch_counter_get_cntvct(void)
 {
 	u64 cval;
 
@@ -97,6 +106,11 @@ static inline u64 arch_counter_get_cntvct(void)
 	return cval;
 }
 
+static inline u64 __arch_counter_get_cntvct_stable(void)
+{
+	return __arch_counter_get_cntvct();
+}
+
 static inline u32 arch_timer_get_cntkctl(void)
 {
 	u32 cntkctl;
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 07e27f212dc7..d2453e2d3f1f 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -68,6 +68,8 @@
 #define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
 #define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
 
+#define CNTVCT				__ACCESS_CP15_64(1, c14)
+
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
 static inline unsigned long get_cr(void)
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 6b51826ab3d1..7e22c81398c4 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -281,8 +281,6 @@ extern void _memcpy_fromio(void *, const volatile void __iomem *, size_t);
 extern void _memcpy_toio(volatile void __iomem *, const void *, size_t);
 extern void _memset_io(volatile void __iomem *, int, size_t);
 
-#define mmiowb()
-
 /*
  *  Memory access primitives
  *  ------------------------
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
index 9e11dce55e06..9587517649bd 100644
--- a/arch/arm/include/asm/stage2_pgtable.h
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -32,14 +32,14 @@
 #define stage2_pgd_present(kvm, pgd)		pgd_present(pgd)
 #define stage2_pgd_populate(kvm, pgd, pud)	pgd_populate(NULL, pgd, pud)
 #define stage2_pud_offset(kvm, pgd, address)	pud_offset(pgd, address)
-#define stage2_pud_free(kvm, pud)		pud_free(NULL, pud)
+#define stage2_pud_free(kvm, pud)		do { } while (0)
 
 #define stage2_pud_none(kvm, pud)		pud_none(pud)
 #define stage2_pud_clear(kvm, pud)		pud_clear(pud)
 #define stage2_pud_present(kvm, pud)		pud_present(pud)
 #define stage2_pud_populate(kvm, pud, pmd)	pud_populate(NULL, pud, pmd)
 #define stage2_pmd_offset(kvm, pud, address)	pmd_offset(pud, address)
-#define stage2_pmd_free(kvm, pmd)		pmd_free(NULL, pmd)
+#define stage2_pmd_free(kvm, pmd)		free_page((unsigned long)pmd)
 
 #define stage2_pud_huge(kvm, pud)		pud_huge(pud)
 
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f854148c8d7c..bc6d04a09899 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -33,271 +33,42 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_GATHER_BUNDLE	8
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 static inline void __tlb_remove_table(void *_table)
 {
 	free_page_and_swap_cache((struct page *)_table);
 }
 
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
-#else
-#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	struct mmu_table_batch	*batch;
-	unsigned int		need_flush;
-#endif
-	unsigned int		fullmm;
-	struct vm_area_struct	*vma;
-	unsigned long		start, end;
-	unsigned long		range_start;
-	unsigned long		range_end;
-	unsigned int		nr;
-	unsigned int		max;
-	struct page		**pages;
-	struct page		*local[MMU_GATHER_BUNDLE];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-/*
- * This is unnecessarily complex.  There's three ways the TLB shootdown
- * code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- *     tlb->vma will be NULL.
- */
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
-	if (tlb->fullmm || !tlb->vma)
-		flush_tlb_mm(tlb->mm);
-	else if (tlb->range_end > 0) {
-		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
-	}
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(struct page *);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	tlb_flush(tlb);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	free_pages_and_swap_cache(tlb->pages, tlb->nr);
-	tlb->nr = 0;
-	if (tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->vma = NULL;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	__tlb_alloc_page(tlb);
+#include <asm-generic/tlb.h>
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
+#ifndef CONFIG_HAVE_RCU_TABLE_FREE
+#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry)
 #endif
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->range_start = start;
-		tlb->range_end = end;
-	}
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-		tlb->vma = vma;
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
 
 static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-	unsigned long addr)
+__pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
 {
 	pgtable_page_dtor(pte);
 
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-#else
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
 	 */
-	addr &= PMD_MASK;
-	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
-	tlb_add_flush(tlb, addr + SZ_1M);
+	addr = (addr & PMD_MASK) + SZ_1M;
+	__tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE);
 #endif
 
-	tlb_remove_entry(tlb, pte);
-}
-
-static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
-				  unsigned long addr)
-{
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-	tlb_remove_entry(tlb, virt_to_page(pmdp));
-#endif
+	tlb_remove_table(tlb, pte);
 }
 
 static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
+__pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 {
-}
-
-static inline void tlb_flush_remove_tables(struct mm_struct *mm)
-{
-}
+#ifdef CONFIG_ARM_LPAE
+	struct page *page = virt_to_page(pmdp);
 
-static inline void tlb_flush_remove_tables_local(void *arg)
-{
+	tlb_remove_table(tlb, page);
+#endif
 }
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 76bb8de6bf6b..be5edfdde558 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -549,8 +549,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	int ret;
 
 	/*
-	 * Increment event counter and perform fixup for the pre-signal
-	 * frame.
+	 * Perform fixup for the pre-signal frame.
 	 */
 	rseq_signal_deliver(ksig, regs);
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index a56e7c856ab5..86870f40f9a0 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -115,8 +115,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 		 * running on another CPU?  For now, ignore it as we
 		 * can't guarantee we won't explode.
 		 */
-		if (trace->nr_entries < trace->max_entries)
-			trace->entries[trace->nr_entries++] = ULONG_MAX;
 		return;
 #else
 		frame.fp = thread_saved_fp(tsk);
@@ -134,8 +132,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
@@ -153,8 +149,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	frame.pc = regs->ARM_pc;
 
 	walk_stackframe(&frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c
index a9dd619c6c29..7bdbf5d5c47d 100644
--- a/arch/arm/vdso/vgettimeofday.c
+++ b/arch/arm/vdso/vgettimeofday.c
@@ -18,9 +18,9 @@
 #include <linux/compiler.h>
 #include <linux/hrtimer.h>
 #include <linux/time.h>
-#include <asm/arch_timer.h>
 #include <asm/barrier.h>
 #include <asm/bug.h>
+#include <asm/cp15.h>
 #include <asm/page.h>
 #include <asm/unistd.h>
 #include <asm/vdso_datapage.h>
@@ -123,7 +123,8 @@ static notrace u64 get_ns(struct vdso_data *vdata)
 	u64 cycle_now;
 	u64 nsec;
 
-	cycle_now = arch_counter_get_cntvct();
+	isb();
+	cycle_now = read_sysreg(CNTVCT);
 
 	cycle_delta = (cycle_now - vdata->cs_cycle_last) & vdata->cs_mask;
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7e34b9eba5de..df350f4e1e7a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -90,6 +90,7 @@ config ARM64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_MULTI_HANDLER
@@ -148,8 +149,8 @@ config ARM64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
-	select HAVE_RCU_TABLE_INVALIDATE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -237,9 +238,6 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
@@ -297,7 +295,7 @@ menu "Kernel Features"
 menu "ARM errata workarounds via the alternatives framework"
 
 config ARM64_WORKAROUND_CLEAN_CACHE
-	def_bool n
+	bool
 
 config ARM64_ERRATUM_826319
 	bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted"
@@ -464,26 +462,28 @@ config ARM64_ERRATUM_1024718
 	bool "Cortex-A55: 1024718: Update of DBM/AP bits without break before make might result in incorrect update"
 	default y
 	help
-	  This option adds work around for Arm Cortex-A55 Erratum 1024718.
+	  This option adds a workaround for ARM Cortex-A55 Erratum 1024718.
 
 	  Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect
 	  update of the hardware dirty bit when the DBM/AP bits are updated
-	  without a break-before-make. The work around is to disable the usage
+	  without a break-before-make. The workaround is to disable the usage
 	  of hardware DBM locally on the affected cores. CPUs not affected by
-	  erratum will continue to use the feature.
+	  this erratum will continue to use the feature.
 
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_1188873
-	bool "Cortex-A76: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
+	bool "Cortex-A76/Neoverse-N1: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
 	default y
+	depends on COMPAT
 	select ARM_ARCH_TIMER_OOL_WORKAROUND
 	help
-	  This option adds work arounds for ARM Cortex-A76 erratum 1188873
+	  This option adds a workaround for ARM Cortex-A76/Neoverse-N1
+	  erratum 1188873.
 
-	  Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could cause
-	  register corruption when accessing the timer registers from
-	  AArch32 userspace.
+	  Affected Cortex-A76/Neoverse-N1 cores (r0p0, r1p0, r2p0) could
+	  cause register corruption when accessing the timer registers
+	  from AArch32 userspace.
 
 	  If unsure, say Y.
 
@@ -491,7 +491,7 @@ config ARM64_ERRATUM_1165522
 	bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
 	help
-	  This option adds work arounds for ARM Cortex-A76 erratum 1165522
+	  This option adds a workaround for ARM Cortex-A76 erratum 1165522.
 
 	  Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could end-up with
 	  corrupted TLBs by speculating an AT instruction during a guest
@@ -504,7 +504,7 @@ config ARM64_ERRATUM_1286807
 	default y
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
-	  This option adds workaround for ARM Cortex-A76 erratum 1286807
+	  This option adds a workaround for ARM Cortex-A76 erratum 1286807.
 
 	  On the affected Cortex-A76 cores (r0p0 to r3p0), if a virtual
 	  address for a cacheable mapping of a location is being
@@ -521,10 +521,10 @@ config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
 	help
-	  Enable workaround for erratum 22375, 24313.
+	  Enable workaround for errata 22375 and 24313.
 
 	  This implements two gicv3-its errata workarounds for ThunderX. Both
-	  with small impact affecting only ITS table allocation.
+	  with a small impact affecting only ITS table allocation.
 
 	    erratum 22375: only alloc 8MB table size
 	    erratum 24313: ignore memory access type
@@ -588,9 +588,6 @@ config QCOM_FALKOR_ERRATUM_1003
 
 config ARM64_WORKAROUND_REPEAT_TLBI
 	bool
-	help
-	  Enable the repeat TLBI workaround for Falkor erratum 1009 and
-	  Cortex-A76 erratum 1286807.
 
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
@@ -626,7 +623,7 @@ config HISILICON_ERRATUM_161600802
 	bool "Hip07 161600802: Erroneous redistributor VLPI base"
 	default y
 	help
-	  The HiSilicon Hip07 SoC usees the wrong redistributor base
+	  The HiSilicon Hip07 SoC uses the wrong redistributor base
 	  when issued ITS commands such as VMOVP and VMAPP, and requires
 	  a 128kB offset to be applied to the target address in this commands.
 
@@ -646,7 +643,7 @@ config FUJITSU_ERRATUM_010001
 	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
 	default y
 	help
-	  This option adds workaround for Fujitsu-A64FX erratum E#010001.
+	  This option adds a workaround for Fujitsu-A64FX erratum E#010001.
 	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
 	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
 	  This fault occurs under a specific hardware condition when a
@@ -657,7 +654,7 @@ config FUJITSU_ERRATUM_010001
 	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
 
 	  The workaround is to ensure these bits are clear in TCR_ELx.
-	  The workaround only affect the Fujitsu-A64FX.
+	  The workaround only affects the Fujitsu-A64FX.
 
 	  If unsure, say Y.
 
@@ -889,6 +886,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	def_bool y if PGTABLE_LEVELS > 2
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---
@@ -1078,9 +1078,65 @@ config RODATA_FULL_DEFAULT_ENABLED
 	  This requires the linear region to be mapped down to pages,
 	  which may adversely affect performance in some cases.
 
+config ARM64_SW_TTBR0_PAN
+	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
+	help
+	  Enabling this option prevents the kernel from accessing
+	  user-space memory directly by pointing TTBR0_EL1 to a reserved
+	  zeroed area and reserved ASID. The user access routines
+	  restore the valid TTBR0_EL1 temporarily.
+
+menuconfig COMPAT
+	bool "Kernel support for 32-bit EL0"
+	depends on ARM64_4K_PAGES || EXPERT
+	select COMPAT_BINFMT_ELF if BINFMT_ELF
+	select HAVE_UID16
+	select OLD_SIGSUSPEND3
+	select COMPAT_OLD_SIGACTION
+	help
+	  This option enables support for a 32-bit EL0 running under a 64-bit
+	  kernel at EL1. AArch32-specific components such as system calls,
+	  the user helper functions, VFP support and the ptrace interface are
+	  handled appropriately by the kernel.
+
+	  If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
+	  that you will only be able to execute AArch32 binaries that were compiled
+	  with page size aligned segments.
+
+	  If you want to execute 32-bit userspace applications, say Y.
+
+if COMPAT
+
+config KUSER_HELPERS
+	bool "Enable kuser helpers page for 32 bit applications"
+	default y
+	help
+	  Warning: disabling this option may break 32-bit user programs.
+
+	  Provide kuser helpers to compat tasks. The kernel provides
+	  helper code to userspace in read only form at a fixed location
+	  to allow userspace to be independent of the CPU type fitted to
+	  the system. This permits binaries to be run on ARMv4 through
+	  to ARMv8 without modification.
+
+	  See Documentation/arm/kernel_user_helpers.txt for details.
+
+	  However, the fixed address nature of these helpers can be used
+	  by ROP (return orientated programming) authors when creating
+	  exploits.
+
+	  If all of the binaries and libraries which run on your platform
+	  are built specifically for your platform, and make no use of
+	  these helpers, then you can turn this option off to hinder
+	  such exploits. However, in that case, if a binary or library
+	  relying on those helpers is run, it will not function correctly.
+
+	  Say N here only if you are absolutely certain that you do not
+	  need these helpers; otherwise, the safe option is to say Y.
+
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
-	depends on COMPAT
 	depends on SYSCTL
 	help
 	  Legacy software support may require certain instructions
@@ -1146,13 +1202,7 @@ config SETEND_EMULATION
 	  If unsure, say Y
 endif
 
-config ARM64_SW_TTBR0_PAN
-	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
-	help
-	  Enabling this option prevents the kernel from accessing
-	  user-space memory directly by pointing TTBR0_EL1 to a reserved
-	  zeroed area and reserved ASID. The user access routines
-	  restore the valid TTBR0_EL1 temporarily.
+endif
 
 menu "ARMv8.1 architectural features"
 
@@ -1318,6 +1368,9 @@ config ARM64_SVE
 
 	  To enable use of this extension on CPUs that implement it, say Y.
 
+	  On CPUs that support the SVE2 extensions, this option will enable
+	  those too.
+
 	  Note that for architectural reasons, firmware _must_ implement SVE
 	  support when running on SVE capable hardware.  The required support
 	  is present in:
@@ -1351,7 +1404,7 @@ config ARM64_PSEUDO_NMI
 	help
 	  Adds support for mimicking Non-Maskable Interrupts through the use of
 	  GIC interrupt priority. This support requires version 3 or later of
-	  Arm GIC.
+	  ARM GIC.
 
 	  This high priority configuration for interrupts needs to be
 	  explicitly enabled by setting the kernel parameter
@@ -1475,25 +1528,6 @@ config DMI
 
 endmenu
 
-config COMPAT
-	bool "Kernel support for 32-bit EL0"
-	depends on ARM64_4K_PAGES || EXPERT
-	select COMPAT_BINFMT_ELF if BINFMT_ELF
-	select HAVE_UID16
-	select OLD_SIGSUSPEND3
-	select COMPAT_OLD_SIGACTION
-	help
-	  This option enables support for a 32-bit EL0 running under a 64-bit
-	  kernel at EL1. AArch32-specific components such as system calls,
-	  the user helper functions, VFP support and the ptrace interface are
-	  handled appropriately by the kernel.
-
-	  If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
-	  that you will only be able to execute AArch32 binaries that were compiled
-	  with page size aligned segments.
-
-	  If you want to execute 32-bit userspace applications, say Y.
-
 config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
diff --git a/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h b/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
index 1b4cb0c55744..385c455a7c98 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
+++ b/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2018 MediaTek Inc.
  * Author: Zhiyong Tao <zhiyong.tao@mediatek.com>
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 5fc6f51908fd..036ea77f83bc 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -372,7 +372,7 @@ static struct aead_alg ccm_aes_alg = {
 
 static int __init aes_mod_init(void)
 {
-	if (!(elf_hwcap & HWCAP_AES))
+	if (!cpu_have_named_feature(AES))
 		return -ENODEV;
 	return crypto_register_aead(&ccm_aes_alg);
 }
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index e7a95a566462..bf1b321ff4c1 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -440,7 +440,7 @@ static int __init aes_init(void)
 	int err;
 	int i;
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index bece1d85bd81..cb054f51c917 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -173,7 +173,7 @@ static struct skcipher_alg algs[] = {
 
 static int __init chacha_simd_mod_init(void)
 {
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index dd325829ee44..e81d5bd555c0 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -101,7 +101,7 @@ static struct shash_alg crc_t10dif_alg[] = {{
 
 static int __init crc_t10dif_mod_init(void)
 {
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		return crypto_register_shashes(crc_t10dif_alg,
 					       ARRAY_SIZE(crc_t10dif_alg));
 	else
@@ -111,7 +111,7 @@ static int __init crc_t10dif_mod_init(void)
 
 static void __exit crc_t10dif_mod_exit(void)
 {
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		crypto_unregister_shashes(crc_t10dif_alg,
 					  ARRAY_SIZE(crc_t10dif_alg));
 	else
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 791ad422c427..4e69bb78ea89 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -704,10 +704,10 @@ static int __init ghash_ce_mod_init(void)
 {
 	int ret;
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		ret = crypto_register_shashes(ghash_alg,
 					      ARRAY_SIZE(ghash_alg));
 	else
@@ -717,7 +717,7 @@ static int __init ghash_ce_mod_init(void)
 	if (ret)
 		return ret;
 
-	if (elf_hwcap & HWCAP_PMULL) {
+	if (cpu_have_named_feature(PMULL)) {
 		ret = crypto_register_aead(&gcm_aes_alg);
 		if (ret)
 			crypto_unregister_shashes(ghash_alg,
@@ -728,7 +728,7 @@ static int __init ghash_ce_mod_init(void)
 
 static void __exit ghash_ce_mod_exit(void)
 {
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		crypto_unregister_shashes(ghash_alg, ARRAY_SIZE(ghash_alg));
 	else
 		crypto_unregister_shash(ghash_alg);
diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c
index 22cc32ac9448..38a589044b6c 100644
--- a/arch/arm64/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c
@@ -56,7 +56,7 @@ static struct shash_alg nhpoly1305_alg = {
 
 static int __init nhpoly1305_mod_init(void)
 {
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	return crypto_register_shash(&nhpoly1305_alg);
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index 4aedeaefd61f..0cccdb9cc2c0 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -173,7 +173,7 @@ static int __init sha256_mod_init(void)
 	if (ret)
 		return ret;
 
-	if (elf_hwcap & HWCAP_ASIMD) {
+	if (cpu_have_named_feature(ASIMD)) {
 		ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs));
 		if (ret)
 			crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
@@ -183,7 +183,7 @@ static int __init sha256_mod_init(void)
 
 static void __exit sha256_mod_fini(void)
 {
-	if (elf_hwcap & HWCAP_ASIMD)
+	if (cpu_have_named_feature(ASIMD))
 		crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs));
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 }
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 1e17ea5c372b..eb0df239a759 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -13,10 +13,10 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += msi.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
-generic-y += rwsem.h
 generic-y += segment.h
 generic-y += serial.h
 generic-y += set_memory.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f2a234d6516c..b7bca1ae09e6 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -31,11 +31,23 @@
 #include <clocksource/arm_arch_timer.h>
 
 #if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
-extern struct static_key_false arch_timer_read_ool_enabled;
-#define needs_unstable_timer_counter_workaround() \
-	static_branch_unlikely(&arch_timer_read_ool_enabled)
+#define has_erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h);					\
+	})
+
+#define erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h) ? __wa->h : arch_timer_##h;		\
+	})
+
 #else
-#define needs_unstable_timer_counter_workaround()  false
+#define has_erratum_handler(h)			   false
+#define erratum_handler(h)			   (arch_timer_##h)
 #endif
 
 enum arch_timer_erratum_match_type {
@@ -61,23 +73,37 @@ struct arch_timer_erratum_workaround {
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
 		timer_unstable_counter_workaround);
 
+/* inline sysreg accessors that make erratum_handler() work */
+static inline notrace u32 arch_timer_read_cntp_tval_el0(void)
+{
+	return read_sysreg(cntp_tval_el0);
+}
+
+static inline notrace u32 arch_timer_read_cntv_tval_el0(void)
+{
+	return read_sysreg(cntv_tval_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntpct_el0(void)
+{
+	return read_sysreg(cntpct_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntvct_el0(void)
+{
+	return read_sysreg(cntvct_el0);
+}
+
 #define arch_timer_reg_read_stable(reg)					\
-({									\
-	u64 _val;							\
-	if (needs_unstable_timer_counter_workaround()) {		\
-		const struct arch_timer_erratum_workaround *wa;		\
+	({								\
+		u64 _val;						\
+									\
 		preempt_disable_notrace();				\
-		wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		if (wa && wa->read_##reg)				\
-			_val = wa->read_##reg();			\
-		else							\
-			_val = read_sysreg(reg);			\
+		_val = erratum_handler(read_ ## reg)();			\
 		preempt_enable_notrace();				\
-	} else {							\
-		_val = read_sysreg(reg);				\
-	}								\
-	_val;								\
-})
+									\
+		_val;							\
+	})
 
 /*
  * These register accessors are marked inline so the compiler can
@@ -148,18 +174,67 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	isb();
 }
 
-static inline u64 arch_counter_get_cntpct(void)
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
+static inline u64 __arch_counter_get_cntpct_stable(void)
+{
+	u64 cnt;
+
+	isb();
+	cnt = arch_timer_reg_read_stable(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static inline u64 __arch_counter_get_cntpct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntpct_el0);
+	cnt = read_sysreg(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntvct_stable(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntvct_el0);
+	cnt = arch_timer_reg_read_stable(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
+static inline u64 __arch_counter_get_cntvct(void)
+{
+	u64 cnt;
+
+	isb();
+	cnt = read_sysreg(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+#undef arch_counter_enforce_ordering
+
 static inline int arch_timer_arch_init(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index c5308d01e228..039fbd822ec6 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -407,10 +407,14 @@ alternative_endif
 	.ifc	\op, cvap
 	sys	3, c7, c12, 1, \kaddr	// dc cvap
 	.else
+	.ifc	\op, cvadp
+	sys	3, c7, c13, 1, \kaddr	// dc cvadp
+	.else
 	dc	\op, \kaddr
 	.endif
 	.endif
 	.endif
+	.endif
 	add	\kaddr, \kaddr, \tmp1
 	cmp	\kaddr, \size
 	b.lo	9998b
@@ -442,8 +446,8 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
  */
 	.macro	reset_pmuserenr_el0, tmpreg
-	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	\tmpreg, \tmpreg, #8, #4
+	mrs	\tmpreg, id_aa64dfr0_el1
+	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	\tmpreg, #1			// Skip if no PMU present
 	b.lt	9000f
 	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index f66bb04fdf2d..85b6bedbcc68 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/kasan-checks.h>
+
 #define __nops(n)	".rept	" #n "\nnop\n.endr\n"
 #define nops(n)		asm volatile(__nops(n))
 
@@ -72,31 +74,33 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
 
 #define __smp_store_release(p, v)					\
 do {									\
+	typeof(p) __p = (p);						\
 	union { typeof(*p) __val; char __c[1]; } __u =			\
-		{ .__val = (__force typeof(*p)) (v) }; 			\
+		{ .__val = (__force typeof(*p)) (v) };			\
 	compiletime_assert_atomic_type(*p);				\
+	kasan_check_write(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u8 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u16 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u32 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u64 *)__u.__c)		\
 				: "memory");				\
 		break;							\
@@ -106,27 +110,29 @@ do {									\
 #define __smp_load_acquire(p)						\
 ({									\
 	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
 	compiletime_assert_atomic_type(*p);				\
+	kasan_check_read(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
 			: "=r" (*(__u8 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
 			: "=r" (*(__u16 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
 			: "=r" (*(__u32 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
 			: "=r" (*(__u64 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	}								\
 	__u.__val;							\
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index 2945fe6cd863..d84294064e6a 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -11,6 +11,8 @@
 
 /*
  * #imm16 values used for BRK instruction generation
+ * 0x004: for installing kprobes
+ * 0x005: for installing uprobes
  * Allowed values for kgdb are 0x400 - 0x7ff
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
@@ -18,10 +20,13 @@
  * 0x800: kernel-mode BUG() and WARN() traps
  * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
  */
+#define KPROBES_BRK_IMM			0x004
+#define UPROBES_BRK_IMM			0x005
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
 #define BUG_BRK_IMM			0x800
 #define KASAN_BRK_IMM			0x900
+#define KASAN_BRK_MASK			0x0ff
 
 #endif
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index f6a76e43f39e..defdc67d9ab4 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -61,7 +61,8 @@
 #define ARM64_HAS_GENERIC_AUTH_ARCH		40
 #define ARM64_HAS_GENERIC_AUTH_IMP_DEF		41
 #define ARM64_HAS_IRQ_PRIO_MASKING		42
+#define ARM64_HAS_DCPODP			43
 
-#define ARM64_NCAPS				43
+#define ARM64_NCAPS				44
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e505e1fbd2b9..f210bcf096f7 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -14,15 +14,8 @@
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
-/*
- * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
- * in the kernel and for user space to keep track of which optional features
- * are supported by the current system. So let's map feature 'x' to HWCAP_x.
- * Note that HWCAP_x constants are bit fields so we need to take the log.
- */
-
-#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
-#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+#define MAX_CPU_FEATURES	64
+#define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
 #ifndef __ASSEMBLY__
 
@@ -399,11 +392,13 @@ extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
 	for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS)
 
 bool this_cpu_has_cap(unsigned int cap);
+void cpu_set_feature(unsigned int num);
+bool cpu_have_feature(unsigned int num);
+unsigned long cpu_get_elf_hwcap(void);
+unsigned long cpu_get_elf_hwcap2(void);
 
-static inline bool cpu_have_feature(unsigned int num)
-{
-	return elf_hwcap & (1UL << num);
-}
+#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
+#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
 
 /* System capability check for constant caps */
 static inline bool __cpus_have_const_cap(int num)
@@ -638,11 +633,7 @@ static inline int arm64_get_ssbd_state(void)
 #endif
 }
 
-#ifdef CONFIG_ARM64_SSBD
 void arm64_set_ssbd_mitigation(bool state);
-#else
-static inline void arm64_set_ssbd_mitigation(bool state) {}
-#endif
 
 extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 5f1437099b99..2602bae334fb 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -89,6 +89,7 @@
 #define ARM_CPU_PART_CORTEX_A35		0xD04
 #define ARM_CPU_PART_CORTEX_A55		0xD05
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
+#define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -118,6 +119,7 @@
 #define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
 #define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
+#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index a44cf5225429..0679f781696d 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -65,12 +65,9 @@
 #define CACHE_FLUSH_IS_SAFE		1
 
 /* kprobes BRK opcodes with ESR encoding  */
-#define BRK64_ESR_MASK		0xFFFF
-#define BRK64_ESR_KPROBES	0x0004
-#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
 /* uprobes BRK opcodes with ESR encoding  */
-#define BRK64_ESR_UPROBES	0x0005
-#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_UPROBES << 5))
+#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
 
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
@@ -94,18 +91,24 @@ struct step_hook {
 	int (*fn)(struct pt_regs *regs, unsigned int esr);
 };
 
-void register_step_hook(struct step_hook *hook);
-void unregister_step_hook(struct step_hook *hook);
+void register_user_step_hook(struct step_hook *hook);
+void unregister_user_step_hook(struct step_hook *hook);
+
+void register_kernel_step_hook(struct step_hook *hook);
+void unregister_kernel_step_hook(struct step_hook *hook);
 
 struct break_hook {
 	struct list_head node;
-	u32 esr_val;
-	u32 esr_mask;
 	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	u16 imm;
+	u16 mask; /* These bits are ignored when comparing with imm */
 };
 
-void register_break_hook(struct break_hook *hook);
-void unregister_break_hook(struct break_hook *hook);
+void register_user_break_hook(struct break_hook *hook);
+void unregister_user_break_hook(struct break_hook *hook);
+
+void register_kernel_break_hook(struct break_hook *hook);
+void unregister_kernel_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 6adc1a90e7e6..355d120b78cb 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -214,10 +214,10 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 	set_thread_flag(TIF_32BIT);					\
  })
 #define COMPAT_ARCH_DLINFO
-extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
-				      int uses_interp);
+extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
+					  int uses_interp);
 #define compat_arch_setup_additional_pages \
-					aarch32_setup_vectors_page
+					aarch32_setup_additional_pages
 
 #endif /* CONFIG_COMPAT */
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 52233f00d53d..0e27fe91d5ea 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -156,9 +156,7 @@
 				 ESR_ELx_WFx_ISS_WFI)
 
 /* BRK instruction trap from AArch64 state */
-#define ESR_ELx_VAL_BRK64(imm)					\
-	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
-	 ((imm) & 0xffff))
+#define ESR_ELx_BRK64_ISS_COMMENT_MASK	0xffff
 
 /* ISS field definitions for System instruction traps */
 #define ESR_ELx_SYS64_ISS_RES0_SHIFT	22
@@ -198,9 +196,10 @@
 /*
  * User space cache operations have the following sysreg encoding
  * in System instructions.
- * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 14 }, WRITE (L=0)
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 13, 14 }, WRITE (L=0)
  */
 #define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC	14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVADP	13
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAP	12
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAU	11
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAC	10
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index c7e1a7837706..a56efb5626fa 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -23,26 +23,34 @@
 
 #include <asm/errno.h>
 
+#define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 do {									\
+	unsigned int loops = FUTEX_MAX_LOOPS;				\
+									\
 	uaccess_enable();						\
 	asm volatile(							\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w0, %w3, %2\n"						\
-"	cbnz	%w0, 1b\n"						\
-"	dmb	ish\n"							\
+"	cbz	%w0, 3f\n"						\
+"	sub	%w4, %w4, %w0\n"					\
+"	cbnz	%w4, 1b\n"						\
+"	mov	%w0, %w7\n"						\
 "3:\n"									\
+"	dmb	ish\n"							\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
-"4:	mov	%w0, %w5\n"						\
+"4:	mov	%w0, %w6\n"						\
 "	b	3b\n"							\
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
-	: "r" (oparg), "Ir" (-EFAULT)					\
+	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp),	\
+	  "+r" (loops)							\
+	: "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN)			\
 	: "memory");							\
 	uaccess_disable();						\
 } while (0)
@@ -57,23 +65,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w3, %w4",
+		__futex_atomic_op("mov	%w3, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w3, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w3, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w3, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w3, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:
@@ -93,6 +101,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
+	unsigned int loops = FUTEX_MAX_LOOPS;
 	u32 val, tmp;
 	u32 __user *uaddr;
 
@@ -104,24 +113,30 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
-"	sub	%w3, %w1, %w4\n"
-"	cbnz	%w3, 3f\n"
-"2:	stlxr	%w3, %w5, %2\n"
-"	cbnz	%w3, 1b\n"
-"	dmb	ish\n"
+"	sub	%w3, %w1, %w5\n"
+"	cbnz	%w3, 4f\n"
+"2:	stlxr	%w3, %w6, %2\n"
+"	cbz	%w3, 3f\n"
+"	sub	%w4, %w4, %w3\n"
+"	cbnz	%w4, 1b\n"
+"	mov	%w0, %w8\n"
 "3:\n"
+"	dmb	ish\n"
+"4:\n"
 "	.pushsection .fixup,\"ax\"\n"
-"4:	mov	%w0, %w6\n"
-"	b	3b\n"
+"5:	mov	%w0, %w7\n"
+"	b	4b\n"
 "	.popsection\n"
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 4b)
-	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
-	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
+	_ASM_EXTABLE(1b, 5b)
+	_ASM_EXTABLE(2b, 5b)
+	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+	: "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN)
 	: "memory");
 	uaccess_disable();
 
-	*uval = val;
+	if (!ret)
+		*uval = val;
+
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 400b80b49595..b4bfb6672168 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -17,6 +17,7 @@
 #define __ASM_HWCAP_H
 
 #include <uapi/asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 #define COMPAT_HWCAP_HALF	(1 << 1)
 #define COMPAT_HWCAP_THUMB	(1 << 2)
@@ -40,11 +41,67 @@
 #define COMPAT_HWCAP2_CRC32	(1 << 4)
 
 #ifndef __ASSEMBLY__
+#include <linux/log2.h>
+
+/*
+ * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
+ * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
+ * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here
+ * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart.
+ *
+ * Hwcaps should be set and tested within the kernel via the
+ * cpu_{set,have}_named_feature(feature) where feature is the unique suffix
+ * of KERNEL_HWCAP_{feature}.
+ */
+#define __khwcap_feature(x)		const_ilog2(HWCAP_ ## x)
+#define KERNEL_HWCAP_FP			__khwcap_feature(FP)
+#define KERNEL_HWCAP_ASIMD		__khwcap_feature(ASIMD)
+#define KERNEL_HWCAP_EVTSTRM		__khwcap_feature(EVTSTRM)
+#define KERNEL_HWCAP_AES		__khwcap_feature(AES)
+#define KERNEL_HWCAP_PMULL		__khwcap_feature(PMULL)
+#define KERNEL_HWCAP_SHA1		__khwcap_feature(SHA1)
+#define KERNEL_HWCAP_SHA2		__khwcap_feature(SHA2)
+#define KERNEL_HWCAP_CRC32		__khwcap_feature(CRC32)
+#define KERNEL_HWCAP_ATOMICS		__khwcap_feature(ATOMICS)
+#define KERNEL_HWCAP_FPHP		__khwcap_feature(FPHP)
+#define KERNEL_HWCAP_ASIMDHP		__khwcap_feature(ASIMDHP)
+#define KERNEL_HWCAP_CPUID		__khwcap_feature(CPUID)
+#define KERNEL_HWCAP_ASIMDRDM		__khwcap_feature(ASIMDRDM)
+#define KERNEL_HWCAP_JSCVT		__khwcap_feature(JSCVT)
+#define KERNEL_HWCAP_FCMA		__khwcap_feature(FCMA)
+#define KERNEL_HWCAP_LRCPC		__khwcap_feature(LRCPC)
+#define KERNEL_HWCAP_DCPOP		__khwcap_feature(DCPOP)
+#define KERNEL_HWCAP_SHA3		__khwcap_feature(SHA3)
+#define KERNEL_HWCAP_SM3		__khwcap_feature(SM3)
+#define KERNEL_HWCAP_SM4		__khwcap_feature(SM4)
+#define KERNEL_HWCAP_ASIMDDP		__khwcap_feature(ASIMDDP)
+#define KERNEL_HWCAP_SHA512		__khwcap_feature(SHA512)
+#define KERNEL_HWCAP_SVE		__khwcap_feature(SVE)
+#define KERNEL_HWCAP_ASIMDFHM		__khwcap_feature(ASIMDFHM)
+#define KERNEL_HWCAP_DIT		__khwcap_feature(DIT)
+#define KERNEL_HWCAP_USCAT		__khwcap_feature(USCAT)
+#define KERNEL_HWCAP_ILRCPC		__khwcap_feature(ILRCPC)
+#define KERNEL_HWCAP_FLAGM		__khwcap_feature(FLAGM)
+#define KERNEL_HWCAP_SSBS		__khwcap_feature(SSBS)
+#define KERNEL_HWCAP_SB			__khwcap_feature(SB)
+#define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
+#define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
+
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 32)
+#define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
+#define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
+#define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
+#define KERNEL_HWCAP_SVEPMULL		__khwcap2_feature(SVEPMULL)
+#define KERNEL_HWCAP_SVEBITPERM		__khwcap2_feature(SVEBITPERM)
+#define KERNEL_HWCAP_SVESHA3		__khwcap2_feature(SVESHA3)
+#define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
+
 /*
  * This yields a mask that user programs can use to figure out what
  * instruction set this cpu supports.
  */
-#define ELF_HWCAP		(elf_hwcap)
+#define ELF_HWCAP		cpu_get_elf_hwcap()
+#define ELF_HWCAP2		cpu_get_elf_hwcap2()
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
@@ -60,6 +117,5 @@ enum {
 #endif
 };
 
-extern unsigned long elf_hwcap;
 #endif
 #endif
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 8bb7210ac286..b807cb9b517d 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -124,8 +124,6 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #define __io_par(v)		__iormb(v)
 #define __iowmb()		wmb()
 
-#define mmiowb()		do { } while (0)
-
 /*
  * Relaxed I/O memory access primitives. These follow the Device memory
  * ordering rules but do not guarantee any ordering relative to Normal memory
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 43d8366c1e87..629963189085 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -43,7 +43,7 @@ static inline void arch_local_irq_enable(void)
 	asm volatile(ALTERNATIVE(
 		"msr	daifclr, #2		// arch_local_irq_enable\n"
 		"nop",
-		"msr_s  " __stringify(SYS_ICC_PMR_EL1) ",%0\n"
+		__msr_s(SYS_ICC_PMR_EL1, "%0")
 		"dsb	sy",
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
@@ -55,7 +55,7 @@ static inline void arch_local_irq_disable(void)
 {
 	asm volatile(ALTERNATIVE(
 		"msr	daifset, #2		// arch_local_irq_disable",
-		"msr_s  " __stringify(SYS_ICC_PMR_EL1) ", %0",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" ((unsigned long) GIC_PRIO_IRQOFF)
@@ -86,7 +86,7 @@ static inline unsigned long arch_local_save_flags(void)
 			"mov	%0, %1\n"
 			"nop\n"
 			"nop",
-			"mrs_s	%0, " __stringify(SYS_ICC_PMR_EL1) "\n"
+			__mrs_s("%0", SYS_ICC_PMR_EL1)
 			"ands	%1, %1, " __stringify(PSR_I_BIT) "\n"
 			"csel	%0, %0, %2, eq",
 			ARM64_HAS_IRQ_PRIO_MASKING)
@@ -116,7 +116,7 @@ static inline void arch_local_irq_restore(unsigned long flags)
 	asm volatile(ALTERNATIVE(
 			"msr	daif, %0\n"
 			"nop",
-			"msr_s	" __stringify(SYS_ICC_PMR_EL1) ", %0\n"
+			__msr_s(SYS_ICC_PMR_EL1, "%0")
 			"dsb	sy",
 			ARM64_HAS_IRQ_PRIO_MASKING)
 		: "+r" (flags)
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index d5a44cf859e9..21721fbf44e7 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -54,8 +54,6 @@ void arch_remove_kprobe(struct kprobe *);
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 			     unsigned long val, void *data);
-int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
-int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
 void kretprobe_trampoline(void);
 void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 4da765f2cca5..c3060833b7a5 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -30,7 +30,7 @@
 	({								\
 		u64 reg;						\
 		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
-					 "mrs_s %0, " __stringify(r##vh),\
+					 __mrs_s("%0", r##vh),		\
 					 ARM64_HAS_VIRT_HOST_EXTN)	\
 			     : "=r" (reg));				\
 		reg;							\
@@ -40,7 +40,7 @@
 	do {								\
 		u64 __val = (u64)(v);					\
 		asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
-					 "msr_s " __stringify(r##vh) ", %x0",\
+					 __msr_s(r##vh, "%x0"),		\
 					 ARM64_HAS_VIRT_HOST_EXTN)	\
 					 : : "rZ" (__val));		\
 	} while (0)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 290195168bb3..2cb8248fa2c8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -302,7 +302,7 @@ static inline void *phys_to_virt(phys_addr_t x)
  */
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
+#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c73bf0..dabba4b2c61f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)__get_free_page(PGALLOC_GFP);
+	struct page *page;
+
+	page = alloc_page(PGALLOC_GFP);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	return page_address(page);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
 {
 	BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmdp));
 	free_page((unsigned long)pmdp);
 }
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index de70c1eabf33..2c41b04708fe 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -478,6 +478,8 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 	return __pmd_to_phys(pmd);
 }
 
+static inline void pte_unmap(pte_t *pte) { }
+
 /* Find an entry in the third-level page table. */
 #define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
@@ -485,9 +487,6 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 #define pte_offset_kernel(dir,addr)	((pte_t *)__va(pte_offset_phys((dir), (addr))))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_offset_map_nested(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte)			do { } while (0)
-#define pte_unmap_nested(pte)		do { } while (0)
 
 #define pte_set_fixmap(addr)		((pte_t *)set_fixmap_offset(FIX_PTE, addr))
 #define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 15d49515efdd..d328540cb85e 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_POINTER_AUTH_H
 #define __ASM_POINTER_AUTH_H
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5d9ce62bdebd..fcd0e691b1ea 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -57,7 +57,15 @@
 #define TASK_SIZE_64		(UL(1) << vabits_user)
 
 #ifdef CONFIG_COMPAT
+#if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
 #define TASK_SIZE_32		UL(0x100000000)
+#else
+#define TASK_SIZE_32		(UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
 #define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index ec60174c8c18..b2de32939ada 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -305,6 +305,28 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->regs[0];
 }
 
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:	pt_regs of that context
+ * @n:		function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note that this chooses the most likely register mapping. In very rare
+ * cases this may not return correct data, for example, if one of the
+ * function parameters is 16 bytes or bigger. In such cases, we cannot
+ * get access the parameter correctly and the register assignment of
+ * subsequent parameters will be shifted.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						     unsigned int n)
+{
+#define NR_REG_ARGUMENTS 8
+	if (n < NR_REG_ARGUMENTS)
+		return pt_regs_read_reg(regs, n);
+	return 0;
+}
+
 /* We must avoid circular header include via sched.h */
 struct task_struct;
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index ffe47d766c25..63e0b92a5fbb 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2017 Arm Ltd.
 #ifndef __ASM_SDEI_H
 #define __ASM_SDEI_H
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index 81abea0b7650..58e288aaf0ba 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -20,8 +20,6 @@
 #ifdef CONFIG_COMPAT
 #include <linux/compat.h>
 
-#define AARCH32_KERN_SIGRET_CODE_OFFSET	0x500
-
 int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
 		       struct pt_regs *regs);
 int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 5412fa40825e..915809e4ac32 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -119,7 +119,7 @@ static inline pud_t *stage2_pud_offset(struct kvm *kvm,
 static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)
 {
 	if (kvm_stage2_has_pud(kvm))
-		pud_free(NULL, pud);
+		free_page((unsigned long)pud);
 }
 
 static inline bool stage2_pud_table_empty(struct kvm *kvm, pud_t *pudp)
@@ -192,7 +192,7 @@ static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
 static inline void stage2_pmd_free(struct kvm *kvm, pmd_t *pmd)
 {
 	if (kvm_stage2_has_pmd(kvm))
-		pmd_free(NULL, pmd);
+		free_page((unsigned long)pmd);
 }
 
 static inline bool stage2_pud_huge(struct kvm *kvm, pud_t pud)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5b267dec6194..3f7b917e8f3a 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -606,6 +606,20 @@
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 
+/* id_aa64zfr0 */
+#define ID_AA64ZFR0_SM4_SHIFT		40
+#define ID_AA64ZFR0_SHA3_SHIFT		32
+#define ID_AA64ZFR0_BITPERM_SHIFT	16
+#define ID_AA64ZFR0_AES_SHIFT		4
+#define ID_AA64ZFR0_SVEVER_SHIFT	0
+
+#define ID_AA64ZFR0_SM4			0x1
+#define ID_AA64ZFR0_SHA3		0x1
+#define ID_AA64ZFR0_BITPERM		0x1
+#define ID_AA64ZFR0_AES			0x1
+#define ID_AA64ZFR0_AES_PMULL		0x2
+#define ID_AA64ZFR0_SVEVER_SVE2		0x1
+
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
 #define ID_AA64MMFR0_TGRAN64_SHIFT	24
@@ -746,20 +760,39 @@
 #include <linux/build_bug.h>
 #include <linux/types.h>
 
-asm(
-"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
-"	.equ	.L__reg_num_x\\num, \\num\n"
-"	.endr\n"
+#define __DEFINE_MRS_MSR_S_REGNUM				\
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+"	.equ	.L__reg_num_x\\num, \\num\n"			\
+"	.endr\n"						\
 "	.equ	.L__reg_num_xzr, 31\n"
-"\n"
-"	.macro	mrs_s, rt, sreg\n"
-	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MRS_S						\
+	__DEFINE_MRS_MSR_S_REGNUM				\
+"	.macro	mrs_s, rt, sreg\n"				\
+	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))	\
 "	.endm\n"
-"\n"
-"	.macro	msr_s, sreg, rt\n"
-	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MSR_S						\
+	__DEFINE_MRS_MSR_S_REGNUM				\
+"	.macro	msr_s, sreg, rt\n"				\
+	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))	\
 "	.endm\n"
-);
+
+#define UNDEFINE_MRS_S						\
+"	.purgem	mrs_s\n"
+
+#define UNDEFINE_MSR_S						\
+"	.purgem	msr_s\n"
+
+#define __mrs_s(v, r)						\
+	DEFINE_MRS_S						\
+"	mrs_s " v ", " __stringify(r) "\n"			\
+	UNDEFINE_MRS_S
+
+#define __msr_s(r, v)						\
+	DEFINE_MSR_S						\
+"	msr_s " __stringify(r) ", " v "\n"			\
+	UNDEFINE_MSR_S
 
 /*
  * Unlike read_cpuid, calls to read_sysreg are never expected to be
@@ -787,13 +820,13 @@ asm(
  */
 #define read_sysreg_s(r) ({						\
 	u64 __val;							\
-	asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val));	\
+	asm volatile(__mrs_s("%0", r) : "=r" (__val));			\
 	__val;								\
 })
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)(v);						\
-	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
+	asm volatile(__msr_s(r, "%x0") : : "rZ" (__val));		\
 } while (0)
 
 /*
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 32693f34f431..fca95424e873 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -41,7 +41,6 @@ void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 			   int sig, int code, const char *name);
 
 struct mm_struct;
-extern void show_pte(unsigned long addr);
 extern void __show_regs(struct pt_regs *);
 
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..a287189ca8b4 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -27,6 +27,7 @@ static inline void __tlb_remove_table(void *_table)
 	free_page_and_swap_cache((struct page *)_table);
 }
 
+#define tlb_flush tlb_flush
 static void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
@@ -62,7 +63,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_remove_table(tlb, virt_to_page(pmdp));
+	struct page *page = virt_to_page(pmdp);
+
+	pgtable_pmd_page_dtor(page);
+	tlb_remove_table(tlb, page);
 }
 #endif
 
diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h
index 2b9a63771eda..f89263c8e11a 100644
--- a/arch/arm64/include/asm/vdso_datapage.h
+++ b/arch/arm64/include/asm/vdso_datapage.h
@@ -38,6 +38,7 @@ struct vdso_data {
 	__u32 tz_minuteswest;	/* Whacky timezone stuff */
 	__u32 tz_dsttime;
 	__u32 use_syscall;
+	__u32 hrtimer_res;
 };
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
index 0b5ec6e08c10..0a12115d9638 100644
--- a/arch/arm64/include/asm/vmap_stack.h
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2017 Arm Ltd.
 #ifndef __ASM_VMAP_STACK_H
 #define __ASM_VMAP_STACK_H
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 5f0750c2199c..1a772b162191 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -18,7 +18,7 @@
 #define _UAPI__ASM_HWCAP_H
 
 /*
- * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP
+ * HWCAP flags - for AT_HWCAP
  */
 #define HWCAP_FP		(1 << 0)
 #define HWCAP_ASIMD		(1 << 1)
@@ -53,4 +53,15 @@
 #define HWCAP_PACA		(1 << 30)
 #define HWCAP_PACG		(1UL << 31)
 
+/*
+ * HWCAP2 flags - for AT_HWCAP2
+ */
+#define HWCAP2_DCPODP		(1 << 0)
+#define HWCAP2_SVE2		(1 << 1)
+#define HWCAP2_SVEAES		(1 << 2)
+#define HWCAP2_SVEPMULL		(1 << 3)
+#define HWCAP2_SVEBITPERM	(1 << 4)
+#define HWCAP2_SVESHA3		(1 << 5)
+#define HWCAP2_SVESM4		(1 << 6)
+
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index cd434d0719c1..9e7dcb2c31c7 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,9 +7,9 @@ CPPFLAGS_vmlinux.lds	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_armv8_deprecated.o := -I$(src)
 
-CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_insn.o = -pg
-CFLAGS_REMOVE_return_address.o = -pg
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
@@ -27,8 +27,9 @@ OBJCOPYFLAGS := --prefix-symbols=__efistub_
 $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
-obj-$(CONFIG_COMPAT)			+= sys32.o kuser32.o signal32.o 	\
-					   sys_compat.o
+obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
+					   sigreturn32.o sys_compat.o
+obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
 obj-$(CONFIG_ARM64_MODULE_PLTS)		+= module-plts.o
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7f40dcbdd51d..e10e2a5d9ddc 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -94,7 +94,7 @@ int main(void)
   DEFINE(CLOCK_REALTIME,	CLOCK_REALTIME);
   DEFINE(CLOCK_MONOTONIC,	CLOCK_MONOTONIC);
   DEFINE(CLOCK_MONOTONIC_RAW,	CLOCK_MONOTONIC_RAW);
-  DEFINE(CLOCK_REALTIME_RES,	MONOTONIC_RES_NSEC);
+  DEFINE(CLOCK_REALTIME_RES,	offsetof(struct vdso_data, hrtimer_res));
   DEFINE(CLOCK_REALTIME_COARSE,	CLOCK_REALTIME_COARSE);
   DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE);
   DEFINE(CLOCK_COARSE_RES,	LOW_RES_NSEC);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 9950bb0cbd52..e88d4e7bdfc7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -19,6 +19,7 @@
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
 #include <linux/types.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
@@ -109,7 +110,6 @@ cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 
 atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
@@ -131,9 +131,9 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
-				      const char *hyp_vecs_start,
-				      const char *hyp_vecs_end)
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
+				    const char *hyp_vecs_start,
+				    const char *hyp_vecs_end)
 {
 	static DEFINE_RAW_SPINLOCK(bp_lock);
 	int cpu, slot = -1;
@@ -169,7 +169,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 #define __smccc_workaround_1_smc_start		NULL
 #define __smccc_workaround_1_smc_end		NULL
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
 {
@@ -177,23 +177,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
-				     bp_hardening_cb_t fn,
-				     const char *hyp_vecs_start,
-				     const char *hyp_vecs_end)
-{
-	u64 pfr0;
-
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
-	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
-	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
-		return;
-
-	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
-}
-
 #include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
@@ -220,60 +203,83 @@ static void qcom_link_stack_sanitization(void)
 		     : "=&r" (tmp));
 }
 
-static void
-enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+static bool __nospectre_v2;
+static int __init parse_nospectre_v2(char *str)
+{
+	__nospectre_v2 = true;
+	return 0;
+}
+early_param("nospectre_v2", parse_nospectre_v2);
+
+/*
+ * -1: No workaround
+ *  0: No workaround required
+ *  1: Workaround installed
+ */
+static int detect_harden_bp_fw(void)
 {
 	bp_hardening_cb_t cb;
 	void *smccc_start, *smccc_end;
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return;
+		return -1;
 
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_hvc_arch_workaround_1;
-		/* This is a guest, no need to patch KVM vectors */
-		smccc_start = NULL;
-		smccc_end = NULL;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_hvc_arch_workaround_1;
+			/* This is a guest, no need to patch KVM vectors */
+			smccc_start = NULL;
+			smccc_end = NULL;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	case PSCI_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc_start;
-		smccc_end = __smccc_workaround_1_smc_end;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_smc_arch_workaround_1;
+			smccc_start = __smccc_workaround_1_smc_start;
+			smccc_end = __smccc_workaround_1_smc_end;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	default:
-		return;
+		return -1;
 	}
 
 	if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
 	    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1))
 		cb = qcom_link_stack_sanitization;
 
-	install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
+	if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR))
+		install_bp_hardening_cb(cb, smccc_start, smccc_end);
 
-	return;
+	return 1;
 }
-#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
-#ifdef CONFIG_ARM64_SSBD
 DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
 
 int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
+static bool __ssb_safe = true;
 
 static const struct ssbd_options {
 	const char	*str;
@@ -343,6 +349,11 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
+		pr_info_once("SSBD disabled by kernel configuration\n");
+		return;
+	}
+
 	if (this_cpu_has_cap(ARM64_SSBS)) {
 		if (state)
 			asm volatile(SET_PSTATE_SSBS(0));
@@ -372,16 +383,28 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	struct arm_smccc_res res;
 	bool required = true;
 	s32 val;
+	bool this_cpu_safe = false;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
+	if (cpu_mitigations_off())
+		ssbd_state = ARM64_SSBD_FORCE_DISABLE;
+
+	/* delay setting __ssb_safe until we get a firmware response */
+	if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list))
+		this_cpu_safe = true;
+
 	if (this_cpu_has_cap(ARM64_SSBS)) {
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		required = false;
 		goto out_printmsg;
 	}
 
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -398,6 +421,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 
 	default:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -406,14 +431,18 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	switch (val) {
 	case SMCCC_RET_NOT_SUPPORTED:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 
+	/* machines with mixed mitigation requirements must not return this */
 	case SMCCC_RET_NOT_REQUIRED:
 		pr_info_once("%s mitigation not required\n", entry->desc);
 		ssbd_state = ARM64_SSBD_MITIGATED;
 		return false;
 
 	case SMCCC_RET_SUCCESS:
+		__ssb_safe = false;
 		required = true;
 		break;
 
@@ -423,6 +452,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 
 	default:
 		WARN_ON(1);
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -462,7 +493,14 @@ out_printmsg:
 
 	return required;
 }
-#endif	/* CONFIG_ARM64_SSBD */
+
+/* known invulnerable cores */
+static const struct midr_range arm64_ssb_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	{},
+};
 
 static void __maybe_unused
 cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
@@ -507,26 +545,67 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
 	.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,			\
 	CAP_MIDR_RANGE_LIST(midr_list)
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+/* Track overall mitigation state. We are only mitigated if all cores are ok */
+static bool __hardenbp_enab = true;
+static bool __spectrev2_safe = true;
 
 /*
- * List of CPUs where we need to issue a psci call to
- * harden the branch predictor.
+ * List of CPUs that do not need any Spectre-v2 mitigation at all.
  */
-static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
-	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
-	MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
-	{},
+static const struct midr_range spectre_v2_safe_list[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	{ /* sentinel */ }
 };
 
-#endif
+/*
+ * Track overall bp hardening for all heterogeneous cores in the machine.
+ * We are only considered "safe" if all booted cores are known safe.
+ */
+static bool __maybe_unused
+check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	int need_wa;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	/* If the CPU has CSV2 set, we're safe */
+	if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1),
+						 ID_AA64PFR0_CSV2_SHIFT))
+		return false;
+
+	/* Alternatively, we have a list of unaffected CPUs */
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+		return false;
+
+	/* Fallback to firmware detection */
+	need_wa = detect_harden_bp_fw();
+	if (!need_wa)
+		return false;
+
+	__spectrev2_safe = false;
+
+	if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) {
+		pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	/* forced off */
+	if (__nospectre_v2 || cpu_mitigations_off()) {
+		pr_info_once("spectrev2 mitigation disabled by command line option\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	if (need_wa < 0) {
+		pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n");
+		__hardenbp_enab = false;
+	}
+
+	return (need_wa > 0);
+}
 
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
@@ -603,6 +682,16 @@ static const struct midr_range workaround_clean_cache[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+static const struct midr_range erratum_1188873_list[] = {
+	/* Cortex-A76 r0p0 to r2p0 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+	/* Neoverse-N1 r0p0 to r2p0 */
+	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 2, 0),
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -701,13 +790,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 	},
 #endif
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
-		.cpu_enable = enable_smccc_arch_workaround_1,
-		ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = check_branch_predictor,
 	},
-#endif
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 	{
 		.desc = "EL2 vector hardening",
@@ -715,20 +802,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
 #endif
-#ifdef CONFIG_ARM64_SSBD
 	{
 		.desc = "Speculative Store Bypass Disable",
 		.capability = ARM64_SSBD,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_ssbd_mitigation,
+		.midr_range_list = arm64_ssb_cpus,
 	},
-#endif
 #ifdef CONFIG_ARM64_ERRATUM_1188873
 	{
-		/* Cortex-A76 r0p0 to r2p0 */
 		.desc = "ARM erratum 1188873",
 		.capability = ARM64_WORKAROUND_1188873,
-		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+		ERRATA_MIDR_RANGE_LIST(erratum_1188873_list),
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1165522
@@ -742,3 +827,38 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 	}
 };
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	if (__spectrev2_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (__hardenbp_enab)
+		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (__ssb_safe)
+		return sprintf(buf, "Not affected\n");
+
+	switch (ssbd_state) {
+	case ARM64_SSBD_KERNEL:
+	case ARM64_SSBD_FORCE_ENABLE:
+		if (IS_ENABLED(CONFIG_ARM64_SSBD))
+			return sprintf(buf,
+			    "Mitigation: Speculative Store Bypass disabled via prctl\n");
+	}
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index ea001241bdd4..00f8b8612b69 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -85,6 +85,7 @@ static const char *__init cpu_read_enable_method(int cpu)
 				pr_err("%pOF: missing enable-method property\n",
 					dn);
 		}
+		of_node_put(dn);
 	} else {
 		enable_method = acpi_get_enable_method(cpu);
 		if (!enable_method) {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4061de10cea6..2b807f129e60 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -25,6 +25,7 @@
 #include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -35,8 +36,8 @@
 #include <asm/traps.h>
 #include <asm/virt.h>
 
-unsigned long elf_hwcap __read_mostly;
-EXPORT_SYMBOL_GPL(elf_hwcap);
+/* Kernel representation of AT_HWCAP and AT_HWCAP2 */
+static unsigned long elf_hwcap __read_mostly;
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP_DEFAULT	\
@@ -184,6 +185,15 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -392,7 +402,7 @@ static const struct __ftr_reg_entry {
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
 	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
-	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
+	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -947,7 +957,7 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
 	return has_cpuid_feature(entry, scope);
 }
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static bool __meltdown_safe = true;
 static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
 
 static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
@@ -966,7 +976,17 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		{ /* sentinel */ }
 	};
-	char const *str = "command line option";
+	char const *str = "kpti command line option";
+	bool meltdown_safe;
+
+	meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+
+	/* Defer to CPU feature registers */
+	if (has_cpuid_feature(entry, scope))
+		meltdown_safe = true;
+
+	if (!meltdown_safe)
+		__meltdown_safe = false;
 
 	/*
 	 * For reasons that aren't entirely clear, enabling KPTI on Cavium
@@ -978,6 +998,24 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		__kpti_forced = -1;
 	}
 
+	/* Useful for KASLR robustness */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) {
+		if (!__kpti_forced) {
+			str = "KASLR";
+			__kpti_forced = 1;
+		}
+	}
+
+	if (cpu_mitigations_off() && !__kpti_forced) {
+		str = "mitigations=off";
+		__kpti_forced = -1;
+	}
+
+	if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) {
+		pr_info_once("kernel page table isolation disabled by kernel configuration\n");
+		return false;
+	}
+
 	/* Forced? */
 	if (__kpti_forced) {
 		pr_info_once("kernel page table isolation forced %s by %s\n",
@@ -985,18 +1023,10 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		return __kpti_forced > 0;
 	}
 
-	/* Useful for KASLR robustness */
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return kaslr_offset() > 0;
-
-	/* Don't force KPTI for CPUs that are not vulnerable */
-	if (is_midr_in_range_list(read_cpuid_id(), kpti_safe_list))
-		return false;
-
-	/* Defer to CPU feature registers */
-	return !has_cpuid_feature(entry, scope);
+	return !meltdown_safe;
 }
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static void
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
@@ -1026,6 +1056,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 
 	return;
 }
+#else
+static void
+kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
+{
+}
+#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 static int __init parse_kpti(char *str)
 {
@@ -1039,7 +1075,6 @@ static int __init parse_kpti(char *str)
 	return 0;
 }
 early_param("kpti", parse_kpti);
-#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 static inline void __cpu_enable_hw_dbm(void)
@@ -1306,7 +1341,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	{
 		.desc = "Kernel page table isolation (KPTI)",
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
@@ -1322,7 +1356,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = unmap_kernel_at_el0,
 		.cpu_enable = kpti_install_ng_mappings,
 	},
-#endif
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
@@ -1340,6 +1373,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
 		.min_field_value = 1,
 	},
+	{
+		.desc = "Data cache clean to Point of Deep Persistence",
+		.capability = ARM64_HAS_DCPODP,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
+		.min_field_value = 2,
+	},
 #endif
 #ifdef CONFIG_ARM64_SVE
 	{
@@ -1571,39 +1614,46 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
 #endif
 
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FLAGM),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_DIT),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SB),
-	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
+	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
 #endif
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
 #ifdef CONFIG_ARM64_PTR_AUTH
-	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, HWCAP_PACA),
-	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, HWCAP_PACG),
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
 #endif
 	{},
 };
@@ -1623,7 +1673,7 @@ static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
-		elf_hwcap |= cap->hwcap;
+		cpu_set_feature(cap->hwcap);
 		break;
 #ifdef CONFIG_COMPAT
 	case CAP_COMPAT_HWCAP:
@@ -1646,7 +1696,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
-		rc = (elf_hwcap & cap->hwcap) != 0;
+		rc = cpu_have_feature(cap->hwcap);
 		break;
 #ifdef CONFIG_COMPAT
 	case CAP_COMPAT_HWCAP:
@@ -1667,7 +1717,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 {
 	/* We support emulation of accesses to CPU ID feature registers */
-	elf_hwcap |= HWCAP_CPUID;
+	cpu_set_named_feature(CPUID);
 	for (; hwcaps->matches; hwcaps++)
 		if (hwcaps->matches(hwcaps, cpucap_default_scope(hwcaps)))
 			cap_set_elf_hwcap(hwcaps);
@@ -1947,6 +1997,35 @@ bool this_cpu_has_cap(unsigned int n)
 	return false;
 }
 
+void cpu_set_feature(unsigned int num)
+{
+	WARN_ON(num >= MAX_CPU_FEATURES);
+	elf_hwcap |= BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_set_feature);
+
+bool cpu_have_feature(unsigned int num)
+{
+	WARN_ON(num >= MAX_CPU_FEATURES);
+	return elf_hwcap & BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_have_feature);
+
+unsigned long cpu_get_elf_hwcap(void)
+{
+	/*
+	 * We currently only populate the first 32 bits of AT_HWCAP. Please
+	 * note that for userspace compatibility we guarantee that bits 62
+	 * and 63 will always be returned as 0.
+	 */
+	return lower_32_bits(elf_hwcap);
+}
+
+unsigned long cpu_get_elf_hwcap2(void)
+{
+	return upper_32_bits(elf_hwcap);
+}
+
 static void __init setup_system_capabilities(void)
 {
 	/*
@@ -2101,3 +2180,15 @@ static int __init enable_mrs_emulation(void)
 }
 
 core_initcall(enable_mrs_emulation);
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	if (__meltdown_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (arm64_kernel_unmapped_at_el0())
+		return sprintf(buf, "Mitigation: PTI\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index ca0685f33900..f6f7936be6e7 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -85,6 +85,13 @@ static const char *const hwcap_str[] = {
 	"sb",
 	"paca",
 	"pacg",
+	"dcpodp",
+	"sve2",
+	"sveaes",
+	"svepmull",
+	"svebitperm",
+	"svesha3",
+	"svesm4",
 	NULL
 };
 
@@ -167,7 +174,7 @@ static int c_show(struct seq_file *m, void *v)
 #endif /* CONFIG_COMPAT */
 		} else {
 			for (j = 0; hwcap_str[j]; j++)
-				if (elf_hwcap & (1 << j))
+				if (cpu_have_feature(j))
 					seq_printf(m, " %s", hwcap_str[j]);
 		}
 		seq_puts(m, "\n");
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index d7bb6aefae0a..555b6bd2f3d6 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -135,6 +135,7 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
  */
 static int clear_os_lock(unsigned int cpu)
 {
+	write_sysreg(0, osdlr_el1);
 	write_sysreg(0, oslar_el1);
 	isb();
 	return 0;
@@ -163,25 +164,46 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(clear_regs_spsr_ss);
 
-/* EL1 Single Step Handler hooks */
-static LIST_HEAD(step_hook);
-static DEFINE_SPINLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(debug_hook_lock);
+static LIST_HEAD(user_step_hook);
+static LIST_HEAD(kernel_step_hook);
 
-void register_step_hook(struct step_hook *hook)
+static void register_debug_hook(struct list_head *node, struct list_head *list)
 {
-	spin_lock(&step_hook_lock);
-	list_add_rcu(&hook->node, &step_hook);
-	spin_unlock(&step_hook_lock);
+	spin_lock(&debug_hook_lock);
+	list_add_rcu(node, list);
+	spin_unlock(&debug_hook_lock);
+
 }
 
-void unregister_step_hook(struct step_hook *hook)
+static void unregister_debug_hook(struct list_head *node)
 {
-	spin_lock(&step_hook_lock);
-	list_del_rcu(&hook->node);
-	spin_unlock(&step_hook_lock);
+	spin_lock(&debug_hook_lock);
+	list_del_rcu(node);
+	spin_unlock(&debug_hook_lock);
 	synchronize_rcu();
 }
 
+void register_user_step_hook(struct step_hook *hook)
+{
+	register_debug_hook(&hook->node, &user_step_hook);
+}
+
+void unregister_user_step_hook(struct step_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_step_hook(struct step_hook *hook)
+{
+	register_debug_hook(&hook->node, &kernel_step_hook);
+}
+
+void unregister_kernel_step_hook(struct step_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
+}
+
 /*
  * Call registered single step handlers
  * There is no Syndrome info to check for determining the handler.
@@ -191,11 +213,14 @@ void unregister_step_hook(struct step_hook *hook)
 static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 {
 	struct step_hook *hook;
+	struct list_head *list;
 	int retval = DBG_HOOK_ERROR;
 
+	list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
+
 	rcu_read_lock();
 
-	list_for_each_entry_rcu(hook, &step_hook, node)	{
+	list_for_each_entry_rcu(hook, list, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
@@ -222,7 +247,7 @@ static void send_user_sigtrap(int si_code)
 			     "User debug trap");
 }
 
-static int single_step_handler(unsigned long addr, unsigned int esr,
+static int single_step_handler(unsigned long unused, unsigned int esr,
 			       struct pt_regs *regs)
 {
 	bool handler_found = false;
@@ -234,10 +259,6 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 	if (!reinstall_suspended_bps(regs))
 		return 0;
 
-#ifdef	CONFIG_KPROBES
-	if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
-		handler_found = true;
-#endif
 	if (!handler_found && call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
 		handler_found = true;
 
@@ -264,61 +285,59 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 }
 NOKPROBE_SYMBOL(single_step_handler);
 
-/*
- * Breakpoint handler is re-entrant as another breakpoint can
- * hit within breakpoint handler, especically in kprobes.
- * Use reader/writer locks instead of plain spinlock.
- */
-static LIST_HEAD(break_hook);
-static DEFINE_SPINLOCK(break_hook_lock);
+static LIST_HEAD(user_break_hook);
+static LIST_HEAD(kernel_break_hook);
 
-void register_break_hook(struct break_hook *hook)
+void register_user_break_hook(struct break_hook *hook)
 {
-	spin_lock(&break_hook_lock);
-	list_add_rcu(&hook->node, &break_hook);
-	spin_unlock(&break_hook_lock);
+	register_debug_hook(&hook->node, &user_break_hook);
 }
 
-void unregister_break_hook(struct break_hook *hook)
+void unregister_user_break_hook(struct break_hook *hook)
 {
-	spin_lock(&break_hook_lock);
-	list_del_rcu(&hook->node);
-	spin_unlock(&break_hook_lock);
-	synchronize_rcu();
+	unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_break_hook(struct break_hook *hook)
+{
+	register_debug_hook(&hook->node, &kernel_break_hook);
+}
+
+void unregister_kernel_break_hook(struct break_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 {
 	struct break_hook *hook;
+	struct list_head *list;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
+	list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
+
 	rcu_read_lock();
-	list_for_each_entry_rcu(hook, &break_hook, node)
-		if ((esr & hook->esr_mask) == hook->esr_val)
+	list_for_each_entry_rcu(hook, list, node) {
+		unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+		if ((comment & ~hook->mask) == hook->imm)
 			fn = hook->fn;
+	}
 	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
 NOKPROBE_SYMBOL(call_break_hook);
 
-static int brk_handler(unsigned long addr, unsigned int esr,
+static int brk_handler(unsigned long unused, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	bool handler_found = false;
-
-#ifdef	CONFIG_KPROBES
-	if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
-		if (kprobe_breakpoint_handler(regs, esr) == DBG_HOOK_HANDLED)
-			handler_found = true;
-	}
-#endif
-	if (!handler_found && call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
-		handler_found = true;
+	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
+		return 0;
 
-	if (!handler_found && user_mode(regs)) {
+	if (user_mode(regs)) {
 		send_user_sigtrap(TRAP_BRKPT);
-	} else if (!handler_found) {
+	} else {
 		pr_warn("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
 	}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c50a7a75f2e0..1a7811b7e3c4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -336,6 +336,21 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+alternative_if_not ARM64_WORKAROUND_1188873
+	b	4f
+alternative_else_nop_endif
+	/*
+	 * if (x22.mode32 == cntkctl_el1.el0vcten)
+	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
+	 */
+	mrs	x1, cntkctl_el1
+	eon	x0, x1, x22, lsr #3
+	tbz	x0, #1, 4f
+	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x1
+4:
+#endif
 	apply_ssbd 0, x0, x1
 	.endif
 
@@ -362,11 +377,11 @@ alternative_else_nop_endif
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	4f
+	bne	5f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-4:
+5:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 5ebe73b69961..735cf1f8b109 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1258,14 +1258,14 @@ static inline void fpsimd_hotplug_init(void) { }
  */
 static int __init fpsimd_init(void)
 {
-	if (elf_hwcap & HWCAP_FP) {
+	if (cpu_have_named_feature(FP)) {
 		fpsimd_pm_init();
 		fpsimd_hotplug_init();
 	} else {
 		pr_notice("Floating-point is not implemented\n");
 	}
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
 	return sve_sysctl_init();
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index eecf7927dab0..fcae3f85c6cd 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -505,7 +505,7 @@ ENTRY(el2_setup)
 	 * kernel is intended to run at EL2.
 	 */
 	mrs	x2, id_aa64mmfr1_el1
-	ubfx	x2, x2, #8, #4
+	ubfx	x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
 #else
 	mov	x2, xzr
 #endif
@@ -538,7 +538,7 @@ set_hcr:
 #ifdef CONFIG_ARM_GIC_V3
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
-	ubfx	x0, x0, #24, #4
+	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
 	cbz	x0, 3f
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
@@ -564,8 +564,8 @@ set_hcr:
 #endif
 
 	/* EL2 debug */
-	mrs	x1, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	x0, x1, #8, #4
+	mrs	x1, id_aa64dfr0_el1
+	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	x0, #1
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
@@ -574,7 +574,7 @@ set_hcr:
 	csel	x3, xzr, x0, lt			// all PMU counters from EL1
 
 	/* Statistical profiling */
-	ubfx	x0, x1, #32, #4			// Check ID_AA64DFR0_EL1 PMSVer
+	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cbz	x0, 7f				// Skip if SPE not present
 	cbnz	x2, 6f				// VHE?
 	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
@@ -684,7 +684,7 @@ ENTRY(__boot_cpu_mode)
  * with MMU turned off.
  */
 ENTRY(__early_cpu_boot_status)
-	.long 	0
+	.quad 	0
 
 	.popsection
 
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 691854b77c7f..30853d5b7859 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -244,9 +244,6 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
 
 static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
@@ -254,9 +251,6 @@ NOKPROBE_SYMBOL(kgdb_brk_fn)
 
 static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	compiled_break = 1;
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 
@@ -266,7 +260,7 @@ NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
 
 static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs) || !kgdb_single_step)
+	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
@@ -275,15 +269,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
 
 static struct break_hook kgdb_brkpt_hook = {
-	.esr_mask	= 0xffffffff,
-	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM),
-	.fn		= kgdb_brk_fn
+	.fn		= kgdb_brk_fn,
+	.imm		= KGDB_DYN_DBG_BRK_IMM,
 };
 
 static struct break_hook kgdb_compiled_brkpt_hook = {
-	.esr_mask	= 0xffffffff,
-	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM),
-	.fn		= kgdb_compiled_brk_fn
+	.fn		= kgdb_compiled_brk_fn,
+	.imm		= KGDB_COMPILED_DBG_BRK_IMM,
 };
 
 static struct step_hook kgdb_step_hook = {
@@ -332,9 +324,9 @@ int kgdb_arch_init(void)
 	if (ret != 0)
 		return ret;
 
-	register_break_hook(&kgdb_brkpt_hook);
-	register_break_hook(&kgdb_compiled_brkpt_hook);
-	register_step_hook(&kgdb_step_hook);
+	register_kernel_break_hook(&kgdb_brkpt_hook);
+	register_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+	register_kernel_step_hook(&kgdb_step_hook);
 	return 0;
 }
 
@@ -345,9 +337,9 @@ int kgdb_arch_init(void)
  */
 void kgdb_arch_exit(void)
 {
-	unregister_break_hook(&kgdb_brkpt_hook);
-	unregister_break_hook(&kgdb_compiled_brkpt_hook);
-	unregister_step_hook(&kgdb_step_hook);
+	unregister_kernel_break_hook(&kgdb_brkpt_hook);
+	unregister_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+	unregister_kernel_step_hook(&kgdb_step_hook);
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 997e6b27ff6a..49825e9e421e 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -1,29 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Low-level user helpers placed in the vectors page for AArch32.
+ * AArch32 user helpers.
  * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
  *
  * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2012-2018 ARM Ltd.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- *
- * AArch32 user helpers.
- *
- * Each segment is 32-byte aligned and will be moved to the top of the high
- * vector page.  New segments (if ever needed) must be added in front of
- * existing ones.  This mechanism should be used only for things that are
- * really small and justified, and not be abused freely.
+ * The kuser helpers below are mapped at a fixed address by
+ * aarch32_setup_additional_pages() and are provided for compatibility
+ * reasons with 32 bit (aarch32) applications that need them.
  *
  * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
@@ -77,42 +62,3 @@ __kuser_helper_version:			// 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 	.globl	__kuser_helper_end
 __kuser_helper_end:
-
-/*
- * AArch32 sigreturn code
- *
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- *
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-	.globl __aarch32_sigret_code_start
-__aarch32_sigret_code_start:
-
-	/*
-	 * ARM Code
-	 */
-	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
-
-	/*
-	 * ARM code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
-
-        .globl __aarch32_sigret_code_end
-__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 4addb38bc250..6164d389eed6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -431,7 +431,7 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
 	return val;
 }
 
-static inline u64 armv8pmu_read_counter(struct perf_event *event)
+static u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -468,7 +468,7 @@ static inline void armv8pmu_write_hw_counter(struct perf_event *event,
 	}
 }
 
-static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
+static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 7a679caf4585..2509fcb6d404 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -439,15 +439,12 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
 	return DBG_HOOK_ERROR;
 }
 
-int __kprobes
+static int __kprobes
 kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	int retval;
 
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	/* return error if this is not our step */
 	retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
 
@@ -461,16 +458,22 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 	return retval;
 }
 
-int __kprobes
+static struct step_hook kprobes_step_hook = {
+	.fn = kprobe_single_step_handler,
+};
+
+static int __kprobes
 kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	kprobe_handler(regs);
 	return DBG_HOOK_HANDLED;
 }
 
+static struct break_hook kprobes_break_hook = {
+	.imm = KPROBES_BRK_IMM,
+	.fn = kprobe_breakpoint_handler,
+};
+
 /*
  * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
  * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
@@ -599,5 +602,8 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 
 int __init arch_init_kprobes(void)
 {
+	register_kernel_break_hook(&kprobes_break_hook);
+	register_kernel_step_hook(&kprobes_step_hook);
+
 	return 0;
 }
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 636ca0119c0e..605945eac1f8 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -171,7 +171,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self,
 static int uprobe_breakpoint_handler(struct pt_regs *regs,
 		unsigned int esr)
 {
-	if (user_mode(regs) && uprobe_pre_sstep_notifier(regs))
+	if (uprobe_pre_sstep_notifier(regs))
 		return DBG_HOOK_HANDLED;
 
 	return DBG_HOOK_ERROR;
@@ -182,21 +182,16 @@ static int uprobe_single_step_handler(struct pt_regs *regs,
 {
 	struct uprobe_task *utask = current->utask;
 
-	if (user_mode(regs)) {
-		WARN_ON(utask &&
-			(instruction_pointer(regs) != utask->xol_vaddr + 4));
-
-		if (uprobe_post_sstep_notifier(regs))
-			return DBG_HOOK_HANDLED;
-	}
+	WARN_ON(utask && (instruction_pointer(regs) != utask->xol_vaddr + 4));
+	if (uprobe_post_sstep_notifier(regs))
+		return DBG_HOOK_HANDLED;
 
 	return DBG_HOOK_ERROR;
 }
 
 /* uprobe breakpoint handler hook */
 static struct break_hook uprobes_break_hook = {
-	.esr_mask = BRK64_ESR_MASK,
-	.esr_val = BRK64_ESR_UPROBES,
+	.imm = UPROBES_BRK_IMM,
 	.fn = uprobe_breakpoint_handler,
 };
 
@@ -207,8 +202,8 @@ static struct step_hook uprobes_step_hook = {
 
 static int __init arch_init_uprobes(void)
 {
-	register_break_hook(&uprobes_break_hook);
-	register_step_hook(&uprobes_step_hook);
+	register_user_break_hook(&uprobes_break_hook);
+	register_user_step_hook(&uprobes_step_hook);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index cb7800acd19f..caea6e25db2a 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -403,8 +403,7 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = AARCH32_VECTORS_BASE +
-			  AARCH32_KERN_SIGRET_CODE_OFFSET +
+		retcode = (unsigned long)current->mm->context.vdso +
 			  (idx << 2) + thumb;
 	}
 
diff --git a/arch/arm64/kernel/sigreturn32.S b/arch/arm64/kernel/sigreturn32.S
new file mode 100644
index 000000000000..475d30d471ac
--- /dev/null
+++ b/arch/arm64/kernel/sigreturn32.S
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch32 sigreturn code.
+ * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
+ *
+ * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
+ * Copyright (C) 2012-2018 ARM Ltd.
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+
+#include <asm/unistd.h>
+
+	.globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+	/*
+	 * ARM Code
+	 */
+	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3		// mov	r7, #__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef		// svc	#__NR_compat_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
+
+	/*
+	 * ARM code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
+
+        .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d908b5e9e949..b00ec7d483d1 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -140,8 +140,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 #endif
 
 	walk_stackframe(current, &frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_regs);
 
@@ -172,8 +170,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 #endif
 
 	walk_stackframe(tsk, &frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
 	put_task_stack(tsk);
 }
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index b44065fb1616..6f91e8116514 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -31,7 +31,7 @@
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, off_t, off)
+		unsigned long, fd, unsigned long, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 29755989f616..ade32046f3fe 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -462,6 +462,9 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAC:	/* DC CVAC, gets promoted */
 		__user_cache_maint("dc civac", address, ret);
 		break;
+	case ESR_ELx_SYS64_ISS_CRM_DC_CVADP:	/* DC CVADP */
+		__user_cache_maint("sys 3, c7, c13, 1", address, ret);
+		break;
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAP:	/* DC CVAP */
 		__user_cache_maint("sys 3, c7, c12, 1", address, ret);
 		break;
@@ -496,7 +499,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 
-	pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+	pt_regs_write_reg(regs, rt, arch_timer_read_counter());
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
@@ -668,7 +671,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
 	int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
-	u64 val = arch_counter_get_cntvct();
+	u64 val = arch_timer_read_counter();
 
 	pt_regs_write_reg(regs, rt, lower_32_bits(val));
 	pt_regs_write_reg(regs, rt2, upper_32_bits(val));
@@ -950,9 +953,6 @@ int is_valid_bugaddr(unsigned long addr)
 
 static int bug_handler(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	switch (report_bug(regs->pc, regs)) {
 	case BUG_TRAP_TYPE_BUG:
 		die("Oops - BUG", regs, 0);
@@ -972,9 +972,8 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
 }
 
 static struct break_hook bug_break_hook = {
-	.esr_val = 0xf2000000 | BUG_BRK_IMM,
-	.esr_mask = 0xffffffff,
 	.fn = bug_handler,
+	.imm = BUG_BRK_IMM,
 };
 
 #ifdef CONFIG_KASAN_SW_TAGS
@@ -992,9 +991,6 @@ static int kasan_handler(struct pt_regs *regs, unsigned int esr)
 	u64 addr = regs->regs[0];
 	u64 pc = regs->pc;
 
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	kasan_report(addr, size, write, pc);
 
 	/*
@@ -1019,13 +1015,10 @@ static int kasan_handler(struct pt_regs *regs, unsigned int esr)
 	return DBG_HOOK_HANDLED;
 }
 
-#define KASAN_ESR_VAL (0xf2000000 | KASAN_BRK_IMM)
-#define KASAN_ESR_MASK 0xffffff00
-
 static struct break_hook kasan_break_hook = {
-	.esr_val = KASAN_ESR_VAL,
-	.esr_mask = KASAN_ESR_MASK,
-	.fn = kasan_handler,
+	.fn	= kasan_handler,
+	.imm	= KASAN_BRK_IMM,
+	.mask	= KASAN_BRK_MASK,
 };
 #endif
 
@@ -1037,7 +1030,9 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
 		struct pt_regs *regs)
 {
 #ifdef CONFIG_KASAN_SW_TAGS
-	if ((esr & KASAN_ESR_MASK) == KASAN_ESR_VAL)
+	unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+	if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
@@ -1046,8 +1041,8 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
 /* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
-	register_break_hook(&bug_break_hook);
+	register_kernel_break_hook(&bug_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
-	register_break_hook(&kasan_break_hook);
+	register_kernel_break_hook(&kasan_break_hook);
 #endif
 }
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 2d419006ad43..8074cbd3a3a8 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -1,5 +1,5 @@
 /*
- * VDSO implementation for AArch64 and vector page setup for AArch32.
+ * VDSO implementations.
  *
  * Copyright (C) 2012 ARM Limited
  *
@@ -53,61 +53,129 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
 /*
  * Create and map the vectors page for AArch32 tasks.
  */
-static struct page *vectors_page[1] __ro_after_init;
+#define C_VECTORS	0
+#define C_SIGPAGE	1
+#define C_PAGES		(C_SIGPAGE + 1)
+static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
+static const struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
+	{
+		.name	= "[vectors]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_VECTORS],
+	},
+	{
+		.name	= "[sigpage]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
+	},
+};
 
-static int __init alloc_vectors_page(void)
+static int aarch32_alloc_kuser_vdso_page(void)
 {
 	extern char __kuser_helper_start[], __kuser_helper_end[];
-	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
-
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
-	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
-	unsigned long vpage;
+	unsigned long vdso_page;
 
-	vpage = get_zeroed_page(GFP_ATOMIC);
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
 
-	if (!vpage)
+	vdso_page = get_zeroed_page(GFP_ATOMIC);
+	if (!vdso_page)
 		return -ENOMEM;
 
-	/* kuser helpers */
-	memcpy((void *)vpage + 0x1000 - kuser_sz, __kuser_helper_start,
-		kuser_sz);
+	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
+	       kuser_sz);
+	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
+	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+	return 0;
+}
 
-	/* sigreturn code */
-	memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
-               __aarch32_sigret_code_start, sigret_sz);
+static int __init aarch32_alloc_vdso_pages(void)
+{
+	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
+	unsigned long sigpage;
+	int ret;
 
-	flush_icache_range(vpage, vpage + PAGE_SIZE);
-	vectors_page[0] = virt_to_page(vpage);
+	sigpage = get_zeroed_page(GFP_ATOMIC);
+	if (!sigpage)
+		return -ENOMEM;
 
-	return 0;
+	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
+	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
+	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+
+	ret = aarch32_alloc_kuser_vdso_page();
+	if (ret)
+		free_page(sigpage);
+
+	return ret;
 }
-arch_initcall(alloc_vectors_page);
+arch_initcall(aarch32_alloc_vdso_pages);
 
-int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
+static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 {
-	struct mm_struct *mm = current->mm;
-	unsigned long addr = AARCH32_VECTORS_BASE;
-	static const struct vm_special_mapping spec = {
-		.name	= "[vectors]",
-		.pages	= vectors_page,
+	void *ret;
+
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
+
+	/*
+	 * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's
+	 * not safe to CoW the page containing the CPU exception vectors.
+	 */
+	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
+				       VM_READ | VM_EXEC |
+				       VM_MAYREAD | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_VECTORS]);
 
-	};
+	return PTR_ERR_OR_ZERO(ret);
+}
+
+static int aarch32_sigreturn_setup(struct mm_struct *mm)
+{
+	unsigned long addr;
 	void *ret;
 
-	if (down_write_killable(&mm->mmap_sem))
-		return -EINTR;
-	current->mm->context.vdso = (void *)addr;
+	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = ERR_PTR(addr);
+		goto out;
+	}
 
-	/* Map vectors page at the high address. */
+	/*
+	 * VM_MAYWRITE is required to allow gdb to Copy-on-Write and
+	 * set breakpoints.
+	 */
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
-				       VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
-				       &spec);
+				       VM_READ | VM_EXEC | VM_MAYREAD |
+				       VM_MAYWRITE | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_SIGPAGE]);
+	if (IS_ERR(ret))
+		goto out;
 
-	up_write(&mm->mmap_sem);
+	mm->context.vdso = (void *)addr;
 
+out:
 	return PTR_ERR_OR_ZERO(ret);
 }
+
+int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
+	ret = aarch32_kuser_helpers_setup(mm);
+	if (ret)
+		goto out;
+
+	ret = aarch32_sigreturn_setup(mm);
+
+out:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
 #endif /* CONFIG_COMPAT */
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
@@ -146,8 +214,6 @@ static int __init vdso_init(void)
 	}
 
 	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-	pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
-		vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
 
 	/* Allocate the vDSO pagelist, plus a page for the data. */
 	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
@@ -232,6 +298,9 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
+	/* Read without the seqlock held by clock_getres() */
+	WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution);
+
 	if (!use_syscall) {
 		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
 		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index b215c712d897..744b9dbaba03 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -12,17 +12,12 @@ obj-vdso := gettimeofday.o note.o sigreturn.o
 targets := $(obj-vdso) vdso.so vdso.so.dbg
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
-ccflags-y := -shared -fno-common -fno-builtin
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
-		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 \
+		$(call ld-option, --hash-style=sysv) -n -T
 
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
-# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
-# down to collect2, resulting in silent corruption of the vDSO image.
-ccflags-y += -Wl,-shared
-
 obj-y += vdso.o
 extra-y += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
@@ -31,8 +26,8 @@ CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 $(obj)/vdso.o : $(obj)/vdso.so
 
 # Link rule for the .so file, .lds has to be first
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
-	$(call if_changed,vdsold)
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,ld)
 
 # Strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -42,9 +37,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 # Generate VDSO offsets using helper script
 gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
 quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
-	$(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
-endef
+      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
 
 include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
@@ -54,8 +47,6 @@ $(obj-vdso): %.o: %.S FORCE
 	$(call if_changed_dep,vdsoas)
 
 # Actual build commands
-quiet_cmd_vdsold = VDSOL   $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA   $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index c39872a7b03c..856fee6d3512 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -73,6 +73,13 @@ x_tmp		.req	x8
 	movn	x_tmp, #0xff00, lsl #48
 	and	\res, x_tmp, \res
 	mul	\res, \res, \mult
+	/*
+	 * Fake address dependency from the value computed from the counter
+	 * register to subsequent data page accesses so that the sequence
+	 * locking also orders the read of the counter.
+	 */
+	and	x_tmp, \res, xzr
+	add	vdso_data, vdso_data, x_tmp
 	.endm
 
 	/*
@@ -147,12 +154,12 @@ ENTRY(__kernel_gettimeofday)
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=1b
 
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=1b
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -211,13 +218,13 @@ realtime:
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=realtime
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=realtime
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 	clock_gettime_return, shift=1
@@ -231,7 +238,6 @@ monotonic:
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
 	ldp	x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic
 
 	/* All computations are done with left-shifted nsecs. */
 	lsl	x4, x4, x12
@@ -239,6 +245,7 @@ monotonic:
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -253,13 +260,13 @@ monotonic_raw:
 	/* w11 = cs_raw_mult, w12 = cs_shift */
 	ldp	w12, w11, [vdso_data, #VDSO_CS_SHIFT]
 	ldp	x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-	seqcnt_check fail=monotonic_raw
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic_raw
 	get_ts_clock_raw res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, nsec_to_sec=x9
 
@@ -301,13 +308,14 @@ ENTRY(__kernel_clock_getres)
 	ccmp	w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
 	b.ne	1f
 
-	ldr	x2, 5f
+	adr	vdso_data, _vdso_data
+	ldr	w2, [vdso_data, #CLOCK_REALTIME_RES]
 	b	2f
 1:
 	cmp	w0, #CLOCK_REALTIME_COARSE
 	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
 	b.ne	4f
-	ldr	x2, 6f
+	ldr	x2, 5f
 2:
 	cbz	x1, 3f
 	stp	xzr, x2, [x1]
@@ -321,8 +329,6 @@ ENTRY(__kernel_clock_getres)
 	svc	#0
 	ret
 5:
-	.quad	CLOCK_REALTIME_RES
-6:
 	.quad	CLOCK_COARSE_RES
 	.cfi_endproc
 ENDPROC(__kernel_clock_getres)
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 5540a1638baf..33c2a4abda04 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -24,7 +24,7 @@ CFLAGS_atomic_ll_sc.o	:= -ffixed-x1 -ffixed-x2        		\
 		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\
 		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
 		   -fcall-saved-x18 -fomit-frame-pointer
-CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+CFLAGS_REMOVE_atomic_ll_sc.o := $(CC_FLAGS_FTRACE)
 GCOV_PROFILE_atomic_ll_sc.o	:= n
 KASAN_SANITIZE_atomic_ll_sc.o	:= n
 KCOV_INSTRUMENT_atomic_ll_sc.o	:= n
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 1a7e92ab69eb..0cb0e09995e1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -148,7 +148,7 @@ static inline bool is_ttbr1_addr(unsigned long addr)
 /*
  * Dump out the page tables associated with 'addr' in the currently active mm.
  */
-void show_pte(unsigned long addr)
+static void show_pte(unsigned long addr)
 {
 	struct mm_struct *mm;
 	pgd_t *pgdp;
@@ -810,13 +810,12 @@ void __init hook_debug_fault_code(int nr,
 	debug_fault_info[nr].name	= name;
 }
 
-asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
-					      unsigned int esr,
-					      struct pt_regs *regs)
+asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
+					       unsigned int esr,
+					       struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_debug_fault_info(esr);
 	unsigned long pc = instruction_pointer(regs);
-	int rv;
 
 	/*
 	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
@@ -828,17 +827,12 @@ asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
 	if (user_mode(regs) && !is_ttbr0_addr(pc))
 		arm64_apply_bp_hardening();
 
-	if (!inf->fn(addr_if_watchpoint, esr, regs)) {
-		rv = 1;
-	} else {
+	if (inf->fn(addr_if_watchpoint, esr, regs)) {
 		arm64_notify_die(inf->name, regs,
 				 inf->sig, inf->code, (void __user *)pc, esr);
-		rv = 0;
 	}
 
 	if (interrupts_enabled(regs))
 		trace_hardirqs_on();
-
-	return rv;
 }
 NOKPROBE_SYMBOL(do_debug_exception);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7cae155e81a5..40e2d7e5efcb 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -377,7 +377,7 @@ void __init arm64_memblock_init(void)
 			 base + size > memblock_start_of_DRAM() +
 				       linear_region_size,
 			"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
-			initrd_start = 0;
+			phys_initrd_size = 0;
 		} else {
 			memblock_remove(base, size); /* clear MEMBLOCK_ flags */
 			memblock_add(base, size);
@@ -440,6 +440,7 @@ void __init bootmem_init(void)
 	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
 
 	max_pfn = max_low_pfn = max;
+	min_low_pfn = min;
 
 	arm64_numa_init();
 	/*
@@ -535,7 +536,7 @@ void __init mem_init(void)
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
 
-	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
+	set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 	free_unused_memmap();
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e97f018ff740..ef82312860ac 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -97,7 +97,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 }
 EXPORT_SYMBOL(phys_mem_access_prot);
 
-static phys_addr_t __init early_pgtable_alloc(void)
+static phys_addr_t __init early_pgtable_alloc(int shift)
 {
 	phys_addr_t phys;
 	void *ptr;
@@ -174,7 +174,7 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(void),
+				phys_addr_t (*pgtable_alloc)(int),
 				int flags)
 {
 	unsigned long next;
@@ -184,7 +184,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 	if (pmd_none(pmd)) {
 		phys_addr_t pte_phys;
 		BUG_ON(!pgtable_alloc);
-		pte_phys = pgtable_alloc();
+		pte_phys = pgtable_alloc(PAGE_SHIFT);
 		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
 		pmd = READ_ONCE(*pmdp);
 	}
@@ -208,7 +208,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
 static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
-		     phys_addr_t (*pgtable_alloc)(void), int flags)
+		     phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
 	pmd_t *pmdp;
@@ -246,7 +246,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(void), int flags)
+				phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
@@ -258,7 +258,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	if (pud_none(pud)) {
 		phys_addr_t pmd_phys;
 		BUG_ON(!pgtable_alloc);
-		pmd_phys = pgtable_alloc();
+		pmd_phys = pgtable_alloc(PMD_SHIFT);
 		__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
 		pud = READ_ONCE(*pudp);
 	}
@@ -294,7 +294,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
 
 static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 			   phys_addr_t phys, pgprot_t prot,
-			   phys_addr_t (*pgtable_alloc)(void),
+			   phys_addr_t (*pgtable_alloc)(int),
 			   int flags)
 {
 	unsigned long next;
@@ -304,7 +304,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	if (pgd_none(pgd)) {
 		phys_addr_t pud_phys;
 		BUG_ON(!pgtable_alloc);
-		pud_phys = pgtable_alloc();
+		pud_phys = pgtable_alloc(PUD_SHIFT);
 		__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
 		pgd = READ_ONCE(*pgdp);
 	}
@@ -345,7 +345,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 unsigned long virt, phys_addr_t size,
 				 pgprot_t prot,
-				 phys_addr_t (*pgtable_alloc)(void),
+				 phys_addr_t (*pgtable_alloc)(int),
 				 int flags)
 {
 	unsigned long addr, length, end, next;
@@ -371,17 +371,36 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 	} while (pgdp++, addr = next, addr != end);
 }
 
-static phys_addr_t pgd_pgtable_alloc(void)
+static phys_addr_t __pgd_pgtable_alloc(int shift)
 {
 	void *ptr = (void *)__get_free_page(PGALLOC_GFP);
-	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
-		BUG();
+	BUG_ON(!ptr);
 
 	/* Ensure the zeroed page is visible to the page table walker */
 	dsb(ishst);
 	return __pa(ptr);
 }
 
+static phys_addr_t pgd_pgtable_alloc(int shift)
+{
+	phys_addr_t pa = __pgd_pgtable_alloc(shift);
+
+	/*
+	 * Call proper page table ctor in case later we need to
+	 * call core mm functions like apply_to_page_range() on
+	 * this pre-allocated page table.
+	 *
+	 * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
+	 * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+	 */
+	if (shift == PAGE_SHIFT)
+		BUG_ON(!pgtable_page_ctor(phys_to_page(pa)));
+	else if (shift == PMD_SHIFT)
+		BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa)));
+
+	return pa;
+}
+
 /*
  * This function can only be used to modify existing table entries,
  * without allocating new levels of table. Note that this permits the
@@ -583,7 +602,7 @@ static int __init map_entry_trampoline(void)
 	/* Map only the text into the trampoline page table */
 	memset(tramp_pg_dir, 0, PGD_SIZE);
 	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
-			     prot, pgd_pgtable_alloc, 0);
+			     prot, __pgd_pgtable_alloc, 0);
 
 	/* Map both the text and data into the kernel page table */
 	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
@@ -1055,7 +1074,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
-			     size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
+			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   altmap, want_memblock);
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 06a6f264f2dd..5202f63c29c9 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -124,7 +124,7 @@ static void __init setup_node_to_cpumask_map(void)
 }
 
 /*
- *  Set the cpu to node and mem mapping
+ * Set the cpu to node and mem mapping
  */
 void numa_store_cpu_info(unsigned int cpu)
 {
@@ -200,7 +200,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 
 /**
- * numa_add_memblk - Set node id to memblk
+ * numa_add_memblk() - Set node id to memblk
  * @nid: NUMA node ID of the new memblk
  * @start: Start address of the new memblk
  * @end:  End address of the new memblk
@@ -223,7 +223,7 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	return ret;
 }
 
-/**
+/*
  * Initialize NODE_DATA for a node on the local memory
  */
 static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
@@ -257,7 +257,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
 }
 
-/**
+/*
  * numa_free_distance
  *
  * The current table is freed.
@@ -277,10 +277,8 @@ void __init numa_free_distance(void)
 	numa_distance = NULL;
 }
 
-/**
- *
+/*
  * Create a new NUMA distance table.
- *
  */
 static int __init numa_alloc_distance(void)
 {
@@ -311,7 +309,7 @@ static int __init numa_alloc_distance(void)
 }
 
 /**
- * numa_set_distance - Set inter node NUMA distance from node to node.
+ * numa_set_distance() - Set inter node NUMA distance from node to node.
  * @from: the 'from' node to set distance
  * @to: the 'to'  node to set distance
  * @distance: NUMA distance
@@ -321,7 +319,6 @@ static int __init numa_alloc_distance(void)
  *
  * If @from or @to is higher than the highest known node or lower than zero
  * or @distance doesn't make sense, the call is ignored.
- *
  */
 void __init numa_set_distance(int from, int to, int distance)
 {
@@ -347,7 +344,7 @@ void __init numa_set_distance(int from, int to, int distance)
 	numa_distance[from * numa_distance_cnt + to] = distance;
 }
 
-/**
+/*
  * Return NUMA distance @from to @to
  */
 int __node_distance(int from, int to)
@@ -422,13 +419,15 @@ out_free_distance:
 }
 
 /**
- * dummy_numa_init - Fallback dummy NUMA init
+ * dummy_numa_init() - Fallback dummy NUMA init
  *
  * Used if there's no underlying NUMA architecture, NUMA initialization
  * fails, or NUMA is disabled on the command line.
  *
  * Must online at least one node (node 0) and add memory blocks that cover all
  * allowed memory. It is unlikely that this function fails.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 static int __init dummy_numa_init(void)
 {
@@ -454,9 +453,9 @@ static int __init dummy_numa_init(void)
 }
 
 /**
- * arm64_numa_init - Initialize NUMA
+ * arm64_numa_init() - Initialize NUMA
  *
- * Try each configured NUMA initialization method until one succeeds.  The
+ * Try each configured NUMA initialization method until one succeeds. The
  * last fallback is dummy single node config encomapssing whole memory.
  */
 void __init arm64_numa_init(void)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index aa0817c9c4c3..fdd626d34274 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -65,24 +65,25 @@ ENTRY(cpu_do_suspend)
 	mrs	x2, tpidr_el0
 	mrs	x3, tpidrro_el0
 	mrs	x4, contextidr_el1
-	mrs	x5, cpacr_el1
-	mrs	x6, tcr_el1
-	mrs	x7, vbar_el1
-	mrs	x8, mdscr_el1
-	mrs	x9, oslsr_el1
-	mrs	x10, sctlr_el1
+	mrs	x5, osdlr_el1
+	mrs	x6, cpacr_el1
+	mrs	x7, tcr_el1
+	mrs	x8, vbar_el1
+	mrs	x9, mdscr_el1
+	mrs	x10, oslsr_el1
+	mrs	x11, sctlr_el1
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x11, tpidr_el1
+	mrs	x12, tpidr_el1
 alternative_else
-	mrs	x11, tpidr_el2
+	mrs	x12, tpidr_el2
 alternative_endif
-	mrs	x12, sp_el0
+	mrs	x13, sp_el0
 	stp	x2, x3, [x0]
-	stp	x4, xzr, [x0, #16]
-	stp	x5, x6, [x0, #32]
-	stp	x7, x8, [x0, #48]
-	stp	x9, x10, [x0, #64]
-	stp	x11, x12, [x0, #80]
+	stp	x4, x5, [x0, #16]
+	stp	x6, x7, [x0, #32]
+	stp	x8, x9, [x0, #48]
+	stp	x10, x11, [x0, #64]
+	stp	x12, x13, [x0, #80]
 	ret
 ENDPROC(cpu_do_suspend)
 
@@ -105,8 +106,8 @@ ENTRY(cpu_do_resume)
 	msr	cpacr_el1, x6
 
 	/* Don't change t0sz here, mask those bits when restoring */
-	mrs	x5, tcr_el1
-	bfi	x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+	mrs	x7, tcr_el1
+	bfi	x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
@@ -130,6 +131,7 @@ alternative_endif
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
 	 */
+	msr	osdlr_el1, x5
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index e5cd3c5f8399..eeb0471268a0 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -20,6 +20,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select ARCH_NO_COHERENT_DMA_MMAP
+	select MMU_GATHER_NO_RANGE if MMU
 
 config MMU
 	def_bool n
@@ -27,9 +28,6 @@ config MMU
 config FPU
 	def_bool n
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 249c9f6f26dc..6b168d32fbff 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -23,6 +23,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += mmu.h
 generic-y += mmu_context.h
 generic-y += pci.h
diff --git a/arch/c6x/include/asm/tlb.h b/arch/c6x/include/asm/tlb.h
index 34525dea1356..240ba0febb57 100644
--- a/arch/c6x/include/asm/tlb.h
+++ b/arch/c6x/include/asm/tlb.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_C6X_TLB_H
 #define _ASM_C6X_TLB_H
 
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _ASM_C6X_TLB_H */
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 725a115759c9..6555d1781132 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -92,9 +92,6 @@ config GENERIC_HWEIGHT
 config MMU
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config STACKTRACE_SUPPORT
 	def_bool y
 
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index 2a0abe8f2a35..95f4e550db8a 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -28,6 +28,7 @@ generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += pci.h
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index c071da34e081..61c01db6c292 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -27,9 +27,6 @@ config H8300
 config CPU_BIG_ENDIAN
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index e3dead402e5f..123d8f54be4a 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -29,6 +29,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += mmu.h
 generic-y += mmu_context.h
 generic-y += module.h
diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h
index 98f344279904..d8201ca31206 100644
--- a/arch/h8300/include/asm/tlb.h
+++ b/arch/h8300/include/asm/tlb.h
@@ -2,8 +2,6 @@
 #ifndef __H8300_TLB_H__
 #define __H8300_TLB_H__
 
-#define tlb_flush(tlb)	do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index ac441680dcc0..3e54a53208d5 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -65,12 +65,6 @@ config GENERIC_CSUM
 config GENERIC_IRQ_PROBE
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool n
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index d046e8ccdf78..6234a303d2a3 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -24,10 +24,10 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index e17262ad125e..3d0ae09c2b8e 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -184,8 +184,6 @@ static inline void writel(u32 data, volatile void __iomem *addr)
 #define writew_relaxed __raw_writew
 #define writel_relaxed __raw_writel
 
-#define mmiowb()
-
 /*
  * Need an mtype somewhere in here, for cache type deals?
  * This is probably too long for an inline.
diff --git a/arch/hexagon/include/asm/tlb.h b/arch/hexagon/include/asm/tlb.h
index 2f00772cc08a..f71c4ba83614 100644
--- a/arch/hexagon/include/asm/tlb.h
+++ b/arch/hexagon/include/asm/tlb.h
@@ -22,18 +22,6 @@
 #include <linux/pagemap.h>
 #include <asm/tlbflush.h>
 
-/*
- * We don't need any special per-pte or per-vma handling...
- */
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up
- */
-#define tlb_flush(tlb)		flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 8d7396bd1790..73a26f04644e 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -83,10 +83,6 @@ config STACKTRACE_SUPPORT
 config GENERIC_LOCKBREAK
 	def_bool n
 
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config HUGETLB_PAGE_SIZE_VARIABLE
 	bool
 	depends on HUGETLB_PAGE
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 1e6fef69bb01..a511d62d447a 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -113,20 +113,6 @@ extern int valid_mmap_phys_addr_range (unsigned long pfn, size_t count);
  */
 #define __ia64_mf_a()	ia64_mfa()
 
-/**
- * ___ia64_mmiowb - I/O write barrier
- *
- * Ensure ordering of I/O space writes.  This will make sure that writes
- * following the barrier will arrive after all previous writes.  For most
- * ia64 platforms, this is a simple 'mf.a' instruction.
- *
- * See Documentation/driver-api/device-io.rst for more information.
- */
-static inline void ___ia64_mmiowb(void)
-{
-	ia64_mfa();
-}
-
 static inline void*
 __ia64_mk_io_addr (unsigned long port)
 {
@@ -161,7 +147,6 @@ __ia64_mk_io_addr (unsigned long port)
 #define __ia64_writew	___ia64_writew
 #define __ia64_writel	___ia64_writel
 #define __ia64_writeq	___ia64_writeq
-#define __ia64_mmiowb	___ia64_mmiowb
 
 /*
  * For the in/out routines, we need to do "mf.a" _after_ doing the I/O access to ensure
@@ -296,7 +281,6 @@ __outsl (unsigned long port, const void *src, unsigned long count)
 #define __outb		platform_outb
 #define __outw		platform_outw
 #define __outl		platform_outl
-#define __mmiowb	platform_mmiowb
 
 #define inb(p)		__inb(p)
 #define inw(p)		__inw(p)
@@ -310,7 +294,6 @@ __outsl (unsigned long port, const void *src, unsigned long count)
 #define outsb(p,s,c)	__outsb(p,s,c)
 #define outsw(p,s,c)	__outsw(p,s,c)
 #define outsl(p,s,c)	__outsl(p,s,c)
-#define mmiowb()	__mmiowb()
 
 /*
  * The address passed to these functions are ioremap()ped already.
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 5133739966bc..beae261fbcb4 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -30,7 +30,6 @@ typedef void ia64_mv_irq_init_t (void);
 typedef void ia64_mv_send_ipi_t (int, int, int, int);
 typedef void ia64_mv_timer_interrupt_t (int, void *);
 typedef void ia64_mv_global_tlb_purge_t (struct mm_struct *, unsigned long, unsigned long, unsigned long);
-typedef void ia64_mv_tlb_migrate_finish_t (struct mm_struct *);
 typedef u8 ia64_mv_irq_to_vector (int);
 typedef unsigned int ia64_mv_local_vector_to_irq (u8);
 typedef char *ia64_mv_pci_get_legacy_mem_t (struct pci_bus *);
@@ -80,11 +79,6 @@ machvec_noop (void)
 }
 
 static inline void
-machvec_noop_mm (struct mm_struct *mm)
-{
-}
-
-static inline void
 machvec_noop_task (struct task_struct *task)
 {
 }
@@ -96,7 +90,6 @@ machvec_noop_bus (struct pci_bus *bus)
 
 extern void machvec_setup (char **);
 extern void machvec_timer_interrupt (int, void *);
-extern void machvec_tlb_migrate_finish (struct mm_struct *);
 
 # if defined (CONFIG_IA64_HP_SIM)
 #  include <asm/machvec_hpsim.h>
@@ -124,7 +117,6 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 #  define platform_send_ipi	ia64_mv.send_ipi
 #  define platform_timer_interrupt	ia64_mv.timer_interrupt
 #  define platform_global_tlb_purge	ia64_mv.global_tlb_purge
-#  define platform_tlb_migrate_finish	ia64_mv.tlb_migrate_finish
 #  define platform_dma_init		ia64_mv.dma_init
 #  define platform_dma_get_ops		ia64_mv.dma_get_ops
 #  define platform_irq_to_vector	ia64_mv.irq_to_vector
@@ -167,7 +159,6 @@ struct ia64_machine_vector {
 	ia64_mv_send_ipi_t *send_ipi;
 	ia64_mv_timer_interrupt_t *timer_interrupt;
 	ia64_mv_global_tlb_purge_t *global_tlb_purge;
-	ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish;
 	ia64_mv_dma_init *dma_init;
 	ia64_mv_dma_get_ops *dma_get_ops;
 	ia64_mv_irq_to_vector *irq_to_vector;
@@ -206,7 +197,6 @@ struct ia64_machine_vector {
 	platform_send_ipi,			\
 	platform_timer_interrupt,		\
 	platform_global_tlb_purge,		\
-	platform_tlb_migrate_finish,		\
 	platform_dma_init,			\
 	platform_dma_get_ops,			\
 	platform_irq_to_vector,			\
@@ -270,9 +260,6 @@ extern const struct dma_map_ops *dma_get_ops(struct device *);
 #ifndef platform_global_tlb_purge
 # define platform_global_tlb_purge	ia64_global_tlb_purge /* default to architected version */
 #endif
-#ifndef platform_tlb_migrate_finish
-# define platform_tlb_migrate_finish	machvec_noop_mm
-#endif
 #ifndef platform_kernel_launch_event
 # define platform_kernel_launch_event	machvec_noop
 #endif
diff --git a/arch/ia64/include/asm/machvec_sn2.h b/arch/ia64/include/asm/machvec_sn2.h
index b5153d300289..a243e4fb4877 100644
--- a/arch/ia64/include/asm/machvec_sn2.h
+++ b/arch/ia64/include/asm/machvec_sn2.h
@@ -34,7 +34,6 @@ extern ia64_mv_irq_init_t sn_irq_init;
 extern ia64_mv_send_ipi_t sn2_send_IPI;
 extern ia64_mv_timer_interrupt_t sn_timer_interrupt;
 extern ia64_mv_global_tlb_purge_t sn2_global_tlb_purge;
-extern ia64_mv_tlb_migrate_finish_t	sn_tlb_migrate_finish;
 extern ia64_mv_irq_to_vector sn_irq_to_vector;
 extern ia64_mv_local_vector_to_irq sn_local_vector_to_irq;
 extern ia64_mv_pci_get_legacy_mem_t sn_pci_get_legacy_mem;
@@ -77,7 +76,6 @@ extern ia64_mv_pci_fixup_bus_t		sn_pci_fixup_bus;
 #define platform_send_ipi		sn2_send_IPI
 #define platform_timer_interrupt	sn_timer_interrupt
 #define platform_global_tlb_purge       sn2_global_tlb_purge
-#define platform_tlb_migrate_finish	sn_tlb_migrate_finish
 #define platform_pci_fixup		sn_pci_fixup
 #define platform_inb			__sn_inb
 #define platform_inw			__sn_inw
diff --git a/arch/ia64/include/asm/mmiowb.h b/arch/ia64/include/asm/mmiowb.h
new file mode 100644
index 000000000000..297b85ac84a0
--- /dev/null
+++ b/arch/ia64/include/asm/mmiowb.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_IA64_MMIOWB_H
+#define _ASM_IA64_MMIOWB_H
+
+#include <asm/machvec.h>
+
+/**
+ * ___ia64_mmiowb - I/O write barrier
+ *
+ * Ensure ordering of I/O space writes.  This will make sure that writes
+ * following the barrier will arrive after all previous writes.  For most
+ * ia64 platforms, this is a simple 'mf.a' instruction.
+ */
+static inline void ___ia64_mmiowb(void)
+{
+	ia64_mfa();
+}
+
+#define __ia64_mmiowb	___ia64_mmiowb
+#define mmiowb()	platform_mmiowb()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_IA64_MMIOWB_H */
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
deleted file mode 100644
index 917910607e0e..000000000000
--- a/arch/ia64/include/asm/rwsem.h
+++ /dev/null
@@ -1,172 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * R/W semaphores for ia64
- *
- * Copyright (C) 2003 Ken Chen <kenneth.w.chen@intel.com>
- * Copyright (C) 2003 Asit Mallick <asit.k.mallick@intel.com>
- * Copyright (C) 2005 Christoph Lameter <cl@linux.com>
- *
- * Based on asm-i386/rwsem.h and other architecture implementation.
- *
- * The MSW of the count is the negated number of active writers and
- * waiting lockers, and the LSW is the total number of active locks.
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffffffff00000001 for
- * the case of an uncontended lock. Readers increment by 1 and see a positive
- * value when uncontended, negative if there are writers (and maybe) readers
- * waiting (in which case it goes to sleep).
- */
-
-#ifndef _ASM_IA64_RWSEM_H
-#define _ASM_IA64_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#include <asm/intrinsics.h>
-
-#define RWSEM_UNLOCKED_VALUE		__IA64_UL_CONST(0x0000000000000000)
-#define RWSEM_ACTIVE_BIAS		(1L)
-#define RWSEM_ACTIVE_MASK		(0xffffffffL)
-#define RWSEM_WAITING_BIAS		(-0x100000000L)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline int
-___down_read (struct rw_semaphore *sem)
-{
-	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
-
-	return (result < 0);
-}
-
-static inline void
-__down_read (struct rw_semaphore *sem)
-{
-	if (___down_read(sem))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int
-__down_read_killable (struct rw_semaphore *sem)
-{
-	if (___down_read(sem))
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline long
-___down_write (struct rw_semaphore *sem)
-{
-	long old, new;
-
-	do {
-		old = atomic_long_read(&sem->count);
-		new = old + RWSEM_ACTIVE_WRITE_BIAS;
-	} while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old);
-
-	return old;
-}
-
-static inline void
-__down_write (struct rw_semaphore *sem)
-{
-	if (___down_write(sem))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int
-__down_write_killable (struct rw_semaphore *sem)
-{
-	if (___down_write(sem)) {
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	}
-
-	return 0;
-}
-
-/*
- * unlock after reading
- */
-static inline void
-__up_read (struct rw_semaphore *sem)
-{
-	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1);
-
-	if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0)
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void
-__up_write (struct rw_semaphore *sem)
-{
-	long old, new;
-
-	do {
-		old = atomic_long_read(&sem->count);
-		new = old - RWSEM_ACTIVE_WRITE_BIAS;
-	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
-
-	if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0)
-		rwsem_wake(sem);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int
-__down_read_trylock (struct rw_semaphore *sem)
-{
-	long tmp;
-	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
-		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) {
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int
-__down_write_trylock (struct rw_semaphore *sem)
-{
-	long tmp = atomic_long_cmpxchg_acquire(&sem->count,
-			RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS);
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void
-__downgrade_write (struct rw_semaphore *sem)
-{
-	long old, new;
-
-	do {
-		old = atomic_long_read(&sem->count);
-		new = old - RWSEM_WAITING_BIAS;
-	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
-
-	if (old < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-#endif /* _ASM_IA64_RWSEM_H */
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index afd0b3121b4c..5f620e66384e 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -73,6 +73,8 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned short	*p = (unsigned short *)&lock->lock + 1, tmp;
 
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
 	asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p));
 	WRITE_ONCE(*p, (tmp + 2) & ~1);
 }
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 516355a774bf..86ec034ba499 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -47,263 +47,6 @@
 #include <asm/tlbflush.h>
 #include <asm/machvec.h>
 
-/*
- * If we can't allocate a page to make a big batch of page pointers
- * to work on, then just handle a few from the on-stack structure.
- */
-#define	IA64_GATHER_BUNDLE	8
-
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		nr;
-	unsigned int		max;
-	unsigned char		fullmm;		/* non-zero means full mm flush */
-	unsigned char		need_flush;	/* really unmapped some PTEs? */
-	unsigned long		start, end;
-	unsigned long		start_addr;
-	unsigned long		end_addr;
-	struct page		**pages;
-	struct page		*local[IA64_GATHER_BUNDLE];
-};
-
-struct ia64_tr_entry {
-	u64 ifa;
-	u64 itir;
-	u64 pte;
-	u64 rr;
-}; /*Record for tr entry!*/
-
-extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
-extern void ia64_ptr_entry(u64 target_mask, int slot);
-
-extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
-
-/*
- region register macros
-*/
-#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
-#define RR_VE(val)	(((val) & 0x0000000000000001) << 0)
-#define RR_VE_MASK	0x0000000000000001L
-#define RR_VE_SHIFT	0
-#define RR_TO_PS(val)	(((val) >> 2) & 0x000000000000003f)
-#define RR_PS(val)	(((val) & 0x000000000000003f) << 2)
-#define RR_PS_MASK	0x00000000000000fcL
-#define RR_PS_SHIFT	2
-#define RR_RID_MASK	0x00000000ffffff00L
-#define RR_TO_RID(val) 	((val >> 8) & 0xffffff)
-
-static inline void
-ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	tlb->need_flush = 0;
-
-	if (tlb->fullmm) {
-		/*
-		 * Tearing down the entire address space.  This happens both as a result
-		 * of exit() and execve().  The latter case necessitates the call to
-		 * flush_tlb_mm() here.
-		 */
-		flush_tlb_mm(tlb->mm);
-	} else if (unlikely (end - start >= 1024*1024*1024*1024UL
-			     || REGION_NUMBER(start) != REGION_NUMBER(end - 1)))
-	{
-		/*
-		 * If we flush more than a tera-byte or across regions, we're probably
-		 * better off just flushing the entire TLB(s).  This should be very rare
-		 * and is not worth optimizing for.
-		 */
-		flush_tlb_all();
-	} else {
-		/*
-		 * flush_tlb_range() takes a vma instead of a mm pointer because
-		 * some architectures want the vm_flags for ITLB/DTLB flush.
-		 */
-		struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
-
-		/* flush the address range from the tlb: */
-		flush_tlb_range(&vma, start, end);
-		/* now flush the virt. page-table area mapping the address range: */
-		flush_tlb_range(&vma, ia64_thash(start), ia64_thash(end));
-	}
-
-}
-
-static inline void
-ia64_tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	unsigned long i;
-	unsigned int nr;
-
-	/* lastly, release the freed pages */
-	nr = tlb->nr;
-
-	tlb->nr = 0;
-	tlb->start_addr = ~0UL;
-	for (i = 0; i < nr; ++i)
-		free_page_and_swap_cache(tlb->pages[i]);
-}
-
-/*
- * Flush the TLB for address range START to END and, if not in fast mode, release the
- * freed pages that where gathered up to this point.
- */
-static inline void
-ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	if (!tlb->need_flush)
-		return;
-	ia64_tlb_flush_mmu_tlbonly(tlb, start, end);
-	ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(void *);
-	}
-}
-
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->start_addr = ~0UL;
-}
-
-/*
- * Called at the end of the shootdown operation to free up any resources that were
- * collected.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force)
-		tlb->need_flush = 1;
-	/*
-	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
-	 * tlb->end_addr.
-	 */
-	ia64_tlb_flush_mmu(tlb, start, end);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Logically, this routine frees PAGE.  On MP machines, the actual freeing of the page
- * must be delayed until after the TLB has been flushed (see comments at the beginning of
- * this file).
- */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-
-	if (!tlb->nr && tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu_tlbonly(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-/*
- * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
- * PTE, not just those pointing to (normal) physical memory.
- */
-static inline void
-__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start_addr == ~0UL)
-		tlb->start_addr = address;
-	tlb->end_addr = address + PAGE_SIZE;
-}
-
-#define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
-
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-
-#define tlb_remove_tlb_entry(tlb, ptep, addr)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__tlb_remove_tlb_entry(tlb, ptep, addr);	\
-} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pte_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pmd_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pmd_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pud_free_tlb(tlb, pudp, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pud_free_tlb(tlb, pudp, address);		\
-} while (0)
+#include <asm-generic/tlb.h>
 
 #endif /* _ASM_IA64_TLB_H */
diff --git a/arch/ia64/include/asm/tlbflush.h b/arch/ia64/include/asm/tlbflush.h
index 25e280810f6c..ceac10c4d6e2 100644
--- a/arch/ia64/include/asm/tlbflush.h
+++ b/arch/ia64/include/asm/tlbflush.h
@@ -14,6 +14,31 @@
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 
+struct ia64_tr_entry {
+	u64 ifa;
+	u64 itir;
+	u64 pte;
+	u64 rr;
+}; /*Record for tr entry!*/
+
+extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
+extern void ia64_ptr_entry(u64 target_mask, int slot);
+extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
+
+/*
+ region register macros
+*/
+#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
+#define RR_VE(val)     (((val) & 0x0000000000000001) << 0)
+#define RR_VE_MASK     0x0000000000000001L
+#define RR_VE_SHIFT    0
+#define RR_TO_PS(val)  (((val) >> 2) & 0x000000000000003f)
+#define RR_PS(val)     (((val) & 0x000000000000003f) << 2)
+#define RR_PS_MASK     0x00000000000000fcL
+#define RR_PS_SHIFT    2
+#define RR_RID_MASK    0x00000000ffffff00L
+#define RR_TO_RID(val)         ((val >> 8) & 0xffffff)
+
 /*
  * Now for some TLB flushing routines.  This is the kind of stuff that
  * can be very expensive, so try to avoid them whenever possible.
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 583a3746d70b..c9cfa760cd57 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -1058,9 +1058,7 @@ check_bugs (void)
 
 static int __init run_dmi_scan(void)
 {
-	dmi_scan_machine();
-	dmi_memdev_walk();
-	dmi_set_dump_stack_arch_desc();
+	dmi_setup();
 	return 0;
 }
 core_initcall(run_dmi_scan);
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index 5fc89aabdce1..5158bd28de05 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -305,8 +305,8 @@ local_flush_tlb_all (void)
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
 
-void
-flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
+static void
+__flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 		 unsigned long end)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -343,6 +343,25 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 	preempt_enable();
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
+
+void flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	if (unlikely(end - start >= 1024*1024*1024*1024UL
+			|| REGION_NUMBER(start) != REGION_NUMBER(end - 1))) {
+		/*
+		 * If we flush more than a tera-byte or across regions, we're
+		 * probably better off just flushing the entire TLB(s).  This
+		 * should be very rare and is not worth optimizing for.
+		 */
+		flush_tlb_all();
+	} else {
+		/* flush the address range from the tlb */
+		__flush_tlb_range(vma, start, end);
+		/* flush the virt. page-table area mapping the addr range */
+		__flush_tlb_range(vma, ia64_thash(start), ia64_thash(end));
+	}
+}
 EXPORT_SYMBOL(flush_tlb_range);
 
 void ia64_tlb_init(void)
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index b73b0ebf8214..b510f4f17fd4 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -120,13 +120,6 @@ void sn_migrate(struct task_struct *task)
 		cpu_relax();
 }
 
-void sn_tlb_migrate_finish(struct mm_struct *mm)
-{
-	/* flush_tlb_mm is inefficient if more than 1 users of mm */
-	if (mm == current->mm && mm && atomic_read(&mm->mm_users) == 1)
-		flush_tlb_mm(mm);
-}
-
 static void
 sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 {
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index b54206408f91..fe5cc2da6d10 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -20,7 +20,6 @@ config M68K
 	select GENERIC_STRNCPY_FROM_USER if MMU
 	select GENERIC_STRNLEN_USER if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
 	select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
@@ -28,17 +27,11 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select ARCH_DISCARD_MEMBLOCK
+	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	bool
 
diff --git a/arch/m68k/amiga/cia.c b/arch/m68k/amiga/cia.c
index 2081b8cd5591..b9aee983e6f4 100644
--- a/arch/m68k/amiga/cia.c
+++ b/arch/m68k/amiga/cia.c
@@ -88,10 +88,19 @@ static irqreturn_t cia_handler(int irq, void *dev_id)
 	struct ciabase *base = dev_id;
 	int mach_irq;
 	unsigned char ints;
+	unsigned long flags;
 
+	/* Interrupts get disabled while the timer irq flag is cleared and
+	 * the timer interrupt serviced.
+	 */
 	mach_irq = base->cia_irq;
+	local_irq_save(flags);
 	ints = cia_set_irq(base, CIA_ICR_ALL);
 	amiga_custom.intreq = base->int_mask;
+	if (ints & 1)
+		generic_handle_irq(mach_irq);
+	local_irq_restore(flags);
+	mach_irq++, ints >>= 1;
 	for (; ints; mach_irq++, ints >>= 1) {
 		if (ints & 1)
 			generic_handle_irq(mach_irq);
diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 65f63a457130..c32ab8041cf6 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -17,6 +17,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/rtc.h>
 #include <linux/init.h>
@@ -95,8 +96,6 @@ static char amiga_model_name[13] = "Amiga ";
 static void amiga_sched_init(irq_handler_t handler);
 static void amiga_get_model(char *model);
 static void amiga_get_hardware_list(struct seq_file *m);
-/* amiga specific timer functions */
-static u32 amiga_gettimeoffset(void);
 extern void amiga_mksound(unsigned int count, unsigned int ticks);
 static void amiga_reset(void);
 extern void amiga_init_sound(void);
@@ -386,7 +385,6 @@ void __init config_amiga(void)
 	mach_init_IRQ        = amiga_init_IRQ;
 	mach_get_model       = amiga_get_model;
 	mach_get_hardware_list = amiga_get_hardware_list;
-	arch_gettimeoffset   = amiga_gettimeoffset;
 
 	/*
 	 * default MAX_DMA=0xffffffff on all machines. If we don't do so, the SCSI
@@ -464,7 +462,29 @@ void __init config_amiga(void)
 		*(unsigned char *)ZTWO_VADDR(0xde0002) |= 0x80;
 }
 
+static u64 amiga_read_clk(struct clocksource *cs);
+
+static struct clocksource amiga_clk = {
+	.name   = "ciab",
+	.rating = 250,
+	.read   = amiga_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
 static unsigned short jiffy_ticks;
+static u32 clk_total, clk_offset;
+
+static irqreturn_t ciab_timer_handler(int irq, void *dev_id)
+{
+	irq_handler_t timer_routine = dev_id;
+
+	clk_total += jiffy_ticks;
+	clk_offset = 0;
+	timer_routine(0, NULL);
+
+	return IRQ_HANDLED;
+}
 
 static void __init amiga_sched_init(irq_handler_t timer_routine)
 {
@@ -484,19 +504,22 @@ static void __init amiga_sched_init(irq_handler_t timer_routine)
 	 * Please don't change this to use ciaa, as it interferes with the
 	 * SCSI code. We'll have to take a look at this later
 	 */
-	if (request_irq(IRQ_AMIGA_CIAB_TA, timer_routine, 0, "timer", NULL))
+	if (request_irq(IRQ_AMIGA_CIAB_TA, ciab_timer_handler, IRQF_TIMER,
+			"timer", timer_routine))
 		pr_err("Couldn't register timer interrupt\n");
 	/* start timer */
 	ciab.cra |= 0x11;
-}
 
-#define TICK_SIZE 10000
+	clocksource_register_hz(&amiga_clk, amiga_eclock);
+}
 
-/* This is always executed with interrupts disabled.  */
-static u32 amiga_gettimeoffset(void)
+static u64 amiga_read_clk(struct clocksource *cs)
 {
 	unsigned short hi, lo, hi2;
-	u32 ticks, offset = 0;
+	unsigned long flags;
+	u32 ticks;
+
+	local_irq_save(flags);
 
 	/* read CIA B timer A current value */
 	hi  = ciab.tahi;
@@ -513,12 +536,14 @@ static u32 amiga_gettimeoffset(void)
 	if (ticks > jiffy_ticks / 2)
 		/* check for pending interrupt */
 		if (cia_set_irq(&ciab_base, 0) & CIA_ICR_TA)
-			offset = 10000;
+			clk_offset = jiffy_ticks;
 
 	ticks = jiffy_ticks - ticks;
-	ticks = (10000 * ticks) / jiffy_ticks;
+	ticks += clk_offset + clk_total;
+
+	local_irq_restore(flags);
 
-	return (ticks + offset) * 1000;
+	return ticks;
 }
 
 static void amiga_reset(void)  __noreturn;
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index aef8d42e078d..7d168e6dfb01 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -29,7 +29,6 @@ u_long apollo_model;
 
 extern void dn_sched_init(irq_handler_t handler);
 extern void dn_init_IRQ(void);
-extern u32 dn_gettimeoffset(void);
 extern int dn_dummy_hwclk(int, struct rtc_time *);
 extern void dn_dummy_reset(void);
 #ifdef CONFIG_HEARTBEAT
@@ -152,7 +151,6 @@ void __init config_apollo(void)
 
 	mach_sched_init=dn_sched_init; /* */
 	mach_init_IRQ=dn_init_IRQ;
-	arch_gettimeoffset   = dn_gettimeoffset;
 	mach_max_dma_address = 0xffffffff;
 	mach_hwclk           = dn_dummy_hwclk; /* */
 	mach_reset	     = dn_dummy_reset;  /* */
@@ -205,11 +203,6 @@ void dn_sched_init(irq_handler_t timer_routine)
 		pr_err("Couldn't register timer interrupt\n");
 }
 
-u32 dn_gettimeoffset(void)
-{
-	return 0xdeadbeef;
-}
-
 int dn_dummy_hwclk(int op, struct rtc_time *t) {
 
 
diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
index 3d2b63bedf05..56f02ea2c248 100644
--- a/arch/m68k/atari/ataints.c
+++ b/arch/m68k/atari/ataints.c
@@ -142,7 +142,7 @@ struct mfptimerbase {
 	.name		= "MFP Timer D"
 };
 
-static irqreturn_t mfptimer_handler(int irq, void *dev_id)
+static irqreturn_t mfp_timer_d_handler(int irq, void *dev_id)
 {
 	struct mfptimerbase *base = dev_id;
 	int mach_irq;
@@ -344,7 +344,7 @@ void __init atari_init_IRQ(void)
 	st_mfp.tim_ct_cd = (st_mfp.tim_ct_cd & 0xf0) | 0x6;
 
 	/* request timer D dispatch handler */
-	if (request_irq(IRQ_MFP_TIMD, mfptimer_handler, IRQF_SHARED,
+	if (request_irq(IRQ_MFP_TIMD, mfp_timer_d_handler, IRQF_SHARED,
 			stmfp_base.name, &stmfp_base))
 		pr_err("Couldn't register %s interrupt\n", stmfp_base.name);
 
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 4fcc4b1df1c0..902255e7b5b2 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -78,7 +78,6 @@ static void atari_heartbeat(int on);
 
 /* atari specific timer functions (in time.c) */
 extern void atari_sched_init(irq_handler_t);
-extern u32 atari_gettimeoffset(void);
 extern int atari_mste_hwclk (int, struct rtc_time *);
 extern int atari_tt_hwclk (int, struct rtc_time *);
 
@@ -205,7 +204,6 @@ void __init config_atari(void)
 	mach_init_IRQ        = atari_init_IRQ;
 	mach_get_model	 = atari_get_model;
 	mach_get_hardware_list = atari_get_hardware_list;
-	arch_gettimeoffset   = atari_gettimeoffset;
 	mach_reset           = atari_reset;
 	mach_max_dma_address = 0xffffff;
 #if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c
index 9cca64286464..ce923a523695 100644
--- a/arch/m68k/atari/time.c
+++ b/arch/m68k/atari/time.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/rtc.h>
 #include <linux/bcd.h>
+#include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 
@@ -24,6 +25,35 @@
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL_GPL(rtc_lock);
 
+static u64 atari_read_clk(struct clocksource *cs);
+
+static struct clocksource atari_clk = {
+	.name   = "mfp",
+	.rating = 100,
+	.read   = atari_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total;
+static u8 last_timer_count;
+
+static irqreturn_t mfp_timer_c_handler(int irq, void *dev_id)
+{
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	do {
+		last_timer_count = st_mfp.tim_dt_c;
+	} while (last_timer_count == 1);
+	clk_total += INT_TICKS;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
+	return IRQ_HANDLED;
+}
+
 void __init
 atari_sched_init(irq_handler_t timer_routine)
 {
@@ -32,31 +62,33 @@ atari_sched_init(irq_handler_t timer_routine)
     /* start timer C, div = 1:100 */
     st_mfp.tim_ct_cd = (st_mfp.tim_ct_cd & 15) | 0x60;
     /* install interrupt service routine for MFP Timer C */
-    if (request_irq(IRQ_MFP_TIMC, timer_routine, 0, "timer", timer_routine))
+    if (request_irq(IRQ_MFP_TIMC, mfp_timer_c_handler, IRQF_TIMER, "timer",
+                    timer_routine))
 	pr_err("Couldn't register timer interrupt\n");
+
+    clocksource_register_hz(&atari_clk, INT_CLK);
 }
 
 /* ++andreas: gettimeoffset fixed to check for pending interrupt */
 
-#define TICK_SIZE 10000
-
-/* This is always executed with interrupts disabled.  */
-u32 atari_gettimeoffset(void)
+static u64 atari_read_clk(struct clocksource *cs)
 {
-  u32 ticks, offset = 0;
-
-  /* read MFP timer C current value */
-  ticks = st_mfp.tim_dt_c;
-  /* The probability of underflow is less than 2% */
-  if (ticks > INT_TICKS - INT_TICKS / 50)
-    /* Check for pending timer interrupt */
-    if (st_mfp.int_pn_b & (1 << 5))
-      offset = TICK_SIZE;
-
-  ticks = INT_TICKS - ticks;
-  ticks = ticks * 10000L / INT_TICKS;
-
-  return (ticks + offset) * 1000;
+	unsigned long flags;
+	u8 count;
+	u32 ticks;
+
+	local_irq_save(flags);
+	/* Ensure that the count is monotonically decreasing, even though
+	 * the result may briefly stop changing after counter wrap-around.
+	 */
+	count = min(st_mfp.tim_dt_c, last_timer_count);
+	last_timer_count = count;
+
+	ticks = INT_TICKS - count;
+	ticks += clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 143ee9fa3893..8ebaabc931cd 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
@@ -39,16 +40,10 @@
 
 static void bvme6000_get_model(char *model);
 extern void bvme6000_sched_init(irq_handler_t handler);
-extern u32 bvme6000_gettimeoffset(void);
 extern int bvme6000_hwclk (int, struct rtc_time *);
 extern void bvme6000_reset (void);
 void bvme6000_set_vectors (void);
 
-/* Save tick handler routine pointer, will point to xtime_update() in
- * kernel/timer/timekeeping.c, called via bvme6000_process_int() */
-
-static irq_handler_t tick_handler;
-
 
 int __init bvme6000_parse_bootinfo(const struct bi_record *bi)
 {
@@ -110,7 +105,6 @@ void __init config_bvme6000(void)
     mach_max_dma_address = 0xffffffff;
     mach_sched_init      = bvme6000_sched_init;
     mach_init_IRQ        = bvme6000_init_IRQ;
-    arch_gettimeoffset   = bvme6000_gettimeoffset;
     mach_hwclk           = bvme6000_hwclk;
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
@@ -154,15 +148,38 @@ irqreturn_t bvme6000_abort_int (int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static u64 bvme6000_read_clk(struct clocksource *cs);
+
+static struct clocksource bvme6000_clk = {
+	.name   = "rtc",
+	.rating = 250,
+	.read   = bvme6000_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total, clk_offset;
+
+#define RTC_TIMER_CLOCK_FREQ 8000000
+#define RTC_TIMER_CYCLES     (RTC_TIMER_CLOCK_FREQ / HZ)
+#define RTC_TIMER_COUNT      ((RTC_TIMER_CYCLES / 2) - 1)
 
 static irqreturn_t bvme6000_timer_int (int irq, void *dev_id)
 {
+    irq_handler_t timer_routine = dev_id;
+    unsigned long flags;
     volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
-    unsigned char msr = rtc->msr & 0xc0;
+    unsigned char msr;
 
+    local_irq_save(flags);
+    msr = rtc->msr & 0xc0;
     rtc->msr = msr | 0x20;		/* Ack the interrupt */
+    clk_total += RTC_TIMER_CYCLES;
+    clk_offset = 0;
+    timer_routine(0, NULL);
+    local_irq_restore(flags);
 
-    return tick_handler(irq, dev_id);
+    return IRQ_HANDLED;
 }
 
 /*
@@ -181,14 +198,13 @@ void bvme6000_sched_init (irq_handler_t timer_routine)
 
     rtc->msr = 0;	/* Ensure timer registers accessible */
 
-    tick_handler = timer_routine;
-    if (request_irq(BVME_IRQ_RTC, bvme6000_timer_int, 0,
-				"timer", bvme6000_timer_int))
+    if (request_irq(BVME_IRQ_RTC, bvme6000_timer_int, IRQF_TIMER, "timer",
+                    timer_routine))
 	panic ("Couldn't register timer int");
 
     rtc->t1cr_omr = 0x04;	/* Mode 2, ext clk */
-    rtc->t1msb = 39999 >> 8;
-    rtc->t1lsb = 39999 & 0xff;
+    rtc->t1msb = RTC_TIMER_COUNT >> 8;
+    rtc->t1lsb = RTC_TIMER_COUNT & 0xff;
     rtc->irr_icr1 &= 0xef;	/* Route timer 1 to INTR pin */
     rtc->msr = 0x40;		/* Access int.cntrl, etc */
     rtc->pfr_icr0 = 0x80;	/* Just timer 1 ints enabled */
@@ -200,14 +216,14 @@ void bvme6000_sched_init (irq_handler_t timer_routine)
 
     rtc->msr = msr;
 
+    clocksource_register_hz(&bvme6000_clk, RTC_TIMER_CLOCK_FREQ);
+
     if (request_irq(BVME_IRQ_ABORT, bvme6000_abort_int, 0,
 				"abort", bvme6000_abort_int))
 	panic ("Couldn't register abort int");
 }
 
 
-/* This is always executed with interrupts disabled.  */
-
 /*
  * NOTE:  Don't accept any readings within 5us of rollover, as
  * the T1INT bit may be a little slow getting set.  There is also
@@ -215,14 +231,18 @@ void bvme6000_sched_init (irq_handler_t timer_routine)
  * results...
  */
 
-u32 bvme6000_gettimeoffset(void)
+static u64 bvme6000_read_clk(struct clocksource *cs)
 {
+    unsigned long flags;
     volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
     volatile PitRegsPtr pit = (PitRegsPtr)BVME_PIT_BASE;
-    unsigned char msr = rtc->msr & 0xc0;
+    unsigned char msr, msb;
     unsigned char t1int, t1op;
     u32 v = 800000, ov;
 
+    local_irq_save(flags);
+
+    msr = rtc->msr & 0xc0;
     rtc->msr = 0;	/* Ensure timer registers accessible */
 
     do {
@@ -230,22 +250,25 @@ u32 bvme6000_gettimeoffset(void)
 	t1int = rtc->msr & 0x20;
 	t1op  = pit->pcdr & 0x04;
 	rtc->t1cr_omr |= 0x40;		/* Latch timer1 */
-	v = rtc->t1msb << 8;		/* Read timer1 */
-	v |= rtc->t1lsb;		/* Read timer1 */
+	msb = rtc->t1msb;		/* Read timer1 */
+	v = (msb << 8) | rtc->t1lsb;	/* Read timer1 */
     } while (t1int != (rtc->msr & 0x20) ||
 		t1op != (pit->pcdr & 0x04) ||
 			abs(ov-v) > 80 ||
-				v > 39960);
+				v > RTC_TIMER_COUNT - (RTC_TIMER_COUNT / 100));
 
-    v = 39999 - v;
+    v = RTC_TIMER_COUNT - v;
     if (!t1op)				/* If in second half cycle.. */
-	v += 40000;
-    v /= 8;				/* Convert ticks to microseconds */
-    if (t1int)
-	v += 10000;			/* Int pending, + 10ms */
+	v += RTC_TIMER_CYCLES / 2;
+    if (msb > 0 && t1int)
+	clk_offset = RTC_TIMER_CYCLES;
     rtc->msr = msr;
 
-    return v * 1000;
+    v += clk_offset + clk_total;
+
+    local_irq_restore(flags);
+
+    return v;
 }
 
 /*
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 525421ae277d..fea392cfcf1b 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -56,6 +56,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -210,9 +211,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -234,9 +232,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -313,7 +308,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -460,12 +454,12 @@ CONFIG_RTC_DRV_RP5C01=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -573,9 +567,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -640,6 +636,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -649,4 +646,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index db0e654a88d5..2474d267460e 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -52,6 +52,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -206,9 +207,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -230,9 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -309,7 +304,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -420,12 +414,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -533,9 +527,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -600,6 +596,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -609,4 +606,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 1451168eb789..0fc7d2992fe0 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -59,6 +59,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -213,9 +214,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -237,9 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -316,7 +311,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -442,12 +436,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -555,9 +549,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -622,6 +618,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -631,4 +628,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index b0d3609f5bb3..699df9fdf866 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -49,6 +49,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -203,9 +204,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -227,9 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -306,7 +301,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -413,12 +407,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -526,9 +520,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -593,6 +589,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -602,4 +599,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 4ed7c151347c..b50802255324 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -51,6 +51,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -205,9 +206,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -229,9 +227,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -308,7 +303,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -422,12 +416,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -535,9 +529,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -602,6 +598,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -611,4 +608,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 0dc544e1ce1f..04e7d70f6030 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -50,6 +50,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -204,9 +205,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -228,9 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -310,7 +305,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -444,12 +438,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -557,9 +551,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -624,6 +620,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -633,4 +630,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 5a7b7b0d6e72..5e1cc4c17852 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -70,6 +70,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -224,9 +225,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -248,9 +246,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -330,7 +325,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -526,12 +520,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -639,9 +633,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -706,6 +702,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -715,4 +712,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 71eb9be1803b..170ac8792c2d 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -48,6 +48,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -202,9 +203,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -226,9 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -305,7 +300,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -412,12 +406,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -525,9 +519,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -592,6 +588,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -601,4 +598,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ea2ebd4241c0..d865592a423e 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -49,6 +49,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -203,9 +204,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -227,9 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -306,7 +301,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -413,12 +407,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -526,9 +520,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -593,6 +589,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -602,4 +599,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index cef6dc47c725..034a9de90484 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -50,6 +50,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -204,9 +205,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -228,9 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -307,7 +302,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -431,12 +425,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -544,9 +538,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -611,6 +607,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -620,4 +617,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 69f2282dc4e9..49be0f9fcd8d 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -46,6 +46,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -200,9 +201,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -224,9 +222,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -303,7 +298,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -415,12 +409,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -528,9 +522,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -595,6 +591,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -604,3 +601,4 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index e91267e868b2..a71acf4a6004 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -46,6 +46,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -200,9 +201,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -224,9 +222,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -303,7 +298,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -414,12 +408,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -527,9 +521,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -594,6 +590,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -603,4 +600,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/hp300/config.c b/arch/m68k/hp300/config.c
index a19bcd23f80b..a161d44fd20b 100644
--- a/arch/m68k/hp300/config.c
+++ b/arch/m68k/hp300/config.c
@@ -254,7 +254,6 @@ void __init config_hp300(void)
 	mach_sched_init      = hp300_sched_init;
 	mach_init_IRQ        = hp300_init_IRQ;
 	mach_get_model       = hp300_get_model;
-	arch_gettimeoffset   = hp300_gettimeoffset;
 	mach_hwclk	     = hp300_hwclk;
 	mach_get_ss	     = hp300_get_ss;
 	mach_reset           = hp300_reset;
diff --git a/arch/m68k/hp300/time.c b/arch/m68k/hp300/time.c
index 289d928a46cb..bfee13e1d0fe 100644
--- a/arch/m68k/hp300/time.c
+++ b/arch/m68k/hp300/time.c
@@ -8,6 +8,7 @@
  */
 
 #include <asm/ptrace.h>
+#include <linux/clocksource.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -19,6 +20,18 @@
 #include <asm/traps.h>
 #include <asm/blinken.h>
 
+static u64 hp300_read_clk(struct clocksource *cs);
+
+static struct clocksource hp300_clk = {
+	.name   = "timer",
+	.rating = 250,
+	.read   = hp300_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total, clk_offset;
+
 /* Clock hardware definitions */
 
 #define CLOCKBASE	0xf05f8000
@@ -28,39 +41,61 @@
 #define	CLKCR3		CLKCR1
 #define	CLKSR		CLKCR2
 #define	CLKMSB1		0x5
+#define	CLKLSB1		0x7
 #define	CLKMSB2		0x9
 #define	CLKMSB3		0xD
 
+#define	CLKSR_INT1	BIT(0)
+
 /* This is for machines which generate the exact clock. */
-#define USECS_PER_JIFFY (1000000/HZ)
 
-#define INTVAL ((10000 / 4) - 1)
+#define HP300_TIMER_CLOCK_FREQ 250000
+#define HP300_TIMER_CYCLES     (HP300_TIMER_CLOCK_FREQ / HZ)
+#define INTVAL                 (HP300_TIMER_CYCLES - 1)
 
 static irqreturn_t hp300_tick(int irq, void *dev_id)
 {
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
 	unsigned long tmp;
-	irq_handler_t vector = dev_id;
+
+	local_irq_save(flags);
 	in_8(CLOCKBASE + CLKSR);
 	asm volatile ("movpw %1@(5),%0" : "=d" (tmp) : "a" (CLOCKBASE));
+	clk_total += INTVAL;
+	clk_offset = 0;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
 	/* Turn off the network and SCSI leds */
 	blinken_leds(0, 0xe0);
-	return vector(irq, NULL);
+	return IRQ_HANDLED;
 }
 
-u32 hp300_gettimeoffset(void)
+static u64 hp300_read_clk(struct clocksource *cs)
 {
-  /* Read current timer 1 value */
-  unsigned char lsb, msb1, msb2;
-  unsigned short ticks;
-
-  msb1 = in_8(CLOCKBASE + 5);
-  lsb = in_8(CLOCKBASE + 7);
-  msb2 = in_8(CLOCKBASE + 5);
-  if (msb1 != msb2)
-    /* A carry happened while we were reading.  Read it again */
-    lsb = in_8(CLOCKBASE + 7);
-  ticks = INTVAL - ((msb2 << 8) | lsb);
-  return ((USECS_PER_JIFFY * ticks) / INTVAL) * 1000;
+	unsigned long flags;
+	unsigned char lsb, msb, msb_new;
+	u32 ticks;
+
+	local_irq_save(flags);
+	/* Read current timer 1 value */
+	msb = in_8(CLOCKBASE + CLKMSB1);
+again:
+	if ((in_8(CLOCKBASE + CLKSR) & CLKSR_INT1) && msb > 0)
+		clk_offset = INTVAL;
+	lsb = in_8(CLOCKBASE + CLKLSB1);
+	msb_new = in_8(CLOCKBASE + CLKMSB1);
+	if (msb_new != msb) {
+		msb = msb_new;
+		goto again;
+	}
+
+	ticks = INTVAL - ((msb << 8) | lsb);
+	ticks += clk_offset + clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 void __init hp300_sched_init(irq_handler_t vector)
@@ -70,9 +105,11 @@ void __init hp300_sched_init(irq_handler_t vector)
 
   asm volatile(" movpw %0,%1@(5)" : : "d" (INTVAL), "a" (CLOCKBASE));
 
-  if (request_irq(IRQ_AUTO_6, hp300_tick, 0, "timer tick", vector))
+  if (request_irq(IRQ_AUTO_6, hp300_tick, IRQF_TIMER, "timer tick", vector))
     pr_err("Couldn't register timer interrupt\n");
 
   out_8(CLOCKBASE + CLKCR2, 0x1);		/* select CR1 */
   out_8(CLOCKBASE + CLKCR1, 0x40);		/* enable irq */
+
+  clocksource_register_hz(&hp300_clk, HP300_TIMER_CLOCK_FREQ);
 }
diff --git a/arch/m68k/hp300/time.h b/arch/m68k/hp300/time.h
index f5583ec4033d..1d77b55cc72a 100644
--- a/arch/m68k/hp300/time.h
+++ b/arch/m68k/hp300/time.h
@@ -1,2 +1 @@
 extern void hp300_sched_init(irq_handler_t vector);
-extern u32 hp300_gettimeoffset(void);
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 2c359d9e80f6..0ddae4a74adb 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -18,6 +18,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += sections.h
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 782b78f8a048..6c03ca5bc436 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -377,8 +377,6 @@ static inline void isa_delay(void)
 #define writesw(port, buf, nr)    raw_outsw((port), (u16 *)(buf), (nr))
 #define writesl(port, buf, nr)    raw_outsl((port), (u32 *)(buf), (nr))
 
-#define mmiowb()
-
 #ifndef CONFIG_SUN3
 #define IO_SPACE_LIMIT 0xffff
 #else
diff --git a/arch/m68k/include/asm/mvme147hw.h b/arch/m68k/include/asm/mvme147hw.h
index 9c7ff67c5ffd..257b29184af9 100644
--- a/arch/m68k/include/asm/mvme147hw.h
+++ b/arch/m68k/include/asm/mvme147hw.h
@@ -66,7 +66,7 @@ struct pcc_regs {
 #define PCC_INT_ENAB		0x08
 
 #define PCC_TIMER_INT_CLR	0x80
-#define PCC_TIMER_PRELOAD	63936l
+#define PCC_TIMER_CLR_OVF	0x04
 
 #define PCC_LEVEL_ABORT		0x07
 #define PCC_LEVEL_SERIAL	0x04
diff --git a/arch/m68k/include/asm/tlb.h b/arch/m68k/include/asm/tlb.h
index b4b9efb6f963..3c81f6adfc8b 100644
--- a/arch/m68k/include/asm/tlb.h
+++ b/arch/m68k/include/asm/tlb.h
@@ -2,20 +2,6 @@
 #ifndef _M68K_TLB_H
 #define _M68K_TLB_H
 
-/*
- * m68k doesn't need any special per-pte or
- * per-vma handling..
- */
-#define tlb_start_vma(tlb, vma)	do { } while (0)
-#define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-
-/*
- * .. because we flush the whole mm when it
- * fills up.
- */
-#define tlb_flush(tlb)		flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _M68K_TLB_H */
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index cd9317d53276..11be08f4f750 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -54,8 +54,6 @@ struct mac_booter_data mac_bi_data;
 /* The phys. video addr. - might be bogus on some machines */
 static unsigned long mac_orig_videoaddr;
 
-/* Mac specific timer functions */
-extern u32 mac_gettimeoffset(void);
 extern int mac_hwclk(int, struct rtc_time *);
 extern void iop_preinit(void);
 extern void iop_init(void);
@@ -155,7 +153,6 @@ void __init config_mac(void)
 	mach_sched_init = mac_sched_init;
 	mach_init_IRQ = mac_init_IRQ;
 	mach_get_model = mac_get_model;
-	arch_gettimeoffset = mac_gettimeoffset;
 	mach_hwclk = mac_hwclk;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 0b0289459173..3c2cfcb74982 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -23,6 +23,7 @@
  *
  */
 
+#include <linux/clocksource.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -55,16 +56,6 @@ static __u8 rbv_clear;
 static int gIER,gIFR,gBufA,gBufB;
 
 /*
- * Timer defs.
- */
-
-#define TICK_SIZE		10000
-#define MAC_CLOCK_TICK		(783300/HZ)		/* ticks per HZ */
-#define MAC_CLOCK_LOW		(MAC_CLOCK_TICK&0xFF)
-#define MAC_CLOCK_HIGH		(MAC_CLOCK_TICK>>8)
-
-
-/*
  * On Macs with a genuine VIA chip there is no way to mask an individual slot
  * interrupt. This limitation also seems to apply to VIA clone logic cores in
  * Quadra-like ASICs. (RBV and OSS machines don't have this limitation.)
@@ -272,22 +263,6 @@ void __init via_init(void)
 }
 
 /*
- * Start the 100 Hz clock
- */
-
-void __init via_init_clock(irq_handler_t func)
-{
-	via1[vACR] |= 0x40;
-	via1[vT1LL] = MAC_CLOCK_LOW;
-	via1[vT1LH] = MAC_CLOCK_HIGH;
-	via1[vT1CL] = MAC_CLOCK_LOW;
-	via1[vT1CH] = MAC_CLOCK_HIGH;
-
-	if (request_irq(IRQ_MAC_TIMER_1, func, 0, "timer", func))
-		pr_err("Couldn't register %s interrupt\n", "timer");
-}
-
-/*
  * Debugging dump, used in various places to see what's going on.
  */
 
@@ -315,29 +290,6 @@ void via_debug_dump(void)
 }
 
 /*
- * This is always executed with interrupts disabled.
- *
- * TBI: get time offset between scheduling timer ticks
- */
-
-u32 mac_gettimeoffset(void)
-{
-	unsigned long ticks, offset = 0;
-
-	/* read VIA1 timer 2 current value */
-	ticks = via1[vT1CL] | (via1[vT1CH] << 8);
-	/* The probability of underflow is less than 2% */
-	if (ticks > MAC_CLOCK_TICK - MAC_CLOCK_TICK / 50)
-		/* Check for pending timer interrupt in VIA1 IFR */
-		if (via1[vIFR] & 0x40) offset = TICK_SIZE;
-
-	ticks = MAC_CLOCK_TICK - ticks;
-	ticks = ticks * 10000L / MAC_CLOCK_TICK;
-
-	return (ticks + offset) * 1000;
-}
-
-/*
  * Flush the L2 cache on Macs that have it by flipping
  * the system into 24-bit mode for an instant.
  */
@@ -440,6 +392,8 @@ void via_nubus_irq_shutdown(int irq)
  * via6522.c :-), disable/pending masks added.
  */
 
+#define VIA_TIMER_1_INT BIT(6)
+
 void via1_irq(struct irq_desc *desc)
 {
 	int irq_num;
@@ -449,6 +403,21 @@ void via1_irq(struct irq_desc *desc)
 	if (!events)
 		return;
 
+	irq_num = IRQ_MAC_TIMER_1;
+	irq_bit = VIA_TIMER_1_INT;
+	if (events & irq_bit) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		via1[vIFR] = irq_bit;
+		generic_handle_irq(irq_num);
+		local_irq_restore(flags);
+
+		events &= ~irq_bit;
+		if (!events)
+			return;
+	}
+
 	irq_num = VIA1_SOURCE_BASE;
 	irq_bit = 1;
 	do {
@@ -605,3 +574,82 @@ int via2_scsi_drq_pending(void)
 	return via2[gIFR] & (1 << IRQ_IDX(IRQ_MAC_SCSIDRQ));
 }
 EXPORT_SYMBOL(via2_scsi_drq_pending);
+
+/* timer and clock source */
+
+#define VIA_CLOCK_FREQ     783360                /* VIA "phase 2" clock in Hz */
+#define VIA_TIMER_CYCLES   (VIA_CLOCK_FREQ / HZ) /* clock cycles per jiffy */
+
+#define VIA_TC             (VIA_TIMER_CYCLES - 2) /* including 0 and -1 */
+#define VIA_TC_LOW         (VIA_TC & 0xFF)
+#define VIA_TC_HIGH        (VIA_TC >> 8)
+
+static u64 mac_read_clk(struct clocksource *cs);
+
+static struct clocksource mac_clk = {
+	.name   = "via1",
+	.rating = 250,
+	.read   = mac_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total, clk_offset;
+
+static irqreturn_t via_timer_handler(int irq, void *dev_id)
+{
+	irq_handler_t timer_routine = dev_id;
+
+	clk_total += VIA_TIMER_CYCLES;
+	clk_offset = 0;
+	timer_routine(0, NULL);
+
+	return IRQ_HANDLED;
+}
+
+void __init via_init_clock(irq_handler_t timer_routine)
+{
+	if (request_irq(IRQ_MAC_TIMER_1, via_timer_handler, IRQF_TIMER, "timer",
+			timer_routine)) {
+		pr_err("Couldn't register %s interrupt\n", "timer");
+		return;
+	}
+
+	via1[vT1LL] = VIA_TC_LOW;
+	via1[vT1LH] = VIA_TC_HIGH;
+	via1[vT1CL] = VIA_TC_LOW;
+	via1[vT1CH] = VIA_TC_HIGH;
+	via1[vACR] |= 0x40;
+
+	clocksource_register_hz(&mac_clk, VIA_CLOCK_FREQ);
+}
+
+static u64 mac_read_clk(struct clocksource *cs)
+{
+	unsigned long flags;
+	u8 count_high;
+	u16 count;
+	u32 ticks;
+
+	/*
+	 * Timer counter wrap-around is detected with the timer interrupt flag
+	 * but reading the counter low byte (vT1CL) would reset the flag.
+	 * Also, accessing both counter registers is essentially a data race.
+	 * These problems are avoided by ignoring the low byte. Clock accuracy
+	 * is 256 times worse (error can reach 0.327 ms) but CPU overhead is
+	 * reduced by avoiding slow VIA register accesses.
+	 */
+
+	local_irq_save(flags);
+	count_high = via1[vT1CH];
+	if (count_high == 0xFF)
+		count_high = 0;
+	if (count_high > 0 && (via1[vIFR] & VIA_TIMER_1_INT))
+		clk_offset = VIA_TIMER_CYCLES;
+	count = count_high << 8;
+	ticks = VIA_TIMER_CYCLES - count;
+	ticks += clk_offset + clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
+}
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index adea549d240e..545a1fe0e119 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
@@ -38,18 +39,12 @@
 
 static void mvme147_get_model(char *model);
 extern void mvme147_sched_init(irq_handler_t handler);
-extern u32 mvme147_gettimeoffset(void);
 extern int mvme147_hwclk (int, struct rtc_time *);
 extern void mvme147_reset (void);
 
 
 static int bcd2int (unsigned char b);
 
-/* Save tick handler routine pointer, will point to xtime_update() in
- * kernel/time/timekeeping.c, called via mvme147_process_int() */
-
-irq_handler_t tick_handler;
-
 
 int __init mvme147_parse_bootinfo(const struct bi_record *bi)
 {
@@ -89,7 +84,6 @@ void __init config_mvme147(void)
 	mach_max_dma_address	= 0x01000000;
 	mach_sched_init		= mvme147_sched_init;
 	mach_init_IRQ		= mvme147_init_IRQ;
-	arch_gettimeoffset	= mvme147_gettimeoffset;
 	mach_hwclk		= mvme147_hwclk;
 	mach_reset		= mvme147_reset;
 	mach_get_model		= mvme147_get_model;
@@ -99,45 +93,76 @@ void __init config_mvme147(void)
 		vme_brdtype = VME_TYPE_MVME147;
 }
 
+static u64 mvme147_read_clk(struct clocksource *cs);
+
+static struct clocksource mvme147_clk = {
+	.name   = "pcc",
+	.rating = 250,
+	.read   = mvme147_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total;
+
+#define PCC_TIMER_CLOCK_FREQ 160000
+#define PCC_TIMER_CYCLES     (PCC_TIMER_CLOCK_FREQ / HZ)
+#define PCC_TIMER_PRELOAD    (0x10000 - PCC_TIMER_CYCLES)
 
 /* Using pcc tick timer 1 */
 
 static irqreturn_t mvme147_timer_int (int irq, void *dev_id)
 {
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
+
+	local_irq_save(flags);
 	m147_pcc->t1_int_cntrl = PCC_TIMER_INT_CLR;
-	m147_pcc->t1_int_cntrl = PCC_INT_ENAB|PCC_LEVEL_TIMER1;
-	return tick_handler(irq, dev_id);
+	m147_pcc->t1_cntrl = PCC_TIMER_CLR_OVF;
+	clk_total += PCC_TIMER_CYCLES;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
+	return IRQ_HANDLED;
 }
 
 
 void mvme147_sched_init (irq_handler_t timer_routine)
 {
-	tick_handler = timer_routine;
-	if (request_irq(PCC_IRQ_TIMER1, mvme147_timer_int, 0, "timer 1", NULL))
+	if (request_irq(PCC_IRQ_TIMER1, mvme147_timer_int, IRQF_TIMER,
+			"timer 1", timer_routine))
 		pr_err("Couldn't register timer interrupt\n");
 
 	/* Init the clock with a value */
-	/* our clock goes off every 6.25us */
+	/* The clock counter increments until 0xFFFF then reloads */
 	m147_pcc->t1_preload = PCC_TIMER_PRELOAD;
 	m147_pcc->t1_cntrl = 0x0;	/* clear timer */
 	m147_pcc->t1_cntrl = 0x3;	/* start timer */
 	m147_pcc->t1_int_cntrl = PCC_TIMER_INT_CLR;  /* clear pending ints */
 	m147_pcc->t1_int_cntrl = PCC_INT_ENAB|PCC_LEVEL_TIMER1;
+
+	clocksource_register_hz(&mvme147_clk, PCC_TIMER_CLOCK_FREQ);
 }
 
-/* This is always executed with interrupts disabled.  */
-/* XXX There are race hazards in this code XXX */
-u32 mvme147_gettimeoffset(void)
+static u64 mvme147_read_clk(struct clocksource *cs)
 {
-	volatile unsigned short *cp = (volatile unsigned short *)0xfffe1012;
-	unsigned short n;
-
-	n = *cp;
-	while (n != *cp)
-		n = *cp;
-
-	n -= PCC_TIMER_PRELOAD;
-	return ((unsigned long)n * 25 / 4) * 1000;
+	unsigned long flags;
+	u8 overflow, tmp;
+	u16 count;
+	u32 ticks;
+
+	local_irq_save(flags);
+	tmp = m147_pcc->t1_cntrl >> 4;
+	count = m147_pcc->t1_count;
+	overflow = m147_pcc->t1_cntrl >> 4;
+	if (overflow != tmp)
+		count = m147_pcc->t1_count;
+	count -= PCC_TIMER_PRELOAD;
+	ticks = count + overflow * PCC_TIMER_CYCLES;
+	ticks += clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 static int bcd2int (unsigned char b)
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 6ee36a5b528d..9bc2da69f80c 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
@@ -44,17 +45,11 @@ static MK48T08ptr_t volatile rtc = (MK48T08ptr_t)MVME_RTC_BASE;
 
 static void mvme16x_get_model(char *model);
 extern void mvme16x_sched_init(irq_handler_t handler);
-extern u32 mvme16x_gettimeoffset(void);
 extern int mvme16x_hwclk (int, struct rtc_time *);
 extern void mvme16x_reset (void);
 
 int bcd2int (unsigned char b);
 
-/* Save tick handler routine pointer, will point to xtime_update() in
- * kernel/time/timekeeping.c, called via mvme16x_process_int() */
-
-static irq_handler_t tick_handler;
-
 
 unsigned short mvme16x_config;
 EXPORT_SYMBOL(mvme16x_config);
@@ -120,11 +115,11 @@ static void __init mvme16x_init_IRQ (void)
 	m68k_setup_user_interrupt(VEC_USER, 192);
 }
 
-#define pcc2chip	((volatile u_char *)0xfff42000)
-#define PccSCCMICR	0x1d
-#define PccSCCTICR	0x1e
-#define PccSCCRICR	0x1f
-#define PccTPIACKR	0x25
+#define PCC2CHIP   (0xfff42000)
+#define PCCSCCMICR (PCC2CHIP + 0x1d)
+#define PCCSCCTICR (PCC2CHIP + 0x1e)
+#define PCCSCCRICR (PCC2CHIP + 0x1f)
+#define PCCTPIACKR (PCC2CHIP + 0x25)
 
 #ifdef CONFIG_EARLY_PRINTK
 
@@ -232,10 +227,10 @@ void mvme16x_cons_write(struct console *co, const char *str, unsigned count)
 	base_addr[CyIER] = CyTxMpty;
 
 	while (1) {
-		if (pcc2chip[PccSCCTICR] & 0x20)
+		if (in_8(PCCSCCTICR) & 0x20)
 		{
 			/* We have a Tx int. Acknowledge it */
-			sink = pcc2chip[PccTPIACKR];
+			sink = in_8(PCCTPIACKR);
 			if ((base_addr[CyLICR] >> 2) == port) {
 				if (i == count) {
 					/* Last char of string is now output */
@@ -277,7 +272,6 @@ void __init config_mvme16x(void)
     mach_max_dma_address = 0xffffffff;
     mach_sched_init      = mvme16x_sched_init;
     mach_init_IRQ        = mvme16x_init_IRQ;
-    arch_gettimeoffset   = mvme16x_gettimeoffset;
     mach_hwclk           = mvme16x_hwclk;
     mach_reset		 = mvme16x_reset;
     mach_get_model       = mvme16x_get_model;
@@ -350,10 +344,46 @@ static irqreturn_t mvme16x_abort_int (int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static u64 mvme16x_read_clk(struct clocksource *cs);
+
+static struct clocksource mvme16x_clk = {
+	.name   = "pcc",
+	.rating = 250,
+	.read   = mvme16x_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total;
+
+#define PCC_TIMER_CLOCK_FREQ 1000000
+#define PCC_TIMER_CYCLES     (PCC_TIMER_CLOCK_FREQ / HZ)
+
+#define PCCTCMP1             (PCC2CHIP + 0x04)
+#define PCCTCNT1             (PCC2CHIP + 0x08)
+#define PCCTOVR1             (PCC2CHIP + 0x17)
+#define PCCTIC1              (PCC2CHIP + 0x1b)
+
+#define PCCTOVR1_TIC_EN      0x01
+#define PCCTOVR1_COC_EN      0x02
+#define PCCTOVR1_OVR_CLR     0x04
+
+#define PCCTIC1_INT_CLR      0x08
+#define PCCTIC1_INT_EN       0x10
+
 static irqreturn_t mvme16x_timer_int (int irq, void *dev_id)
 {
-    *(volatile unsigned char *)0xfff4201b |= 8;
-    return tick_handler(irq, dev_id);
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	out_8(PCCTIC1, in_8(PCCTIC1) | PCCTIC1_INT_CLR);
+	out_8(PCCTOVR1, PCCTOVR1_OVR_CLR);
+	clk_total += PCC_TIMER_CYCLES;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
+	return IRQ_HANDLED;
 }
 
 void mvme16x_sched_init (irq_handler_t timer_routine)
@@ -361,16 +391,17 @@ void mvme16x_sched_init (irq_handler_t timer_routine)
     uint16_t brdno = be16_to_cpu(mvme_bdid.brdno);
     int irq;
 
-    tick_handler = timer_routine;
     /* Using PCCchip2 or MC2 chip tick timer 1 */
-    *(volatile unsigned long *)0xfff42008 = 0;
-    *(volatile unsigned long *)0xfff42004 = 10000;	/* 10ms */
-    *(volatile unsigned char *)0xfff42017 |= 3;
-    *(volatile unsigned char *)0xfff4201b = 0x16;
-    if (request_irq(MVME16x_IRQ_TIMER, mvme16x_timer_int, 0,
-				"timer", mvme16x_timer_int))
+    out_be32(PCCTCNT1, 0);
+    out_be32(PCCTCMP1, PCC_TIMER_CYCLES);
+    out_8(PCCTOVR1, in_8(PCCTOVR1) | PCCTOVR1_TIC_EN | PCCTOVR1_COC_EN);
+    out_8(PCCTIC1, PCCTIC1_INT_EN | 6);
+    if (request_irq(MVME16x_IRQ_TIMER, mvme16x_timer_int, IRQF_TIMER, "timer",
+                    timer_routine))
 	panic ("Couldn't register timer int");
 
+    clocksource_register_hz(&mvme16x_clk, PCC_TIMER_CLOCK_FREQ);
+
     if (brdno == 0x0162 || brdno == 0x172)
 	irq = MVME162_IRQ_ABORT;
     else
@@ -380,11 +411,23 @@ void mvme16x_sched_init (irq_handler_t timer_routine)
 	panic ("Couldn't register abort int");
 }
 
-
-/* This is always executed with interrupts disabled.  */
-u32 mvme16x_gettimeoffset(void)
+static u64 mvme16x_read_clk(struct clocksource *cs)
 {
-    return (*(volatile u32 *)0xfff42008) * 1000;
+	unsigned long flags;
+	u8 overflow, tmp;
+	u32 ticks;
+
+	local_irq_save(flags);
+	tmp = in_8(PCCTOVR1) >> 4;
+	ticks = in_be32(PCCTCNT1);
+	overflow = in_8(PCCTOVR1) >> 4;
+	if (overflow != tmp)
+		ticks = in_be32(PCCTCNT1);
+	ticks += overflow * PCC_TIMER_CYCLES;
+	ticks += clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 int bcd2int (unsigned char b)
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 96810d91da2b..e63eb5f06999 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -40,7 +40,6 @@ extern void q40_init_IRQ(void);
 static void q40_get_model(char *model);
 extern void q40_sched_init(irq_handler_t handler);
 
-static u32 q40_gettimeoffset(void);
 static int q40_hwclk(int, struct rtc_time *);
 static unsigned int q40_get_ss(void);
 static int q40_get_rtc_pll(struct rtc_pll_info *pll);
@@ -169,7 +168,6 @@ void __init config_q40(void)
 	mach_sched_init = q40_sched_init;
 
 	mach_init_IRQ = q40_init_IRQ;
-	arch_gettimeoffset = q40_gettimeoffset;
 	mach_hwclk = q40_hwclk;
 	mach_get_ss = q40_get_ss;
 	mach_get_rtc_pll = q40_get_rtc_pll;
@@ -201,13 +199,6 @@ int __init q40_parse_bootinfo(const struct bi_record *rec)
 	return 1;
 }
 
-
-static u32 q40_gettimeoffset(void)
-{
-	return 5000 * (ql_ticks != 0) * 1000;
-}
-
-
 /*
  * Looks like op is non-zero for setting the clock, and zero for
  * reading the clock.
diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
index 3e7603202977..1c696906c159 100644
--- a/arch/m68k/q40/q40ints.c
+++ b/arch/m68k/q40/q40ints.c
@@ -127,10 +127,10 @@ void q40_mksound(unsigned int hz, unsigned int ticks)
 	sound_ticks = ticks << 1;
 }
 
-static irq_handler_t q40_timer_routine;
-
-static irqreturn_t q40_timer_int (int irq, void * dev)
+static irqreturn_t q40_timer_int(int irq, void *dev_id)
 {
+	irq_handler_t timer_routine = dev_id;
+
 	ql_ticks = ql_ticks ? 0 : 1;
 	if (sound_ticks) {
 		unsigned char sval=(sound_ticks & 1) ? 128-SVOL : 128+SVOL;
@@ -139,8 +139,13 @@ static irqreturn_t q40_timer_int (int irq, void * dev)
 		*DAC_RIGHT=sval;
 	}
 
-	if (!ql_ticks)
-		q40_timer_routine(irq, dev);
+	if (!ql_ticks) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		timer_routine(0, NULL);
+		local_irq_restore(flags);
+	}
 	return IRQ_HANDLED;
 }
 
@@ -148,11 +153,9 @@ void q40_sched_init (irq_handler_t timer_routine)
 {
 	int timer_irq;
 
-	q40_timer_routine = timer_routine;
 	timer_irq = Q40_IRQ_FRAME;
 
-	if (request_irq(timer_irq, q40_timer_int, 0,
-				"timer", q40_timer_int))
+	if (request_irq(timer_irq, q40_timer_int, 0, "timer", timer_routine))
 		panic("Couldn't register timer int");
 
 	master_outb(-1, FRAME_CLEAR_REG);
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 542c4404861c..229ea37dfe1b 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -37,7 +37,6 @@
 
 char sun3_reserved_pmeg[SUN3_PMEGS_NUM];
 
-extern u32 sun3_gettimeoffset(void);
 static void sun3_sched_init(irq_handler_t handler);
 extern void sun3_get_model (char* model);
 extern int sun3_hwclk(int set, struct rtc_time *t);
@@ -138,7 +137,6 @@ void __init config_sun3(void)
         mach_sched_init      =  sun3_sched_init;
         mach_init_IRQ        =  sun3_init_IRQ;
         mach_reset           =  sun3_reboot;
-	arch_gettimeoffset   =  sun3_gettimeoffset;
 	mach_get_model	     =  sun3_get_model;
 	mach_hwclk           =  sun3_hwclk;
 	mach_halt	     =  sun3_halt;
diff --git a/arch/m68k/sun3/intersil.c b/arch/m68k/sun3/intersil.c
index d911070af02a..8fc74864de81 100644
--- a/arch/m68k/sun3/intersil.c
+++ b/arch/m68k/sun3/intersil.c
@@ -22,13 +22,6 @@
 #define STOP_VAL (INTERSIL_STOP | INTERSIL_INT_ENABLE | INTERSIL_24H_MODE)
 #define START_VAL (INTERSIL_RUN | INTERSIL_INT_ENABLE | INTERSIL_24H_MODE)
 
-/* does this need to be implemented? */
-u32 sun3_gettimeoffset(void)
-{
-  return 1000;
-}
-
-
 /* get/set hwclock */
 
 int sun3_hwclk(int set, struct rtc_time *t)
diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c
index 6bbca30c9188..a5824abb4a39 100644
--- a/arch/m68k/sun3/sun3ints.c
+++ b/arch/m68k/sun3/sun3ints.c
@@ -61,8 +61,10 @@ static irqreturn_t sun3_int7(int irq, void *dev_id)
 
 static irqreturn_t sun3_int5(int irq, void *dev_id)
 {
+	unsigned long flags;
 	unsigned int cnt;
 
+	local_irq_save(flags);
 #ifdef CONFIG_SUN3
 	intersil_clear();
 #endif
@@ -76,6 +78,7 @@ static irqreturn_t sun3_int5(int irq, void *dev_id)
 	cnt = kstat_irqs_cpu(irq, 0);
 	if (!(cnt % 20))
 		sun3_leds(led_pattern[cnt % 160 / 20]);
+	local_irq_restore(flags);
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/m68k/sun3x/config.c b/arch/m68k/sun3x/config.c
index 33d3a1c6fba0..03ce7f9facfe 100644
--- a/arch/m68k/sun3x/config.c
+++ b/arch/m68k/sun3x/config.c
@@ -49,7 +49,6 @@ void __init config_sun3x(void)
 	mach_sched_init      = sun3x_sched_init;
 	mach_init_IRQ        = sun3_init_IRQ;
 
-	arch_gettimeoffset   = sun3x_gettimeoffset;
 	mach_reset           = sun3x_reboot;
 
 	mach_hwclk           = sun3x_hwclk;
diff --git a/arch/m68k/sun3x/time.c b/arch/m68k/sun3x/time.c
index 047e2bcee3d7..9163294b0fb6 100644
--- a/arch/m68k/sun3x/time.c
+++ b/arch/m68k/sun3x/time.c
@@ -73,22 +73,21 @@ int sun3x_hwclk(int set, struct rtc_time *t)
 
 	return 0;
 }
-/* Not much we can do here */
-u32 sun3x_gettimeoffset(void)
-{
-    return 0L;
-}
 
 #if 0
-static void sun3x_timer_tick(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t sun3x_timer_tick(int irq, void *dev_id)
 {
-    void (*vector)(int, void *, struct pt_regs *) = dev_id;
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
 
-    /* Clear the pending interrupt - pulse the enable line low */
-    disable_irq(5);
-    enable_irq(5);
+	local_irq_save(flags);
+	/* Clear the pending interrupt - pulse the enable line low */
+	disable_irq(5);
+	enable_irq(5);
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
 
-    vector(irq, NULL, regs);
+	return IRQ_HANDLED;
 }
 #endif
 
diff --git a/arch/m68k/sun3x/time.h b/arch/m68k/sun3x/time.h
index 496f406412ad..86ce78bb3c28 100644
--- a/arch/m68k/sun3x/time.h
+++ b/arch/m68k/sun3x/time.h
@@ -3,7 +3,6 @@
 #define SUN3X_TIME_H
 
 extern int sun3x_hwclk(int set, struct rtc_time *t);
-u32 sun3x_gettimeoffset(void);
 void sun3x_sched_init(irq_handler_t vector);
 
 struct mostek_dt {
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index a51b965b3b82..adb179f519f9 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -41,6 +41,7 @@ config MICROBLAZE
 	select TRACING_SUPPORT
 	select VIRT_TO_BUS
 	select CPU_NO_EFFICIENT_FFS
+	select MMU_GATHER_NO_RANGE if MMU
 
 # Endianness selection
 choice
@@ -58,15 +59,9 @@ config CPU_LITTLE_ENDIAN
 
 endchoice
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config ZONE_DMA
 	def_bool y
 
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	def_bool n
 
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 1a8285c3f693..17a8d0a62038 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -23,6 +23,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h
index 99b6ded54849..628a78ee0a72 100644
--- a/arch/microblaze/include/asm/tlb.h
+++ b/arch/microblaze/include/asm/tlb.h
@@ -11,16 +11,7 @@
 #ifndef _ASM_MICROBLAZE_TLB_H
 #define _ASM_MICROBLAZE_TLB_H
 
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 #include <linux/pagemap.h>
-
-#ifdef CONFIG_MMU
-#define tlb_start_vma(tlb, vma)		do { } while (0)
-#define tlb_end_vma(tlb, vma)		do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
-#endif
-
 #include <asm-generic/tlb.h>
 
 #endif /* _ASM_MICROBLAZE_TLB_H */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 4a5f5b0ee9a9..b9c48b27162d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1037,13 +1037,6 @@ source "arch/mips/paravirt/Kconfig"
 
 endmenu
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config GENERIC_HWEIGHT
 	bool
 	default y
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 845fbbc7a2e3..29997e42480e 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -102,9 +102,6 @@ static inline void set_io_port_base(unsigned long base)
 #define iobarrier_w() wmb()
 #define iobarrier_sync() iob()
 
-/* Some callers use this older API instead.  */
-#define mmiowb() iobarrier_w()
-
 /*
  *     virt_to_phys    -       map virtual addresses to physical
  *     @address: address to remap
diff --git a/arch/mips/include/asm/mmiowb.h b/arch/mips/include/asm/mmiowb.h
new file mode 100644
index 000000000000..a40824e3ef8e
--- /dev/null
+++ b/arch/mips/include/asm/mmiowb.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_MMIOWB_H
+#define _ASM_MMIOWB_H
+
+#include <asm/io.h>
+
+#define mmiowb()	iobarrier_w()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_MMIOWB_H */
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index ee81297d9117..8a88eb265516 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -11,6 +11,21 @@
 
 #include <asm/processor.h>
 #include <asm/qrwlock.h>
+
+#include <asm-generic/qspinlock_types.h>
+
+#define	queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
+	smp_store_release(&lock->locked, 0);
+}
+
 #include <asm/qspinlock.h>
 
 #endif /* _ASM_SPINLOCK_H */
diff --git a/arch/mips/include/asm/tlb.h b/arch/mips/include/asm/tlb.h
index b6823b9e94da..90f3ad76d9e0 100644
--- a/arch/mips/include/asm/tlb.h
+++ b/arch/mips/include/asm/tlb.h
@@ -5,23 +5,6 @@
 #include <asm/cpu-features.h>
 #include <asm/mipsregs.h>
 
-/*
- * MIPS doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for area to be unmapped.
- */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up.
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
 #define _UNIQUE_ENTRYHI(base, idx)					\
 		(((base) + ((idx) << (PAGE_SHIFT + 1))) |		\
 		 (cpu_has_tlbinv ? MIPS_ENTRYHI_EHINV : 0))
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 0effd3cba9a7..98bf0c222b5f 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -186,8 +186,9 @@ enum which_ebpf_reg {
  * separate frame pointer, so BPF_REG_10 relative accesses are
  * adjusted to be $sp relative.
  */
-int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn,
-		     enum which_ebpf_reg w)
+static int ebpf_to_mips_reg(struct jit_ctx *ctx,
+			    const struct bpf_insn *insn,
+			    enum which_ebpf_reg w)
 {
 	int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ?
 		insn->src_reg : insn->dst_reg;
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index addb7f5f5264..55559ca0efe4 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -60,9 +60,6 @@ config GENERIC_LOCKBREAK
         def_bool y
 	depends on PREEMPT
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index 64ceff7ab99b..688b6ed26227 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -31,6 +31,7 @@ generic-y += limits.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += parport.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/nds32/include/asm/io.h b/arch/nds32/include/asm/io.h
index 71cd226d6863..5ef8ae5ba833 100644
--- a/arch/nds32/include/asm/io.h
+++ b/arch/nds32/include/asm/io.h
@@ -55,8 +55,6 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 #define __iormb()               rmb()
 #define __iowmb()               wmb()
 
-#define mmiowb()        __asm__ __volatile__ ("msync all" : : : "memory");
-
 /*
  * {read,write}{b,w,l,q}_relaxed() are like the regular version, but
  * are not guaranteed to provide ordering against spinlocks or memory
diff --git a/arch/nds32/include/asm/tlb.h b/arch/nds32/include/asm/tlb.h
index b35ae5eae3ab..d5ae571c8d30 100644
--- a/arch/nds32/include/asm/tlb.h
+++ b/arch/nds32/include/asm/tlb.h
@@ -4,22 +4,6 @@
 #ifndef __ASMNDS32_TLB_H
 #define __ASMNDS32_TLB_H
 
-#define tlb_start_vma(tlb,vma)						\
-	do {								\
-		if (!tlb->fullmm)					\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	} while (0)
-
-#define tlb_end_vma(tlb,vma)				\
-	do { 						\
-		if(!tlb->fullmm)			\
-			flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-	} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, addr) do { } while (0)
-
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
diff --git a/arch/nds32/include/asm/tlbflush.h b/arch/nds32/include/asm/tlbflush.h
index 9b411f401903..38ee769b18d8 100644
--- a/arch/nds32/include/asm/tlbflush.h
+++ b/arch/nds32/include/asm/tlbflush.h
@@ -42,6 +42,5 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 
 void update_mmu_cache(struct vm_area_struct *vma,
 		      unsigned long address, pte_t * pte);
-void tlb_migrate_finish(struct mm_struct *mm);
 
 #endif
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 4ef15a61b7bc..ea37394ff3ea 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -24,6 +24,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select ARCH_DISCARD_MEMBLOCK
+	select MMU_GATHER_NO_RANGE if MMU
 
 config GENERIC_CSUM
 	def_bool y
@@ -40,9 +41,6 @@ config NO_IOPORT_MAP
 config FPU
 	def_bool n
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool n
 
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 88a667d12aaa..d7ef3512504a 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -27,6 +27,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/nios2/include/asm/tlb.h b/arch/nios2/include/asm/tlb.h
index d3bc648e08b5..f9f2e27e32dd 100644
--- a/arch/nios2/include/asm/tlb.h
+++ b/arch/nios2/include/asm/tlb.h
@@ -11,22 +11,12 @@
 #ifndef _ASM_NIOS2_TLB_H
 #define _ASM_NIOS2_TLB_H
 
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 extern void set_mmu_pid(unsigned long pid);
 
 /*
- * NiosII doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for the area to be unmapped.
+ * NIOS32 does have flush_tlb_range(), but it lacks a limit and fallback to
+ * full mm invalidation. So use flush_tlb_mm() for everything.
  */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  while (0)
-
-#define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
 
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index a5e361fbb75a..7cfb20555b10 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -36,6 +36,7 @@ config OPENRISC
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
+	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -43,12 +44,6 @@ config CPU_BIG_ENDIAN
 config MMU
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool n
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 22aa97136c01..1919cc5e0f11 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -24,6 +24,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/openrisc/include/asm/tlb.h b/arch/openrisc/include/asm/tlb.h
index fa4376a4515d..92d8a4209884 100644
--- a/arch/openrisc/include/asm/tlb.h
+++ b/arch/openrisc/include/asm/tlb.h
@@ -20,14 +20,10 @@
 #define __ASM_OPENRISC_TLB_H__
 
 /*
- * or32 doesn't need any special per-pte or
- * per-vma handling..
+ * OpenRISC doesn't have an efficient flush_tlb_range() so use flush_tlb_mm()
+ * for everything.
  */
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index c8e621296092..f1ed8ddfe486 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -75,12 +75,6 @@ config GENERIC_LOCKBREAK
 	default y
 	depends on SMP && PREEMPT
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	bool
 	default n
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 9bcd0c903dbb..b8c7db777144 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += seccomp.h
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 30a8315d5c07..93d37010b375 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -229,8 +229,6 @@ static inline void writeq(unsigned long long q, volatile void __iomem *addr)
 #define writel_relaxed(l, addr)	writel(l, addr)
 #define writeq_relaxed(q, addr)	writeq(q, addr)
 
-#define mmiowb() do { } while (0)
-
 void memset_io(volatile void __iomem *addr, unsigned char val, int count);
 void memcpy_fromio(void *dst, const volatile void __iomem *src, int count);
 void memcpy_toio(volatile void __iomem *dst, const void *src, int count);
diff --git a/arch/parisc/include/asm/tlb.h b/arch/parisc/include/asm/tlb.h
index 0c881e74d8a6..8c0446b04c9e 100644
--- a/arch/parisc/include/asm/tlb.h
+++ b/arch/parisc/include/asm/tlb.h
@@ -2,24 +2,6 @@
 #ifndef _PARISC_TLB_H
 #define _PARISC_TLB_H
 
-#define tlb_flush(tlb)			\
-do {	if ((tlb)->fullmm)		\
-		flush_tlb_mm((tlb)->mm);\
-} while (0)
-
-#define tlb_start_vma(tlb, vma) \
-do {	if (!(tlb)->fullmm)	\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define tlb_end_vma(tlb, vma)	\
-do {	if (!(tlb)->fullmm)	\
-		flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
-	do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
diff --git a/arch/parisc/kernel/stacktrace.c b/arch/parisc/kernel/stacktrace.c
index ec5835e83a7a..6f0b9c8d8052 100644
--- a/arch/parisc/kernel/stacktrace.c
+++ b/arch/parisc/kernel/stacktrace.c
@@ -29,22 +29,17 @@ static void dump_trace(struct task_struct *task, struct stack_trace *trace)
 	}
 }
 
-
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
  */
 void save_stack_trace(struct stack_trace *trace)
 {
 	dump_trace(current, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	dump_trace(tsk, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2d0be82c3061..fa7219ffeadc 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -103,13 +103,6 @@ config LOCKDEP_SUPPORT
 	bool
 	default y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config GENERIC_LOCKBREAK
 	bool
 	default y
@@ -132,6 +125,7 @@ config PPC
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
 	select ARCH_HAS_PTE_SPECIAL
@@ -218,6 +212,8 @@ config PPC
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
+	select HAVE_MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -318,6 +314,10 @@ config ARCH_SUSPEND_POSSIBLE
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
 		   || 44x || 40x
 
+config ARCH_SUSPEND_NONZERO_CPU
+	def_bool y
+	depends on PPC_POWERNV || PPC_PSERIES
+
 config PPC_DCR_NATIVE
 	bool
 
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index a0c132bedfae..36bda391e549 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -8,6 +8,5 @@ generic-y += irq_regs.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += vtime.h
 generic-y += msi.h
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 4b73847e9b95..1fad67b46409 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -34,14 +34,11 @@ extern struct pci_dev *isa_bridge_pcidev;
 #include <asm/byteorder.h>
 #include <asm/synch.h>
 #include <asm/delay.h>
+#include <asm/mmiowb.h>
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
 #include <asm/pgtable.h>
 
-#ifdef CONFIG_PPC64
-#include <asm/paca.h>
-#endif
-
 #define SIO_CONFIG_RA	0x398
 #define SIO_CONFIG_RD	0x399
 
@@ -107,12 +104,6 @@ extern bool isa_io_special;
  *
  */
 
-#ifdef CONFIG_PPC64
-#define IO_SET_SYNC_FLAG()	do { local_paca->io_sync = 1; } while(0)
-#else
-#define IO_SET_SYNC_FLAG()
-#endif
-
 #define DEF_MMIO_IN_X(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
 {									\
@@ -127,7 +118,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn" %1,%y0"			\
 		: "=Z" (*addr) : "r" (val) : "memory");			\
-	IO_SET_SYNC_FLAG();						\
+	mmiowb_set_pending();						\
 }
 
 #define DEF_MMIO_IN_D(name, size, insn)				\
@@ -144,7 +135,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0"			\
 		: "=m" (*addr) : "r" (val) : "memory");			\
-	IO_SET_SYNC_FLAG();						\
+	mmiowb_set_pending();						\
 }
 
 DEF_MMIO_IN_D(in_8,     8, lbz);
@@ -652,24 +643,6 @@ static inline void name at					\
 
 #include <asm-generic/iomap.h>
 
-#ifdef CONFIG_PPC32
-#define mmiowb()
-#else
-/*
- * Enforce synchronisation of stores vs. spin_unlock
- * (this does it explicitly, though our implementation of spin_unlock
- * does it implicitely too)
- */
-static inline void mmiowb(void)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__("sync; li %0,0; stb %0,%1(13)"
-	: "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
-	: "memory");
-}
-#endif /* !CONFIG_PPC32 */
-
 static inline void iosync(void)
 {
         __asm__ __volatile__ ("sync" : : : "memory");
diff --git a/arch/powerpc/include/asm/mmiowb.h b/arch/powerpc/include/asm/mmiowb.h
new file mode 100644
index 000000000000..74a00127eb20
--- /dev/null
+++ b/arch/powerpc/include/asm/mmiowb.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_MMIOWB_H
+#define _ASM_POWERPC_MMIOWB_H
+
+#ifdef CONFIG_MMIOWB
+
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <asm/paca.h>
+
+#define arch_mmiowb_state()	(&local_paca->mmiowb_state)
+#define mmiowb()		mb()
+
+#endif /* CONFIG_MMIOWB */
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_POWERPC_MMIOWB_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index e843bc5d1a0f..134e912d403f 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -34,6 +34,8 @@
 #include <asm/cpuidle.h>
 #include <asm/atomic.h>
 
+#include <asm-generic/mmiowb_types.h>
+
 register struct paca_struct *local_paca asm("r13");
 
 #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
@@ -171,7 +173,6 @@ struct paca_struct {
 	u16 trap_save;			/* Used when bad stack is encountered */
 	u8 irq_soft_mask;		/* mask for irq soft masking */
 	u8 irq_happened;		/* irq happened while soft-disabled */
-	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -264,6 +265,9 @@ struct paca_struct {
 #ifdef CONFIG_STACKPROTECTOR
 	unsigned long canary;
 #endif
+#ifdef CONFIG_MMIOWB
+	struct mmiowb_state mmiowb_state;
+#endif
 } ____cacheline_aligned;
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 685c72310f5d..15b39c407c4e 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -39,19 +39,6 @@
 #define LOCK_TOKEN	1
 #endif
 
-#if defined(CONFIG_PPC64) && defined(CONFIG_SMP)
-#define CLEAR_IO_SYNC	(get_paca()->io_sync = 0)
-#define SYNC_IO		do {						\
-				if (unlikely(get_paca()->io_sync)) {	\
-					mb();				\
-					get_paca()->io_sync = 0;	\
-				}					\
-			} while (0)
-#else
-#define CLEAR_IO_SYNC
-#define SYNC_IO
-#endif
-
 #ifdef CONFIG_PPC_PSERIES
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
@@ -99,7 +86,6 @@ static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	CLEAR_IO_SYNC;
 	return __arch_spin_trylock(lock) == 0;
 }
 
@@ -130,7 +116,6 @@ extern void __rw_yield(arch_rwlock_t *lock);
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	CLEAR_IO_SYNC;
 	while (1) {
 		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
@@ -148,7 +133,6 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 {
 	unsigned long flags_dis;
 
-	CLEAR_IO_SYNC;
 	while (1) {
 		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
@@ -167,7 +151,6 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	SYNC_IO;
 	__asm__ __volatile__("# arch_spin_unlock\n\t"
 				PPC_RELEASE_BARRIER: : :"memory");
 	lock->slock = 0;
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index e24c67d5ba75..34fba1ce27f7 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -27,8 +27,8 @@
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 #define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
 
+#define tlb_flush tlb_flush
 extern void tlb_flush(struct mmu_gather *tlb);
 
 /* Get the generic bits... */
@@ -46,22 +46,6 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
 #endif
 }
 
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-	if (!tlb->page_size)
-		tlb->page_size = page_size;
-	else if (tlb->page_size != page_size) {
-		if (!tlb->fullmm)
-			tlb_flush_mmu(tlb);
-		/*
-		 * update the page size after flush for the new
-		 * mmu_gather.
-		 */
-		tlb->page_size = page_size;
-	}
-}
-
 #ifdef CONFIG_SMP
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index b33bafb8fcea..70568ccbd9fd 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -57,7 +57,7 @@ void setup_barrier_nospec(void)
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
 		 security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);
 
-	if (!no_nospec)
+	if (!no_nospec && !cpu_mitigations_off())
 		enable_barrier_nospec(enable);
 }
 
@@ -116,7 +116,7 @@ static int __init handle_nospectre_v2(char *p)
 early_param("nospectre_v2", handle_nospectre_v2);
 void setup_spectre_v2(void)
 {
-	if (no_spectrev2)
+	if (no_spectrev2 || cpu_mitigations_off())
 		do_btb_flush_fixups();
 	else
 		btb_flush_enabled = true;
@@ -300,7 +300,7 @@ void setup_stf_barrier(void)
 
 	stf_enabled_flush_types = type;
 
-	if (!no_stf_barrier)
+	if (!no_stf_barrier && !cpu_mitigations_off())
 		stf_barrier_enable(enable);
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index ba404dd9ce1d..4f49e1a3594c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -932,7 +932,7 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable)
 
 	enabled_flush_types = types;
 
-	if (!no_rfi_flush)
+	if (!no_rfi_flush && !cpu_mitigations_off())
 		rfi_flush_enable(enable);
 }
 
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index f02b04973710..f100e331e69b 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	ret = kvmppc_tce_validate(stt, tce);
 	if (ret != H_SUCCESS)
-		return ret;
+		goto unlock_exit;
 
 	dir = iommu_tce_direction(tce);
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-
 	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 06964350b97a..b2b29d4f9842 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3423,7 +3423,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
 	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
 
-	mtspr(SPRN_PSSCR, host_psscr);
+	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+	mtspr(SPRN_PSSCR, host_psscr |
+	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
 	mtspr(SPRN_HFSCR, host_hfscr);
 	mtspr(SPRN_CIABR, host_ciabr);
 	mtspr(SPRN_DAWR, host_dawr);
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index f29d2f118b44..5d9c3ff728c9 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -98,10 +98,20 @@ static int find_free_bat(void)
 	return -1;
 }
 
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ *   is identified by the lowest bit set to 1 in the base address (for instance
+ *   if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ *   highest bit set to 1.
+ */
 static unsigned int block_size(unsigned long base, unsigned long top)
 {
 	unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
-	unsigned int base_shift = (fls(base) - 1) & 31;
+	unsigned int base_shift = (ffs(base) - 1) & 31;
 	unsigned int block_shift = (fls(top - base) - 1) & 31;
 
 	return min3(max_size, 1U << base_shift, 1U << block_shift);
@@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to
 
 unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
-	int done;
+	unsigned long done;
 	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
 
 	if (__map_without_bats) {
@@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 		return __mmu_mapin_ram(base, top);
 
 	done = __mmu_mapin_ram(base, border);
-	if (done != border - base)
+	if (done != border)
 		return done;
 
-	return done + __mmu_mapin_ram(border, top);
+	return __mmu_mapin_ram(border, top);
 }
 
 void mmu_mark_initmem_nx(void)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a0f44f992360..13c6a47e6150 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2429,7 +2429,10 @@ static void dump_one_paca(int cpu)
 	DUMP(p, trap_save, "%#-*x");
 	DUMP(p, irq_soft_mask, "%#-*x");
 	DUMP(p, irq_happened, "%#-*x");
-	DUMP(p, io_sync, "%#-*x");
+#ifdef CONFIG_MMIOWB
+	DUMP(p, mmiowb_state.nesting_count, "%#-*x");
+	DUMP(p, mmiowb_state.mmiowb_pending, "%#-*x");
+#endif
 	DUMP(p, irq_work_pending, "%#-*x");
 	DUMP(p, nap_state_lost, "%#-*x");
 	DUMP(p, sprg_vdso, "%#-*llx");
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index eb56c82d8aa1..e66745decea1 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -48,6 +48,7 @@ config RISCV
 	select RISCV_TIMER
 	select GENERIC_IRQ_MULTI_HANDLER
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_MMIOWB
 	select HAVE_EBPF_JIT if 64BIT
 
 config MMU
@@ -69,9 +70,6 @@ config STACKTRACE_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1d9c1376dc64..744fd92e77bc 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -20,6 +20,7 @@
 #define _ASM_RISCV_IO_H
 
 #include <linux/types.h>
+#include <asm/mmiowb.h>
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
@@ -100,18 +101,6 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
- * FIXME: I'm flip-flopping on whether or not we should keep this or enforce
- * the ordering with I/O on spinlocks like PowerPC does.  The worry is that
- * drivers won't get this correct, but I also don't want to introduce a fence
- * into the lock code that otherwise only uses AMOs (and is essentially defined
- * by the ISA to be correct).   For now I'm leaving this here: "o,w" is
- * sufficient to ensure that all writes to the device have completed before the
- * write to the spinlock is allowed to commit.  I surmised this from reading
- * "ACQUIRES VS I/O ACCESSES" in memory-barriers.txt.
- */
-#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
-
-/*
  * Unordered I/O memory access primitives.  These are even more relaxed than
  * the relaxed versions, as they don't even order accesses between successive
  * operations to the I/O regions.
@@ -165,7 +154,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #define __io_br()	do {} while (0)
 #define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory");
 #define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory");
-#define __io_aw()	do {} while (0)
+#define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
 #define readw(c)	({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(__v); __v; })
diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h
new file mode 100644
index 000000000000..5d7e3a2b4e3b
--- /dev/null
+++ b/arch/riscv/include/asm/mmiowb.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_MMIOWB_H
+#define _ASM_RISCV_MMIOWB_H
+
+/*
+ * "o,w" is sufficient to ensure that all writes to the device have completed
+ * before the write to the spinlock is allowed to commit.
+ */
+#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* ASM_RISCV_MMIOWB_H */
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 439dc7072e05..1ad8d093c58b 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -18,6 +18,7 @@ struct mmu_gather;
 
 static void tlb_flush(struct mmu_gather *tlb);
 
+#define tlb_flush tlb_flush
 #include <asm-generic/tlb.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index a4b1d94371a0..4d403274c2e8 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -169,8 +169,6 @@ static bool save_trace(unsigned long pc, void *arg)
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	walk_stackframe(tsk, NULL, save_trace, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b6e3d0653002..07485582d027 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -14,12 +14,6 @@ config LOCKDEP_SUPPORT
 config STACKTRACE_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config ARCH_HAS_ILOG2_U32
 	def_bool n
 
@@ -149,6 +143,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_GUP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
@@ -164,11 +159,13 @@ config S390
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MEMBLOCK_PHYS_MAP
+	select HAVE_MMU_GATHER_NO_GATHER
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NOP_MCOUNT
 	select HAVE_OPROFILE
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
+	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -188,7 +185,6 @@ config S390
 	select TTY
 	select VIRT_CPU_ACCOUNTING
 	select ARCH_HAS_SCALED_CPUTIME
-	select VIRT_TO_BUS
 	select HAVE_NMI
 
 
@@ -240,6 +236,7 @@ choice
 
 config MARCH_Z900
 	bool "IBM zSeries model z800 and z900"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z900_FEATURES
 	help
 	  Select this to enable optimizations for model z800/z900 (2064 and
@@ -248,6 +245,7 @@ config MARCH_Z900
 
 config MARCH_Z990
 	bool "IBM zSeries model z890 and z990"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z990_FEATURES
 	help
 	  Select this to enable optimizations for model z890/z990 (2084 and
@@ -256,6 +254,7 @@ config MARCH_Z990
 
 config MARCH_Z9_109
 	bool "IBM System z9"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z9_109_FEATURES
 	help
 	  Select this to enable optimizations for IBM System z9 (2094 and
@@ -347,12 +346,15 @@ config TUNE_DEFAULT
 
 config TUNE_Z900
 	bool "IBM zSeries model z800 and z900"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z990
 	bool "IBM zSeries model z890 and z990"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z9_109
 	bool "IBM System z9"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z10
 	bool "IBM System z10"
@@ -388,6 +390,9 @@ config COMPAT
 	  (and some other stuff like libraries and such) is needed for
 	  executing 31 bit applications.  It is safe to say "Y".
 
+config COMPAT_VDSO
+	def_bool COMPAT && !CC_IS_CLANG
+
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
@@ -549,6 +554,17 @@ config ARCH_HAS_KEXEC_PURGATORY
 	def_bool y
 	depends on KEXEC_FILE
 
+config KEXEC_VERIFY_SIG
+	bool "Verify kernel signature during kexec_file_load() syscall"
+	depends on KEXEC_FILE && SYSTEM_DATA_VERIFICATION
+	help
+	  This option makes kernel signature verification mandatory for
+	  the kexec_file_load() syscall.
+
+	  In addition to that option, you need to enable signature
+	  verification for the corresponding kernel image type being
+	  loaded in order for this to work.
+
 config ARCH_RANDOM
 	def_bool y
 	prompt "s390 architectural random number generation API"
@@ -609,6 +625,29 @@ config EXPOLINE_FULL
 
 endchoice
 
+config RELOCATABLE
+	bool "Build a relocatable kernel"
+	select MODULE_REL_CRCS if MODVERSIONS
+	default y
+	help
+	  This builds a kernel image that retains relocation information
+	  so it can be loaded at an arbitrary address.
+	  The kernel is linked as a position-independent executable (PIE)
+	  and contains dynamic relocations which are processed early in the
+	  bootup process.
+	  The relocations make the kernel image about 15% larger (compressed
+	  10%), but are discarded at runtime.
+
+config RANDOMIZE_BASE
+	bool "Randomize the address of the kernel image (KASLR)"
+	depends on RELOCATABLE
+	default y
+	help
+	  In support of Kernel Address Space Layout Randomization (KASLR),
+	  this randomizes the address at which the kernel image is loaded,
+	  as a security feature that deters exploit attempts relying on
+	  knowledge of the location of kernel internals.
+
 endmenu
 
 menu "Memory setup"
@@ -837,6 +876,17 @@ config HAVE_PNETID
 
 menu "Virtualization"
 
+config PROTECTED_VIRTUALIZATION_GUEST
+	def_bool n
+	prompt "Protected virtualization guest support"
+	help
+	  Select this option, if you want to be able to run this
+	  kernel as a protected virtualization KVM guest.
+	  Protected virtualization capable machines have a mini hypervisor
+	  located at machine level (an ultravisor). With help of the
+	  Ultravisor, KVM will be able to run "protected" VMs, special
+	  VMs whose memory and management data are unavailable to KVM.
+
 config PFAULT
 	def_bool y
 	prompt "Pseudo page fault support"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index e21053e5e0da..df1d6a150f30 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -16,10 +16,14 @@ KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
+ifeq ($(CONFIG_RELOCATABLE),y)
+KBUILD_CFLAGS	+= -fPIE
+LDFLAGS_vmlinux	:= -pie
+endif
 aflags_dwarf	:= -Wa,-gdwarf-2
-KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
 KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
-KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
@@ -111,7 +115,7 @@ endif
 cfi := $(call as-instr,.cfi_startproc\n.cfi_val_offset 15$(comma)-160\n.cfi_endproc,-DCONFIG_AS_CFI_VAL_OFFSET=1)
 
 KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
-KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
+KBUILD_CFLAGS	+= -pipe -Wno-sign-compare
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables $(cfi)
 KBUILD_AFLAGS	+= $(aflags-y) $(cfi)
 export KBUILD_AFLAGS_DECOMPRESSOR
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index c844eaf24ed7..c51496bbac19 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -12,25 +12,35 @@ KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
 #
-# Use -march=z900 for als.c to be able to print an error
+# Use minimum architecture for als.c to be able to print an error
 # message if the kernel is started on a machine which is too old
 #
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
+ifndef CONFIG_CC_IS_CLANG
+CC_FLAGS_MARCH_MINIMUM := -march=z900
+else
+CC_FLAGS_MARCH_MINIMUM := -march=z10
+endif
+
+ifneq ($(CC_FLAGS_MARCH),$(CC_FLAGS_MARCH_MINIMUM))
 AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o			+= -march=z900
+AFLAGS_head.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 AFLAGS_REMOVE_mem.o		+= $(CC_FLAGS_MARCH)
-AFLAGS_mem.o			+= -march=z900
+AFLAGS_mem.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
-CFLAGS_als.o			+= -march=z900
+CFLAGS_als.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o	+= -march=z900
+CFLAGS_sclp_early_core.o	+= $(CC_FLAGS_MARCH_MINIMUM)
 endif
 
 CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
-obj-y	:= head.o als.o startup.o mem_detect.o ipl_parm.o string.o ebcdic.o
-obj-y	+= sclp_early_core.o mem.o ipl_vmparm.o cmdline.o ctype.o
-targets	:= bzImage startup.a section_cmp.boot.data $(obj-y)
+obj-y	:= head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
+obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
+obj-y	+= ctype.o text_dma.o
+obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST)	+= uv.o
+obj-$(CONFIG_RELOCATABLE)	+= machine_kexec_reloc.o
+obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
+targets	:= bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y)
 subdir-	:= compressed
 
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
@@ -48,7 +58,8 @@ define cmd_section_cmp
 	touch $@
 endef
 
-$(obj)/bzImage: $(obj)/compressed/vmlinux $(obj)/section_cmp.boot.data FORCE
+OBJCOPYFLAGS_bzImage := --pad-to $$(readelf -s $(obj)/compressed/vmlinux | awk '/\<_end\>/ {print or(strtonum("0x"$$2),4095)+1}')
+$(obj)/bzImage: $(obj)/compressed/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.boot.preserved.data FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/section_cmp%: vmlinux $(obj)/compressed/vmlinux FORCE
diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c
index f902215e9cd9..ff6801d401c4 100644
--- a/arch/s390/boot/als.c
+++ b/arch/s390/boot/als.c
@@ -99,7 +99,7 @@ static void facility_mismatch(void)
 	print_machine_type();
 	print_missing_facilities();
 	sclp_early_printk("See Principles of Operations for facility bits\n");
-	disabled_wait(0x8badcccc);
+	disabled_wait();
 }
 
 void verify_facilities(void)
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 82bc06346e05..ad57c2205a71 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -9,5 +9,10 @@ void setup_boot_command_line(void);
 void parse_boot_command_line(void);
 void setup_memory_end(void);
 void print_missing_facilities(void);
+unsigned long get_random_base(unsigned long safe_addr);
+
+extern int kaslr_enabled;
+
+unsigned long read_ipl_report(unsigned long safe_offset);
 
 #endif /* BOOT_BOOT_H */
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
index e1c1f2ec60f4..c15eb7114d83 100644
--- a/arch/s390/boot/compressed/decompressor.h
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -17,6 +17,11 @@ struct vmlinux_info {
 	unsigned long bss_size;		/* uncompressed image .bss size */
 	unsigned long bootdata_off;
 	unsigned long bootdata_size;
+	unsigned long bootdata_preserved_off;
+	unsigned long bootdata_preserved_size;
+	unsigned long dynsym_start;
+	unsigned long rela_dyn_start;
+	unsigned long rela_dyn_end;
 };
 
 extern char _vmlinux_info[];
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index 7efc3938f595..112b8d9f1e4c 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -33,7 +33,29 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	/*
+	* .dma section for code, data, ex_table that need to stay below 2 GB,
+	* even when the kernel is relocate: above 2 GB.
+	*/
+	_sdma = .;
+	.dma.text : {
+		. = ALIGN(PAGE_SIZE);
+		_stext_dma = .;
+		*(.dma.text)
+		. = ALIGN(PAGE_SIZE);
+		_etext_dma = .;
+	}
+	. = ALIGN(16);
+	.dma.ex_table : {
+		_start_dma_ex_table = .;
+		KEEP(*(.dma.ex_table))
+		_stop_dma_ex_table = .;
+	}
+	.dma.data : { *(.dma.data) }
+	_edma = .;
+
 	BOOT_DATA
+	BOOT_DATA_PRESERVED
 
 	/*
 	 * uncompressed image info used by the decompressor it should match
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index ce2cbbc41742..028aab03a9e7 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -305,7 +305,7 @@ ENTRY(startup_kdump)
 	xc	0x300(256),0x300
 	xc	0xe00(256),0xe00
 	xc	0xf00(256),0xf00
-	lctlg	%c0,%c15,0x200(%r0)	# initialize control registers
+	lctlg	%c0,%c15,.Lctl-.LPG0(%r13)	# load control registers
 	stcke	__LC_BOOT_CLOCK
 	mvc	__LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
 	spt	6f-.LPG0(%r13)
@@ -319,20 +319,54 @@ ENTRY(startup_kdump)
 	.align	8
 6:	.long	0x7fffffff,0xffffffff
 
+.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
+	.quad	0			# cr1: primary space segment table
+	.quad	.Lduct			# cr2: dispatchable unit control table
+	.quad	0			# cr3: instruction authorization
+	.quad	0xffff			# cr4: instruction authorization
+	.quad	.Lduct			# cr5: primary-aste origin
+	.quad	0			# cr6:	I/O interrupts
+	.quad	0			# cr7:	secondary space segment table
+	.quad	0			# cr8:	access registers translation
+	.quad	0			# cr9:	tracing off
+	.quad	0			# cr10: tracing off
+	.quad	0			# cr11: tracing off
+	.quad	0			# cr12: tracing off
+	.quad	0			# cr13: home space segment table
+	.quad	0xc0000000		# cr14: machine check handling off
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
+
+	.section .dma.data,"aw",@progbits
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
+	.long	0,0,0,0,0,0,0,0
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
+	.align 64
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
+	.align	128
+.Lduald:.rept	8
+	.long	0x80000000,0,0,0	# invalid access-list entries
+	.endr
+	.previous
+
 #include "head_kdump.S"
 
 #
 # params at 10400 (setup.h)
+# Must be keept in sync with struct parmarea in setup.h
 #
 	.org	PARMAREA
-	.long	0,0			# IPL_DEVICE
-	.long	0,0			# INITRD_START
-	.long	0,0			# INITRD_SIZE
-	.long	0,0			# OLDMEM_BASE
-	.long	0,0			# OLDMEM_SIZE
+	.quad	0			# IPL_DEVICE
+	.quad	0			# INITRD_START
+	.quad	0			# INITRD_SIZE
+	.quad	0			# OLDMEM_BASE
+	.quad	0			# OLDMEM_SIZE
 
 	.org	COMMAND_LINE
 	.byte	"root=/dev/ram0 ro"
 	.byte	0
 
-	.org	0x11000
+	.org	EARLY_SCCB_OFFSET
+	.fill	4096
+
+	.org	HEAD_END
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 36beb56de021..3c49bde8aa5e 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -7,16 +7,19 @@
 #include <asm/sections.h>
 #include <asm/boot_data.h>
 #include <asm/facility.h>
+#include <asm/uv.h>
 #include "boot.h"
 
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
-struct ipl_parameter_block __bootdata(early_ipl_block);
-int __bootdata(early_ipl_block_valid);
+struct ipl_parameter_block __bootdata_preserved(ipl_block);
+int __bootdata_preserved(ipl_block_valid);
 
 unsigned long __bootdata(memory_end);
 int __bootdata(memory_end_set);
 int __bootdata(noexec_disabled);
 
+int kaslr_enabled __section(.data);
+
 static inline int __diag308(unsigned long subcode, void *addr)
 {
 	register unsigned long _addr asm("0") = (unsigned long)addr;
@@ -45,13 +48,15 @@ void store_ipl_parmblock(void)
 {
 	int rc;
 
-	rc = __diag308(DIAG308_STORE, &early_ipl_block);
+	uv_set_shared(__pa(&ipl_block));
+	rc = __diag308(DIAG308_STORE, &ipl_block);
+	uv_remove_shared(__pa(&ipl_block));
 	if (rc == DIAG308_RC_OK &&
-	    early_ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
-		early_ipl_block_valid = 1;
+	    ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
+		ipl_block_valid = 1;
 }
 
-static size_t scpdata_length(const char *buf, size_t count)
+static size_t scpdata_length(const u8 *buf, size_t count)
 {
 	while (count) {
 		if (buf[count - 1] != '\0' && buf[count - 1] != ' ')
@@ -68,26 +73,26 @@ static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size,
 	size_t i;
 	int has_lowercase;
 
-	count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data,
-					     ipb->ipl_info.fcp.scp_data_len));
+	count = min(size - 1, scpdata_length(ipb->fcp.scp_data,
+					     ipb->fcp.scp_data_len));
 	if (!count)
 		goto out;
 
 	has_lowercase = 0;
 	for (i = 0; i < count; i++) {
-		if (!isascii(ipb->ipl_info.fcp.scp_data[i])) {
+		if (!isascii(ipb->fcp.scp_data[i])) {
 			count = 0;
 			goto out;
 		}
-		if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i]))
+		if (!has_lowercase && islower(ipb->fcp.scp_data[i]))
 			has_lowercase = 1;
 	}
 
 	if (has_lowercase)
-		memcpy(dest, ipb->ipl_info.fcp.scp_data, count);
+		memcpy(dest, ipb->fcp.scp_data, count);
 	else
 		for (i = 0; i < count; i++)
-			dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]);
+			dest[i] = tolower(ipb->fcp.scp_data[i]);
 out:
 	dest[count] = '\0';
 	return count;
@@ -103,14 +108,14 @@ static void append_ipl_block_parm(void)
 	delim = early_command_line + len;    /* '\0' character position */
 	parm = early_command_line + len + 1; /* append right after '\0' */
 
-	switch (early_ipl_block.hdr.pbt) {
-	case DIAG308_IPL_TYPE_CCW:
+	switch (ipl_block.pb0_hdr.pbt) {
+	case IPL_PBT_CCW:
 		rc = ipl_block_get_ascii_vmparm(
-			parm, COMMAND_LINE_SIZE - len - 1, &early_ipl_block);
+			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
-	case DIAG308_IPL_TYPE_FCP:
+	case IPL_PBT_FCP:
 		rc = ipl_block_get_ascii_scpdata(
-			parm, COMMAND_LINE_SIZE - len - 1, &early_ipl_block);
+			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
 	}
 	if (rc) {
@@ -141,7 +146,7 @@ void setup_boot_command_line(void)
 	strcpy(early_command_line, strim(COMMAND_LINE));
 
 	/* append IPL PARM data to the boot command line */
-	if (early_ipl_block_valid)
+	if (!is_prot_virt_guest() && ipl_block_valid)
 		append_ipl_block_parm();
 }
 
@@ -211,6 +216,7 @@ void parse_boot_command_line(void)
 	char *args;
 	int rc;
 
+	kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE);
 	args = strcpy(command_line_buf, early_command_line);
 	while (*args) {
 		args = next_arg(args, &param, &val);
@@ -228,15 +234,21 @@ void parse_boot_command_line(void)
 
 		if (!strcmp(param, "facilities"))
 			modify_fac_list(val);
+
+		if (!strcmp(param, "nokaslr"))
+			kaslr_enabled = 0;
 	}
 }
 
 void setup_memory_end(void)
 {
 #ifdef CONFIG_CRASH_DUMP
-	if (!OLDMEM_BASE && early_ipl_block_valid &&
-	    early_ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP &&
-	    early_ipl_block.ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP) {
+	if (OLDMEM_BASE) {
+		kaslr_enabled = 0;
+	} else if (ipl_block_valid &&
+		   ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
+		   ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) {
+		kaslr_enabled = 0;
 		if (!sclp_early_get_hsa_size(&memory_end) && memory_end)
 			memory_end_set = 1;
 	}
diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c
new file mode 100644
index 000000000000..0b4965573656
--- /dev/null
+++ b/arch/s390/boot/ipl_report.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/ctype.h>
+#include <asm/ebcdic.h>
+#include <asm/sclp.h>
+#include <asm/sections.h>
+#include <asm/boot_data.h>
+#include <uapi/asm/ipl.h>
+#include "boot.h"
+
+int __bootdata_preserved(ipl_secure_flag);
+
+unsigned long __bootdata_preserved(ipl_cert_list_addr);
+unsigned long __bootdata_preserved(ipl_cert_list_size);
+
+unsigned long __bootdata(early_ipl_comp_list_addr);
+unsigned long __bootdata(early_ipl_comp_list_size);
+
+#define for_each_rb_entry(entry, rb) \
+	for (entry = rb->entries; \
+	     (void *) entry + sizeof(*entry) <= (void *) rb + rb->len; \
+	     entry++)
+
+static inline bool intersects(unsigned long addr0, unsigned long size0,
+			      unsigned long addr1, unsigned long size1)
+{
+	return addr0 + size0 > addr1 && addr1 + size1 > addr0;
+}
+
+static unsigned long find_bootdata_space(struct ipl_rb_components *comps,
+					 struct ipl_rb_certificates *certs,
+					 unsigned long safe_addr)
+{
+	struct ipl_rb_certificate_entry *cert;
+	struct ipl_rb_component_entry *comp;
+	size_t size;
+
+	/*
+	 * Find the length for the IPL report boot data
+	 */
+	early_ipl_comp_list_size = 0;
+	for_each_rb_entry(comp, comps)
+		early_ipl_comp_list_size += sizeof(*comp);
+	ipl_cert_list_size = 0;
+	for_each_rb_entry(cert, certs)
+		ipl_cert_list_size += sizeof(unsigned int) + cert->len;
+	size = ipl_cert_list_size + early_ipl_comp_list_size;
+
+	/*
+	 * Start from safe_addr to find a free memory area large
+	 * enough for the IPL report boot data. This area is used
+	 * for ipl_cert_list_addr/ipl_cert_list_size and
+	 * early_ipl_comp_list_addr/early_ipl_comp_list_size. It must
+	 * not overlap with any component or any certificate.
+	 */
+repeat:
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+	    intersects(INITRD_START, INITRD_SIZE, safe_addr, size))
+		safe_addr = INITRD_START + INITRD_SIZE;
+	for_each_rb_entry(comp, comps)
+		if (intersects(safe_addr, size, comp->addr, comp->len)) {
+			safe_addr = comp->addr + comp->len;
+			goto repeat;
+		}
+	for_each_rb_entry(cert, certs)
+		if (intersects(safe_addr, size, cert->addr, cert->len)) {
+			safe_addr = cert->addr + cert->len;
+			goto repeat;
+		}
+	early_ipl_comp_list_addr = safe_addr;
+	ipl_cert_list_addr = safe_addr + early_ipl_comp_list_size;
+
+	return safe_addr + size;
+}
+
+static void copy_components_bootdata(struct ipl_rb_components *comps)
+{
+	struct ipl_rb_component_entry *comp, *ptr;
+
+	ptr = (struct ipl_rb_component_entry *) early_ipl_comp_list_addr;
+	for_each_rb_entry(comp, comps)
+		memcpy(ptr++, comp, sizeof(*ptr));
+}
+
+static void copy_certificates_bootdata(struct ipl_rb_certificates *certs)
+{
+	struct ipl_rb_certificate_entry *cert;
+	void *ptr;
+
+	ptr = (void *) ipl_cert_list_addr;
+	for_each_rb_entry(cert, certs) {
+		*(unsigned int *) ptr = cert->len;
+		ptr += sizeof(unsigned int);
+		memcpy(ptr, (void *) cert->addr, cert->len);
+		ptr += cert->len;
+	}
+}
+
+unsigned long read_ipl_report(unsigned long safe_addr)
+{
+	struct ipl_rb_certificates *certs;
+	struct ipl_rb_components *comps;
+	struct ipl_pl_hdr *pl_hdr;
+	struct ipl_rl_hdr *rl_hdr;
+	struct ipl_rb_hdr *rb_hdr;
+	unsigned long tmp;
+	void *rl_end;
+
+	/*
+	 * Check if there is a IPL report by looking at the copy
+	 * of the IPL parameter information block.
+	 */
+	if (!ipl_block_valid ||
+	    !(ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR))
+		return safe_addr;
+	ipl_secure_flag = !!(ipl_block.hdr.flags & IPL_PL_FLAG_SIPL);
+	/*
+	 * There is an IPL report, to find it load the pointer to the
+	 * IPL parameter information block from lowcore and skip past
+	 * the IPL parameter list, then align the address to a double
+	 * word boundary.
+	 */
+	tmp = (unsigned long) S390_lowcore.ipl_parmblock_ptr;
+	pl_hdr = (struct ipl_pl_hdr *) tmp;
+	tmp = (tmp + pl_hdr->len + 7) & -8UL;
+	rl_hdr = (struct ipl_rl_hdr *) tmp;
+	/* Walk through the IPL report blocks in the IPL Report list */
+	certs = NULL;
+	comps = NULL;
+	rl_end = (void *) rl_hdr + rl_hdr->len;
+	rb_hdr = (void *) rl_hdr + sizeof(*rl_hdr);
+	while ((void *) rb_hdr + sizeof(*rb_hdr) < rl_end &&
+	       (void *) rb_hdr + rb_hdr->len <= rl_end) {
+
+		switch (rb_hdr->rbt) {
+		case IPL_RBT_CERTIFICATES:
+			certs = (struct ipl_rb_certificates *) rb_hdr;
+			break;
+		case IPL_RBT_COMPONENTS:
+			comps = (struct ipl_rb_components *) rb_hdr;
+			break;
+		default:
+			break;
+		}
+
+		rb_hdr = (void *) rb_hdr + rb_hdr->len;
+	}
+
+	/*
+	 * With either the component list or the certificate list
+	 * missing the kernel will stay ignorant of secure IPL.
+	 */
+	if (!comps || !certs)
+		return safe_addr;
+
+	/*
+	 * Copy component and certificate list to a safe area
+	 * where the decompressed kernel can find them.
+	 */
+	safe_addr = find_bootdata_space(comps, certs, safe_addr);
+	copy_components_bootdata(comps);
+	copy_certificates_bootdata(certs);
+
+	return safe_addr;
+}
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
new file mode 100644
index 000000000000..3bdd8132e56b
--- /dev/null
+++ b/arch/s390/boot/kaslr.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2019
+ */
+#include <asm/mem_detect.h>
+#include <asm/cpacf.h>
+#include <asm/timex.h>
+#include <asm/sclp.h>
+#include "compressed/decompressor.h"
+
+#define PRNG_MODE_TDES	 1
+#define PRNG_MODE_SHA512 2
+#define PRNG_MODE_TRNG	 3
+
+struct prno_parm {
+	u32 res;
+	u32 reseed_counter;
+	u64 stream_bytes;
+	u8  V[112];
+	u8  C[112];
+};
+
+struct prng_parm {
+	u8  parm_block[32];
+	u32 reseed_counter;
+	u64 byte_counter;
+};
+
+static int check_prng(void)
+{
+	if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) {
+		sclp_early_printk("KASLR disabled: CPU has no PRNG\n");
+		return 0;
+	}
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		return PRNG_MODE_TRNG;
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN))
+		return PRNG_MODE_SHA512;
+	else
+		return PRNG_MODE_TDES;
+}
+
+static unsigned long get_random(unsigned long limit)
+{
+	struct prng_parm prng = {
+		/* initial parameter block for tdes mode, copied from libica */
+		.parm_block = {
+			0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52,
+			0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4,
+			0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF,
+			0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0
+		},
+	};
+	unsigned long seed, random;
+	struct prno_parm prno;
+	__u64 entropy[4];
+	int mode, i;
+
+	mode = check_prng();
+	seed = get_tod_clock_fast();
+	switch (mode) {
+	case PRNG_MODE_TRNG:
+		cpacf_trng(NULL, 0, (u8 *) &random, sizeof(random));
+		break;
+	case PRNG_MODE_SHA512:
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED, &prno, NULL, 0,
+			   (u8 *) &seed, sizeof(seed));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, &prno, (u8 *) &random,
+			   sizeof(random), NULL, 0);
+		break;
+	case PRNG_MODE_TDES:
+		/* add entropy */
+		*(unsigned long *) prng.parm_block ^= seed;
+		for (i = 0; i < 16; i++) {
+			cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
+				  (char *) entropy, (char *) entropy,
+				  sizeof(entropy));
+			memcpy(prng.parm_block, entropy, sizeof(entropy));
+		}
+		random = seed;
+		cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, (u8 *) &random,
+			  (u8 *) &random, sizeof(random));
+		break;
+	default:
+		random = 0;
+	}
+	return random % limit;
+}
+
+unsigned long get_random_base(unsigned long safe_addr)
+{
+	unsigned long base, start, end, kernel_size;
+	unsigned long block_sum, offset;
+	int i;
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
+		if (safe_addr < INITRD_START + INITRD_SIZE)
+			safe_addr = INITRD_START + INITRD_SIZE;
+	}
+	safe_addr = ALIGN(safe_addr, THREAD_SIZE);
+
+	kernel_size = vmlinux.image_size + vmlinux.bss_size;
+	block_sum = 0;
+	for_each_mem_detect_block(i, &start, &end) {
+		if (memory_end_set) {
+			if (start >= memory_end)
+				break;
+			if (end > memory_end)
+				end = memory_end;
+		}
+		if (end - start < kernel_size)
+			continue;
+		block_sum += end - start - kernel_size;
+	}
+	if (!block_sum) {
+		sclp_early_printk("KASLR disabled: not enough memory\n");
+		return 0;
+	}
+
+	base = get_random(block_sum);
+	if (base == 0)
+		return 0;
+	if (base < safe_addr)
+		base = safe_addr;
+	block_sum = offset = 0;
+	for_each_mem_detect_block(i, &start, &end) {
+		if (memory_end_set) {
+			if (start >= memory_end)
+				break;
+			if (end > memory_end)
+				end = memory_end;
+		}
+		if (end - start < kernel_size)
+			continue;
+		block_sum += end - start - kernel_size;
+		if (base <= block_sum) {
+			base = start + base - offset;
+			base = ALIGN_DOWN(base, THREAD_SIZE);
+			break;
+		}
+		offset = block_sum;
+	}
+	return base;
+}
diff --git a/arch/s390/boot/machine_kexec_reloc.c b/arch/s390/boot/machine_kexec_reloc.c
new file mode 100644
index 000000000000..b7a5d0f72097
--- /dev/null
+++ b/arch/s390/boot/machine_kexec_reloc.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/machine_kexec_reloc.c"
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index bdfc5549a299..7b0d05414618 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -1,11 +1,55 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/string.h>
+#include <linux/elf.h>
+#include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/kexec.h>
 #include <asm/sclp.h>
+#include <asm/diag.h>
+#include <asm/uv.h>
 #include "compressed/decompressor.h"
 #include "boot.h"
 
 extern char __boot_data_start[], __boot_data_end[];
+extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+unsigned long __bootdata_preserved(__kaslr_offset);
+
+/*
+ * Some code and data needs to stay below 2 GB, even when the kernel would be
+ * relocated above 2 GB, because it has to use 31 bit addresses.
+ * Such code and data is part of the .dma section, and its location is passed
+ * over to the decompressed / relocated kernel via the .boot.preserved.data
+ * section.
+ */
+extern char _sdma[], _edma[];
+extern char _stext_dma[], _etext_dma[];
+extern struct exception_table_entry _start_dma_ex_table[];
+extern struct exception_table_entry _stop_dma_ex_table[];
+unsigned long __bootdata_preserved(__sdma) = __pa(&_sdma);
+unsigned long __bootdata_preserved(__edma) = __pa(&_edma);
+unsigned long __bootdata_preserved(__stext_dma) = __pa(&_stext_dma);
+unsigned long __bootdata_preserved(__etext_dma) = __pa(&_etext_dma);
+struct exception_table_entry *
+	__bootdata_preserved(__start_dma_ex_table) = _start_dma_ex_table;
+struct exception_table_entry *
+	__bootdata_preserved(__stop_dma_ex_table) = _stop_dma_ex_table;
+
+int _diag210_dma(struct diag210 *addr);
+int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode);
+int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode);
+void _diag0c_dma(struct hypfs_diag0c_entry *entry);
+void _diag308_reset_dma(void);
+struct diag_ops __bootdata_preserved(diag_dma_ops) = {
+	.diag210 = _diag210_dma,
+	.diag26c = _diag26c_dma,
+	.diag14 = _diag14_dma,
+	.diag0c = _diag0c_dma,
+	.diag308_reset = _diag308_reset_dma
+};
+static struct diag210 _diag210_tmp_dma __section(".dma.data");
+struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
+void _swsusp_reset_dma(void);
+unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma);
 
 void error(char *x)
 {
@@ -13,7 +57,7 @@ void error(char *x)
 	sclp_early_printk(x);
 	sclp_early_printk("\n\n -- System halted");
 
-	disabled_wait(0xdeadbeef);
+	disabled_wait();
 }
 
 #ifdef CONFIG_KERNEL_UNCOMPRESSED
@@ -23,19 +67,16 @@ unsigned long mem_safe_offset(void)
 }
 #endif
 
-static void rescue_initrd(void)
+static void rescue_initrd(unsigned long addr)
 {
-	unsigned long min_initrd_addr;
-
 	if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
 		return;
 	if (!INITRD_START || !INITRD_SIZE)
 		return;
-	min_initrd_addr = mem_safe_offset();
-	if (min_initrd_addr <= INITRD_START)
+	if (addr <= INITRD_START)
 		return;
-	memmove((void *)min_initrd_addr, (void *)INITRD_START, INITRD_SIZE);
-	INITRD_START = min_initrd_addr;
+	memmove((void *)addr, (void *)INITRD_START, INITRD_SIZE);
+	INITRD_START = addr;
 }
 
 static void copy_bootdata(void)
@@ -43,23 +84,81 @@ static void copy_bootdata(void)
 	if (__boot_data_end - __boot_data_start != vmlinux.bootdata_size)
 		error(".boot.data section size mismatch");
 	memcpy((void *)vmlinux.bootdata_off, __boot_data_start, vmlinux.bootdata_size);
+	if (__boot_data_preserved_end - __boot_data_preserved_start != vmlinux.bootdata_preserved_size)
+		error(".boot.preserved.data section size mismatch");
+	memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
+}
+
+static void handle_relocs(unsigned long offset)
+{
+	Elf64_Rela *rela_start, *rela_end, *rela;
+	int r_type, r_sym, rc;
+	Elf64_Addr loc, val;
+	Elf64_Sym *dynsym;
+
+	rela_start = (Elf64_Rela *) vmlinux.rela_dyn_start;
+	rela_end = (Elf64_Rela *) vmlinux.rela_dyn_end;
+	dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
+	for (rela = rela_start; rela < rela_end; rela++) {
+		loc = rela->r_offset + offset;
+		val = rela->r_addend + offset;
+		r_sym = ELF64_R_SYM(rela->r_info);
+		if (r_sym)
+			val += dynsym[r_sym].st_value;
+		r_type = ELF64_R_TYPE(rela->r_info);
+		rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
+		if (rc)
+			error("Unknown relocation type");
+	}
 }
 
 void startup_kernel(void)
 {
+	unsigned long random_lma;
+	unsigned long safe_addr;
 	void *img;
 
-	rescue_initrd();
-	sclp_early_read_info();
 	store_ipl_parmblock();
+	safe_addr = mem_safe_offset();
+	safe_addr = read_ipl_report(safe_addr);
+	uv_query_info();
+	rescue_initrd(safe_addr);
+	sclp_early_read_info();
 	setup_boot_command_line();
 	parse_boot_command_line();
 	setup_memory_end();
 	detect_memory();
+
+	random_lma = __kaslr_offset = 0;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
+		random_lma = get_random_base(safe_addr);
+		if (random_lma) {
+			__kaslr_offset = random_lma - vmlinux.default_lma;
+			img = (void *)vmlinux.default_lma;
+			vmlinux.default_lma += __kaslr_offset;
+			vmlinux.entry += __kaslr_offset;
+			vmlinux.bootdata_off += __kaslr_offset;
+			vmlinux.bootdata_preserved_off += __kaslr_offset;
+			vmlinux.rela_dyn_start += __kaslr_offset;
+			vmlinux.rela_dyn_end += __kaslr_offset;
+			vmlinux.dynsym_start += __kaslr_offset;
+		}
+	}
+
 	if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) {
 		img = decompress_kernel();
 		memmove((void *)vmlinux.default_lma, img, vmlinux.image_size);
-	}
+	} else if (__kaslr_offset)
+		memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size);
+
 	copy_bootdata();
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		handle_relocs(__kaslr_offset);
+
+	if (__kaslr_offset) {
+		/* Clear non-relocated kernel */
+		if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED))
+			memset(img, 0, vmlinux.image_size);
+	}
 	vmlinux.entry();
 }
diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S
new file mode 100644
index 000000000000..9715715c4c28
--- /dev/null
+++ b/arch/s390/boot/text_dma.S
@@ -0,0 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Code that needs to run below 2 GB.
+ *
+ * Copyright IBM Corp. 2019
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/sigp.h>
+
+#ifdef CC_USING_EXPOLINE
+	.pushsection .dma.text.__s390_indirect_jump_r14,"axG"
+__dma__s390_indirect_jump_r14:
+	larl	%r1,0f
+	ex	0,0(%r1)
+	j	.
+0:	br	%r14
+	.popsection
+#endif
+
+	.section .dma.text,"ax"
+/*
+ * Simplified version of expoline thunk. The normal thunks can not be used here,
+ * because they might be more than 2 GB away, and not reachable by the relative
+ * branch. No comdat, exrl, etc. optimizations used here, because it only
+ * affects a few functions that are not performance-relevant.
+ */
+	.macro BR_EX_DMA_r14
+#ifdef CC_USING_EXPOLINE
+	jg	__dma__s390_indirect_jump_r14
+#else
+	br	%r14
+#endif
+	.endm
+
+/*
+ * int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode)
+ */
+ENTRY(_diag14_dma)
+	lgr	%r1,%r2
+	lgr	%r2,%r3
+	lgr	%r3,%r4
+	lhi	%r5,-EIO
+	sam31
+	diag	%r1,%r2,0x14
+.Ldiag14_ex:
+	ipm	%r5
+	srl	%r5,28
+.Ldiag14_fault:
+	sam64
+	lgfr	%r2,%r5
+	BR_EX_DMA_r14
+	EX_TABLE_DMA(.Ldiag14_ex, .Ldiag14_fault)
+ENDPROC(_diag14_dma)
+
+/*
+ * int _diag210_dma(struct diag210 *addr)
+ */
+ENTRY(_diag210_dma)
+	lgr	%r1,%r2
+	lhi	%r2,-1
+	sam31
+	diag	%r1,%r0,0x210
+.Ldiag210_ex:
+	ipm	%r2
+	srl	%r2,28
+.Ldiag210_fault:
+	sam64
+	lgfr	%r2,%r2
+	BR_EX_DMA_r14
+	EX_TABLE_DMA(.Ldiag210_ex, .Ldiag210_fault)
+ENDPROC(_diag210_dma)
+
+/*
+ * int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode)
+ */
+ENTRY(_diag26c_dma)
+	lghi	%r5,-EOPNOTSUPP
+	sam31
+	diag	%r2,%r4,0x26c
+.Ldiag26c_ex:
+	sam64
+	lgfr	%r2,%r5
+	BR_EX_DMA_r14
+	EX_TABLE_DMA(.Ldiag26c_ex, .Ldiag26c_ex)
+ENDPROC(_diag26c_dma)
+
+/*
+ * void _diag0c_dma(struct hypfs_diag0c_entry *entry)
+ */
+ENTRY(_diag0c_dma)
+	sam31
+	diag	%r2,%r2,0x0c
+	sam64
+	BR_EX_DMA_r14
+ENDPROC(_diag0c_dma)
+
+/*
+ * void _swsusp_reset_dma(void)
+ */
+ENTRY(_swsusp_reset_dma)
+	larl	%r1,restart_entry
+	larl	%r2,.Lrestart_diag308_psw
+	og	%r1,0(%r2)
+	stg	%r1,0(%r0)
+	lghi	%r0,0
+	diag	%r0,%r0,0x308
+restart_entry:
+	lhi	%r1,1
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
+	sam64
+	BR_EX_DMA_r14
+ENDPROC(_swsusp_reset_dma)
+
+/*
+ * void _diag308_reset_dma(void)
+ *
+ * Calls diag 308 subcode 1 and continues execution
+ */
+ENTRY(_diag308_reset_dma)
+	larl	%r4,.Lctlregs		# Save control registers
+	stctg	%c0,%c15,0(%r4)
+	lg	%r2,0(%r4)		# Disable lowcore protection
+	nilh	%r2,0xefff
+	larl	%r4,.Lctlreg0
+	stg	%r2,0(%r4)
+	lctlg	%c0,%c0,0(%r4)
+	larl	%r4,.Lfpctl		# Floating point control register
+	stfpc	0(%r4)
+	larl	%r4,.Lprefix		# Save prefix register
+	stpx	0(%r4)
+	larl	%r4,.Lprefix_zero	# Set prefix register to 0
+	spx	0(%r4)
+	larl	%r4,.Lcontinue_psw	# Save PSW flags
+	epsw	%r2,%r3
+	stm	%r2,%r3,0(%r4)
+	larl	%r4,restart_part2	# Setup restart PSW at absolute 0
+	larl	%r3,.Lrestart_diag308_psw
+	og	%r4,0(%r3)		# Save PSW
+	lghi	%r3,0
+	sturg	%r4,%r3			# Use sturg, because of large pages
+	lghi	%r1,1
+	lghi	%r0,0
+	diag	%r0,%r1,0x308
+restart_part2:
+	lhi	%r0,0			# Load r0 with zero
+	lhi	%r1,2			# Use mode 2 = ESAME (dump)
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to ESAME mode
+	sam64				# Switch to 64 bit addressing mode
+	larl	%r4,.Lctlregs		# Restore control registers
+	lctlg	%c0,%c15,0(%r4)
+	larl	%r4,.Lfpctl		# Restore floating point ctl register
+	lfpc	0(%r4)
+	larl	%r4,.Lprefix		# Restore prefix register
+	spx	0(%r4)
+	larl	%r4,.Lcontinue_psw	# Restore PSW flags
+	lpswe	0(%r4)
+.Lcontinue:
+	BR_EX_DMA_r14
+ENDPROC(_diag308_reset_dma)
+
+	.section .dma.data,"aw",@progbits
+.align	8
+.Lrestart_diag308_psw:
+	.long	0x00080000,0x80000000
+
+.align 8
+.Lcontinue_psw:
+	.quad	0,.Lcontinue
+
+.align 8
+.Lctlreg0:
+	.quad	0
+.Lctlregs:
+	.rept	16
+	.quad	0
+	.endr
+.Lfpctl:
+	.long	0
+.Lprefix:
+	.long	0
+.Lprefix_zero:
+	.long	0
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
new file mode 100644
index 000000000000..ed007f4a6444
--- /dev/null
+++ b/arch/s390/boot/uv.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <asm/uv.h>
+#include <asm/facility.h>
+#include <asm/sections.h>
+
+int __bootdata_preserved(prot_virt_guest);
+
+void uv_query_info(void)
+{
+	struct uv_cb_qui uvcb = {
+		.header.cmd = UVC_CMD_QUI,
+		.header.len = sizeof(uvcb)
+	};
+
+	if (!test_facility(158))
+		return;
+
+	if (uv_call(0, (uint64_t)&uvcb))
+		return;
+
+	if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
+	    test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list))
+		prot_virt_guest = 1;
+}
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 9824c7bad9d4..b0920b35f87b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -64,6 +64,7 @@ CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 4fcbe5792744..09aa5cb14873 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -65,6 +65,7 @@ CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S
index 2bf01ba44107..0099044e2c86 100644
--- a/arch/s390/crypto/crc32be-vx.S
+++ b/arch/s390/crypto/crc32be-vx.S
@@ -207,5 +207,6 @@ ENTRY(crc32_be_vgfm_16)
 .Ldone:
 	VLGVF	%r2,%v2,3
 	BR_EX	%r14
+ENDPROC(crc32_be_vgfm_16)
 
 .previous
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S
index 7d6f568bd3ad..71caf0f4ec08 100644
--- a/arch/s390/crypto/crc32le-vx.S
+++ b/arch/s390/crypto/crc32le-vx.S
@@ -105,13 +105,14 @@
 ENTRY(crc32_le_vgfm_16)
 	larl	%r5,.Lconstants_CRC_32_LE
 	j	crc32_le_vgfm_generic
+ENDPROC(crc32_le_vgfm_16)
 
 ENTRY(crc32c_le_vgfm_16)
 	larl	%r5,.Lconstants_CRC_32C_LE
 	j	crc32_le_vgfm_generic
+ENDPROC(crc32c_le_vgfm_16)
 
-
-crc32_le_vgfm_generic:
+ENTRY(crc32_le_vgfm_generic)
 	/* Load CRC-32 constants */
 	VLM	CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5
 
@@ -267,5 +268,6 @@ crc32_le_vgfm_generic:
 .Ldone:
 	VLGVF	%r2,%v2,2
 	BR_EX	%r14
+ENDPROC(crc32_le_vgfm_generic)
 
 .previous
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index a97a1802cfb4..12cca467af7d 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -61,6 +61,7 @@ static unsigned int prng_reseed_limit;
 module_param_named(reseed_limit, prng_reseed_limit, int, 0);
 MODULE_PARM_DESC(prng_reseed_limit, "PRNG reseed limit");
 
+static bool trng_available;
 
 /*
  * Any one who considers arithmetical methods of producing random digits is,
@@ -115,46 +116,68 @@ static const u8 initial_parm_block[32] __initconst = {
 
 /*
  * generate_entropy:
- * This algorithm produces 64 bytes of entropy data based on 1024
- * individual stckf() invocations assuming that each stckf() value
- * contributes 0.25 bits of entropy. So the caller gets 256 bit
- * entropy per 64 byte or 4 bits entropy per byte.
+ * This function fills a given buffer with random bytes. The entropy within
+ * the random bytes given back is assumed to have at least 50% - meaning
+ * a 64 bytes buffer has at least 64 * 8 / 2 = 256 bits of entropy.
+ * Within the function the entropy generation is done in junks of 64 bytes.
+ * So the caller should also ask for buffer fill in multiples of 64 bytes.
+ * The generation of the entropy is based on the assumption that every stckf()
+ * invocation produces 0.5 bits of entropy. To accumulate 256 bits of entropy
+ * at least 512 stckf() values are needed. The entropy relevant part of the
+ * stckf value is bit 51 (counting starts at the left with bit nr 0) so
+ * here we use the lower 4 bytes and exor the values into 2k of bufferspace.
+ * To be on the save side, if there is ever a problem with stckf() the
+ * other half of the page buffer is filled with bytes from urandom via
+ * get_random_bytes(), so this function consumes 2k of urandom for each
+ * requested 64 bytes output data. Finally the buffer page is condensed into
+ * a 64 byte value by hashing with a SHA512 hash.
  */
 static int generate_entropy(u8 *ebuf, size_t nbytes)
 {
 	int n, ret = 0;
-	u8 *pg, *h, hash[64];
-
-	/* allocate 2 pages */
-	pg = (u8 *) __get_free_pages(GFP_KERNEL, 1);
+	u8 *pg, pblock[80] = {
+		/* 8 x 64 bit init values */
+		0x6A, 0x09, 0xE6, 0x67, 0xF3, 0xBC, 0xC9, 0x08,
+		0xBB, 0x67, 0xAE, 0x85, 0x84, 0xCA, 0xA7, 0x3B,
+		0x3C, 0x6E, 0xF3, 0x72, 0xFE, 0x94, 0xF8, 0x2B,
+		0xA5, 0x4F, 0xF5, 0x3A, 0x5F, 0x1D, 0x36, 0xF1,
+		0x51, 0x0E, 0x52, 0x7F, 0xAD, 0xE6, 0x82, 0xD1,
+		0x9B, 0x05, 0x68, 0x8C, 0x2B, 0x3E, 0x6C, 0x1F,
+		0x1F, 0x83, 0xD9, 0xAB, 0xFB, 0x41, 0xBD, 0x6B,
+		0x5B, 0xE0, 0xCD, 0x19, 0x13, 0x7E, 0x21, 0x79,
+		/* 128 bit counter total message bit length */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 };
+
+	/* allocate one page stckf buffer */
+	pg = (u8 *) __get_free_page(GFP_KERNEL);
 	if (!pg) {
 		prng_errorflag = PRNG_GEN_ENTROPY_FAILED;
 		return -ENOMEM;
 	}
 
+	/* fill the ebuf in chunks of 64 byte each */
 	while (nbytes) {
-		/* fill pages with urandom bytes */
-		get_random_bytes(pg, 2*PAGE_SIZE);
-		/* exor pages with 1024 stckf values */
-		for (n = 0; n < 2 * PAGE_SIZE / sizeof(u64); n++) {
-			u64 *p = ((u64 *)pg) + n;
+		/* fill lower 2k with urandom bytes */
+		get_random_bytes(pg, PAGE_SIZE / 2);
+		/* exor upper 2k with 512 stckf values, offset 4 bytes each */
+		for (n = 0; n < 512; n++) {
+			int offset = (PAGE_SIZE / 2) + (n * 4) - 4;
+			u64 *p = (u64 *)(pg + offset);
 			*p ^= get_tod_clock_fast();
 		}
-		n = (nbytes < sizeof(hash)) ? nbytes : sizeof(hash);
-		if (n < sizeof(hash))
-			h = hash;
-		else
-			h = ebuf;
-		/* hash over the filled pages */
-		cpacf_kimd(CPACF_KIMD_SHA_512, h, pg, 2*PAGE_SIZE);
-		if (n < sizeof(hash))
-			memcpy(ebuf, hash, n);
+		/* hash over the filled page */
+		cpacf_klmd(CPACF_KLMD_SHA_512, pblock, pg, PAGE_SIZE);
+		n = (nbytes < 64) ? nbytes : 64;
+		memcpy(ebuf, pblock, n);
 		ret += n;
 		ebuf += n;
 		nbytes -= n;
 	}
 
-	free_pages((unsigned long)pg, 1);
+	memzero_explicit(pblock, sizeof(pblock));
+	memzero_explicit(pg, PAGE_SIZE);
+	free_page((unsigned long)pg);
 	return ret;
 }
 
@@ -344,8 +367,8 @@ static int __init prng_sha512_selftest(void)
 
 static int __init prng_sha512_instantiate(void)
 {
-	int ret, datalen;
-	u8 seed[64 + 32 + 16];
+	int ret, datalen, seedlen;
+	u8 seed[128 + 16];
 
 	pr_debug("prng runs in SHA-512 mode "
 		 "with chunksize=%d and reseed_limit=%u\n",
@@ -368,16 +391,36 @@ static int __init prng_sha512_instantiate(void)
 	if (ret)
 		goto outfree;
 
-	/* generate initial seed bytestring, with 256 + 128 bits entropy */
-	ret = generate_entropy(seed, 64 + 32);
-	if (ret != 64 + 32)
-		goto outfree;
-	/* followed by 16 bytes of unique nonce */
-	get_tod_clock_ext(seed + 64 + 32);
+	/* generate initial seed, we need at least  256 + 128 bits entropy. */
+	if (trng_available) {
+		/*
+		 * Trng available, so use it. The trng works in chunks of
+		 * 32 bytes and produces 100% entropy. So we pull 64 bytes
+		 * which gives us 512 bits entropy.
+		 */
+		seedlen = 2 * 32;
+		cpacf_trng(NULL, 0, seed, seedlen);
+	} else {
+		/*
+		 * No trng available, so use the generate_entropy() function.
+		 * This function works in 64 byte junks and produces
+		 * 50% entropy. So we pull 2*64 bytes which gives us 512 bits
+		 * of entropy.
+		 */
+		seedlen = 2 * 64;
+		ret = generate_entropy(seed, seedlen);
+		if (ret != seedlen)
+			goto outfree;
+	}
+
+	/* append the seed by 16 bytes of unique nonce */
+	get_tod_clock_ext(seed + seedlen);
+	seedlen += 16;
 
-	/* initial seed of the prno drng */
+	/* now initial seed of the prno drng */
 	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-		   &prng_data->prnows, NULL, 0, seed, sizeof(seed));
+		   &prng_data->prnows, NULL, 0, seed, seedlen);
+	memzero_explicit(seed, sizeof(seed));
 
 	/* if fips mode is enabled, generate a first block of random
 	   bytes for the FIPS 140-2 Conditional Self Test */
@@ -405,17 +448,26 @@ static void prng_sha512_deinstantiate(void)
 
 static int prng_sha512_reseed(void)
 {
-	int ret;
+	int ret, seedlen;
 	u8 seed[64];
 
-	/* fetch 256 bits of fresh entropy */
-	ret = generate_entropy(seed, sizeof(seed));
-	if (ret != sizeof(seed))
-		return ret;
+	/* We need at least 256 bits of fresh entropy for reseeding */
+	if (trng_available) {
+		/* trng produces 256 bits entropy in 32 bytes */
+		seedlen = 32;
+		cpacf_trng(NULL, 0, seed, seedlen);
+	} else {
+		/* generate_entropy() produces 256 bits entropy in 64 bytes */
+		seedlen = 64;
+		ret = generate_entropy(seed, seedlen);
+		if (ret != sizeof(seed))
+			return ret;
+	}
 
 	/* do a reseed of the prno drng with this bytestring */
 	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-		   &prng_data->prnows, NULL, 0, seed, sizeof(seed));
+		   &prng_data->prnows, NULL, 0, seed, seedlen);
+	memzero_explicit(seed, sizeof(seed));
 
 	return 0;
 }
@@ -592,6 +644,7 @@ static ssize_t prng_sha512_read(struct file *file, char __user *ubuf,
 			ret = -EFAULT;
 			break;
 		}
+		memzero_explicit(p, n);
 		ubuf += n;
 		nbytes -= n;
 		ret += n;
@@ -773,6 +826,10 @@ static int __init prng_init(void)
 	if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG))
 		return -EOPNOTSUPP;
 
+	/* check if TRNG subfunction is available */
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		trng_available = true;
+
 	/* choose prng mode */
 	if (prng_mode != PRNG_MODE_TDES) {
 		/* check for MSA5 support for PRNO operations */
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 4d58a92b5d97..c59b922cb6c5 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -39,6 +39,7 @@ CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c
index 72e3140fafb5..3235e4d82f2d 100644
--- a/arch/s390/hypfs/hypfs_diag0c.c
+++ b/arch/s390/hypfs/hypfs_diag0c.c
@@ -16,26 +16,12 @@
 #define DBFS_D0C_HDR_VERSION 0
 
 /*
- * Execute diagnose 0c in 31 bit mode
- */
-static void diag0c(struct hypfs_diag0c_entry *entry)
-{
-	diag_stat_inc(DIAG_STAT_X00C);
-	asm volatile (
-		"	sam31\n"
-		"	diag	%0,%0,0x0c\n"
-		"	sam64\n"
-		: /* no output register */
-		: "a" (entry)
-		: "memory");
-}
-
-/*
  * Get hypfs_diag0c_entry from CPU vector and store diag0c data
  */
 static void diag0c_fn(void *data)
 {
-	diag0c(((void **) data)[smp_processor_id()]);
+	diag_stat_inc(DIAG_STAT_X00C);
+	diag_dma_ops.diag0c(((void **) data)[smp_processor_id()]);
 }
 
 /*
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 12d77cb11fe5..2531f673f099 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -20,7 +20,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += rwsem.h
+generic-y += mmiowb.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
 generic-y += word-at-a-time.h
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index fcf539efb32f..c10d2ee2dfda 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -14,7 +14,7 @@
 
 struct airq_struct {
 	struct hlist_node list;		/* Handler queueing. */
-	void (*handler)(struct airq_struct *);	/* Thin-interrupt handler */
+	void (*handler)(struct airq_struct *airq, bool floating);
 	u8 *lsi_ptr;			/* Local-Summary-Indicator pointer */
 	u8 lsi_mask;			/* Local-Summary-Indicator mask */
 	u8 isc;				/* Interrupt-subclass */
@@ -35,13 +35,15 @@ struct airq_iv {
 	unsigned int *data;	/* 32 bit value associated with each bit */
 	unsigned long bits;	/* Number of bits in the vector */
 	unsigned long end;	/* Number of highest allocated bit + 1 */
+	unsigned long flags;	/* Allocation flags */
 	spinlock_t lock;	/* Lock to protect alloc & free */
 };
 
-#define AIRQ_IV_ALLOC	1	/* Use an allocation bit mask */
-#define AIRQ_IV_BITLOCK	2	/* Allocate the lock bit mask */
-#define AIRQ_IV_PTR	4	/* Allocate the ptr array */
-#define AIRQ_IV_DATA	8	/* Allocate the data array */
+#define AIRQ_IV_ALLOC		1	/* Use an allocation bit mask */
+#define AIRQ_IV_BITLOCK		2	/* Allocate the lock bit mask */
+#define AIRQ_IV_PTR		4	/* Allocate the ptr array */
+#define AIRQ_IV_DATA		8	/* Allocate the data array */
+#define AIRQ_IV_CACHELINE	16	/* Cacheline alignment for the vector */
 
 struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
 void airq_iv_release(struct airq_iv *iv);
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index d1f8a4d94cca..9900d655014c 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -73,7 +73,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__atomic64_or(mask, addr);
+	__atomic64_or(mask, (long *)addr);
 }
 
 static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -94,7 +94,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	__atomic64_and(mask, addr);
+	__atomic64_and(mask, (long *)addr);
 }
 
 static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -115,7 +115,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__atomic64_xor(mask, addr);
+	__atomic64_xor(mask, (long *)addr);
 }
 
 static inline int
@@ -125,7 +125,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __atomic64_or_barrier(mask, addr);
+	old = __atomic64_or_barrier(mask, (long *)addr);
 	return (old & mask) != 0;
 }
 
@@ -136,7 +136,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	old = __atomic64_and_barrier(mask, addr);
+	old = __atomic64_and_barrier(mask, (long *)addr);
 	return (old & ~mask) != 0;
 }
 
@@ -147,7 +147,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __atomic64_xor_barrier(mask, addr);
+	old = __atomic64_xor_barrier(mask, (long *)addr);
 	return (old & mask) != 0;
 }
 
diff --git a/arch/s390/include/asm/boot_data.h b/arch/s390/include/asm/boot_data.h
index 2d999ccb977a..f7eed27b3220 100644
--- a/arch/s390/include/asm/boot_data.h
+++ b/arch/s390/include/asm/boot_data.h
@@ -5,7 +5,14 @@
 #include <asm/ipl.h>
 
 extern char early_command_line[COMMAND_LINE_SIZE];
-extern struct ipl_parameter_block early_ipl_block;
-extern int early_ipl_block_valid;
+extern struct ipl_parameter_block ipl_block;
+extern int ipl_block_valid;
+extern int ipl_secure_flag;
+
+extern unsigned long ipl_cert_list_addr;
+extern unsigned long ipl_cert_list_size;
+
+extern unsigned long early_ipl_comp_list_addr;
+extern unsigned long early_ipl_comp_list_size;
 
 #endif /* _ASM_S390_BOOT_DATA_H */
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 429f43a8a8e8..713fc9735ffb 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -15,7 +15,7 @@
 		".section .rodata.str,\"aMS\",@progbits,1\n"	\
 		"2:	.asciz	\""__FILE__"\"\n"		\
 		".previous\n"					\
-		".section __bug_table,\"aw\"\n"			\
+		".section __bug_table,\"awM\",@progbits,%2\n"	\
 		"3:	.long	1b-3b,2b-3b\n"			\
 		"	.short	%0,%1\n"			\
 		"	.org	3b+%2\n"			\
@@ -27,17 +27,17 @@
 
 #else /* CONFIG_DEBUG_BUGVERBOSE */
 
-#define __EMIT_BUG(x) do {				\
-	asm volatile(					\
-		"0:	j	0b+2\n"			\
-		"1:\n"					\
-		".section __bug_table,\"aw\"\n"		\
-		"2:	.long	1b-2b\n"		\
-		"	.short	%0\n"			\
-		"	.org	2b+%1\n"		\
-		".previous\n"				\
-		: : "i" (x),				\
-		    "i" (sizeof(struct bug_entry)));	\
+#define __EMIT_BUG(x) do {					\
+	asm volatile(						\
+		"0:	j	0b+2\n"				\
+		"1:\n"						\
+		".section __bug_table,\"awM\",@progbits,%1\n"	\
+		"2:	.long	1b-2b\n"			\
+		"	.short	%0\n"				\
+		"	.org	2b+%1\n"			\
+		".previous\n"					\
+		: : "i" (x),					\
+		    "i" (sizeof(struct bug_entry)));		\
 } while (0)
 
 #endif /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 19562be22b7e..0036eab14391 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -308,4 +308,17 @@ union diag318_info {
 int diag204(unsigned long subcode, unsigned long size, void *addr);
 int diag224(void *ptr);
 int diag26c(void *req, void *resp, enum diag26c_sc subcode);
+
+struct hypfs_diag0c_entry;
+
+struct diag_ops {
+	int (*diag210)(struct diag210 *addr);
+	int (*diag26c)(void *req, void *resp, enum diag26c_sc subcode);
+	int (*diag14)(unsigned long rx, unsigned long ry1, unsigned long subcode);
+	void (*diag0c)(struct hypfs_diag0c_entry *entry);
+	void (*diag308_reset)(void);
+};
+
+extern struct diag_ops diag_dma_ops;
+extern struct diag210 *__diag210_tmp_dma;
 #endif /* _ASM_S390_DIAG_H */
diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h
index 29441beb92e6..efb50fc6866c 100644
--- a/arch/s390/include/asm/ebcdic.h
+++ b/arch/s390/include/asm/ebcdic.h
@@ -20,7 +20,7 @@ extern __u8 _ebc_tolower[256]; /* EBCDIC -> lowercase */
 extern __u8 _ebc_toupper[256]; /* EBCDIC -> uppercase */
 
 static inline void
-codepage_convert(const __u8 *codepage, volatile __u8 * addr, unsigned long nr)
+codepage_convert(const __u8 *codepage, volatile char *addr, unsigned long nr)
 {
 	if (nr-- <= 0)
 		return;
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index f74639a05f0f..5775fc22f410 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -107,6 +107,10 @@
 #define HWCAP_S390_VXRS_BCD	4096
 #define HWCAP_S390_VXRS_EXT	8192
 #define HWCAP_S390_GS		16384
+#define HWCAP_S390_VXRS_EXT2	32768
+#define HWCAP_S390_VXRS_PDE	65536
+#define HWCAP_S390_SORT		131072
+#define HWCAP_S390_DFLT		262144
 
 /* Internal bits, not exposed via elf */
 #define HWCAP_INT_SIE		1UL
diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h
index 80a4e5a9cb46..ae27f756b409 100644
--- a/arch/s390/include/asm/extable.h
+++ b/arch/s390/include/asm/extable.h
@@ -19,6 +19,11 @@ struct exception_table_entry
 	int insn, fixup;
 };
 
+extern struct exception_table_entry *__start_dma_ex_table;
+extern struct exception_table_entry *__stop_dma_ex_table;
+
+const struct exception_table_entry *s390_search_extables(unsigned long addr);
+
 static inline unsigned long extable_fixup(const struct exception_table_entry *x)
 {
 	return (unsigned long)&x->fixup + x->fixup;
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 5a3c95b11952..68d362f8d6c1 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -11,9 +11,16 @@
 #define MCOUNT_RETURN_FIXUP	18
 #endif
 
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_CC_IS_CLANG
+/* https://bugs.llvm.org/show_bug.cgi?id=41424 */
+#define ftrace_return_address(n) 0UL
+#else
 #define ftrace_return_address(n) __builtin_return_address(n)
+#endif
 
 void _mcount(void);
 void ftrace_caller(void);
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index f34d729347e4..ca421614722f 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -30,14 +30,8 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 #define ioremap_wc			ioremap_nocache
 #define ioremap_wt			ioremap_nocache
 
-static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
-{
-	return (void __iomem *) offset;
-}
-
-static inline void iounmap(volatile void __iomem *addr)
-{
-}
+void __iomem *ioremap(unsigned long offset, unsigned long size);
+void iounmap(volatile void __iomem *addr);
 
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
@@ -57,14 +51,17 @@ static inline void ioport_unmap(void __iomem *p)
  * the corresponding device and create the mapping cookie.
  */
 #define pci_iomap pci_iomap
+#define pci_iomap_range pci_iomap_range
 #define pci_iounmap pci_iounmap
-#define pci_iomap_wc pci_iomap
-#define pci_iomap_wc_range pci_iomap_range
+#define pci_iomap_wc pci_iomap_wc
+#define pci_iomap_wc_range pci_iomap_wc_range
 
 #define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
 #define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)
 #define memset_io(dst, val, count)	zpci_memset_io(dst, val, count)
 
+#define mmiowb()	zpci_barrier()
+
 #define __raw_readb	zpci_read_u8
 #define __raw_readw	zpci_read_u16
 #define __raw_readl	zpci_read_u32
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index a8389e2d2f03..084e71b7272a 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -12,74 +12,36 @@
 #include <asm/types.h>
 #include <asm/cio.h>
 #include <asm/setup.h>
+#include <uapi/asm/ipl.h>
 
-#define NSS_NAME_SIZE	8
-
-#define IPL_PARM_BLK_FCP_LEN (sizeof(struct ipl_list_hdr) + \
-			      sizeof(struct ipl_block_fcp))
-
-#define IPL_PARM_BLK0_FCP_LEN (sizeof(struct ipl_block_fcp) + 16)
+struct ipl_parameter_block {
+	struct ipl_pl_hdr hdr;
+	union {
+		struct ipl_pb_hdr pb0_hdr;
+		struct ipl_pb0_common common;
+		struct ipl_pb0_fcp fcp;
+		struct ipl_pb0_ccw ccw;
+		char raw[PAGE_SIZE - sizeof(struct ipl_pl_hdr)];
+	};
+} __packed __aligned(PAGE_SIZE);
 
-#define IPL_PARM_BLK_CCW_LEN (sizeof(struct ipl_list_hdr) + \
-			      sizeof(struct ipl_block_ccw))
+#define NSS_NAME_SIZE 8
 
-#define IPL_PARM_BLK0_CCW_LEN (sizeof(struct ipl_block_ccw) + 16)
+#define IPL_BP_FCP_LEN (sizeof(struct ipl_pl_hdr) + \
+			      sizeof(struct ipl_pb0_fcp))
+#define IPL_BP0_FCP_LEN (sizeof(struct ipl_pb0_fcp))
+#define IPL_BP_CCW_LEN (sizeof(struct ipl_pl_hdr) + \
+			      sizeof(struct ipl_pb0_ccw))
+#define IPL_BP0_CCW_LEN (sizeof(struct ipl_pb0_ccw))
 
 #define IPL_MAX_SUPPORTED_VERSION (0)
 
-struct ipl_list_hdr {
-	u32 len;
-	u8  reserved1[3];
-	u8  version;
-	u32 blk0_len;
-	u8  pbt;
-	u8  flags;
-	u16 reserved2;
-	u8  loadparm[8];
-} __attribute__((packed));
-
-struct ipl_block_fcp {
-	u8  reserved1[305-1];
-	u8  opt;
-	u8  reserved2[3];
-	u16 reserved3;
-	u16 devno;
-	u8  reserved4[4];
-	u64 wwpn;
-	u64 lun;
-	u32 bootprog;
-	u8  reserved5[12];
-	u64 br_lba;
-	u32 scp_data_len;
-	u8  reserved6[260];
-	u8  scp_data[];
-} __attribute__((packed));
-
-#define DIAG308_VMPARM_SIZE	64
-#define DIAG308_SCPDATA_SIZE	(PAGE_SIZE - (sizeof(struct ipl_list_hdr) + \
-				 offsetof(struct ipl_block_fcp, scp_data)))
-
-struct ipl_block_ccw {
-	u8  reserved1[84];
-	u16 reserved2 : 13;
-	u8  ssid : 3;
-	u16 devno;
-	u8  vm_flags;
-	u8  reserved3[3];
-	u32 vm_parm_len;
-	u8  nss_name[8];
-	u8  vm_parm[DIAG308_VMPARM_SIZE];
-	u8  reserved4[8];
-} __attribute__((packed));
+#define IPL_RB_CERT_UNKNOWN ((unsigned short)-1)
 
-struct ipl_parameter_block {
-	struct ipl_list_hdr hdr;
-	union {
-		struct ipl_block_fcp fcp;
-		struct ipl_block_ccw ccw;
-		char raw[PAGE_SIZE - sizeof(struct ipl_list_hdr)];
-	} ipl_info;
-} __packed __aligned(PAGE_SIZE);
+#define DIAG308_VMPARM_SIZE (64)
+#define DIAG308_SCPDATA_OFFSET offsetof(struct ipl_parameter_block, \
+					fcp.scp_data)
+#define DIAG308_SCPDATA_SIZE (PAGE_SIZE - DIAG308_SCPDATA_OFFSET)
 
 struct save_area;
 struct save_area * __init save_area_alloc(bool is_boot_cpu);
@@ -88,7 +50,6 @@ void __init save_area_add_regs(struct save_area *, void *regs);
 void __init save_area_add_vxrs(struct save_area *, __vector128 *vxrs);
 
 extern void s390_reset_system(void);
-extern void ipl_store_parameters(void);
 extern size_t ipl_block_get_ascii_vmparm(char *dest, size_t size,
 					 const struct ipl_parameter_block *ipb);
 
@@ -122,6 +83,33 @@ extern struct ipl_info ipl_info;
 extern void setup_ipl(void);
 extern void set_os_info_reipl_block(void);
 
+struct ipl_report {
+	struct ipl_parameter_block *ipib;
+	struct list_head components;
+	struct list_head certificates;
+	size_t size;
+};
+
+struct ipl_report_component {
+	struct list_head list;
+	struct ipl_rb_component_entry entry;
+};
+
+struct ipl_report_certificate {
+	struct list_head list;
+	struct ipl_rb_certificate_entry entry;
+	void *key;
+};
+
+struct kexec_buf;
+struct ipl_report *ipl_report_init(struct ipl_parameter_block *ipib);
+void *ipl_report_finish(struct ipl_report *report);
+int ipl_report_free(struct ipl_report *report);
+int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf,
+			     unsigned char flags, unsigned short cert);
+int ipl_report_add_certificate(struct ipl_report *report, void *key,
+			       unsigned long addr, unsigned long len);
+
 /*
  * DIAG 308 support
  */
@@ -133,32 +121,12 @@ enum diag308_subcode  {
 	DIAG308_STORE = 6,
 };
 
-enum diag308_ipl_type {
-	DIAG308_IPL_TYPE_FCP	= 0,
-	DIAG308_IPL_TYPE_CCW	= 2,
-};
-
-enum diag308_opt {
-	DIAG308_IPL_OPT_IPL	= 0x10,
-	DIAG308_IPL_OPT_DUMP	= 0x20,
-};
-
-enum diag308_flags {
-	DIAG308_FLAGS_LP_VALID	= 0x80,
-};
-
-enum diag308_vm_flags {
-	DIAG308_VM_FLAGS_NSS_VALID	= 0x80,
-	DIAG308_VM_FLAGS_VP_VALID	= 0x40,
-};
-
 enum diag308_rc {
 	DIAG308_RC_OK		= 0x0001,
 	DIAG308_RC_NOCONFIG	= 0x0102,
 };
 
 extern int diag308(unsigned long subcode, void *addr);
-extern void diag308_reset(void);
 extern void store_status(void (*fn)(void *), void *data);
 extern void lgr_info_log(void);
 
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index afaf5e3c57fd..9f75d67b8c20 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -47,7 +47,6 @@ enum interruption_class {
 	IRQEXT_CMC,
 	IRQEXT_FTP,
 	IRQIO_CIO,
-	IRQIO_QAI,
 	IRQIO_DAS,
 	IRQIO_C15,
 	IRQIO_C70,
@@ -55,12 +54,14 @@ enum interruption_class {
 	IRQIO_VMR,
 	IRQIO_LCS,
 	IRQIO_CTC,
-	IRQIO_APB,
 	IRQIO_ADM,
 	IRQIO_CSC,
-	IRQIO_PCI,
-	IRQIO_MSI,
 	IRQIO_VIR,
+	IRQIO_QAI,
+	IRQIO_APB,
+	IRQIO_PCF,
+	IRQIO_PCD,
+	IRQIO_MSI,
 	IRQIO_VAI,
 	IRQIO_GAL,
 	NMI_NMI,
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 825dd0f7f221..ea398a05f643 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -11,6 +11,7 @@
 
 #include <asm/processor.h>
 #include <asm/page.h>
+#include <asm/setup.h>
 /*
  * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
  * I.e. Maximum page that is mapped directly into kernel memory,
@@ -42,6 +43,9 @@
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_S390
 
+/* Allow kexec_file to load a segment to 0 */
+#define KEXEC_BUF_MEM_UNKNOWN -1
+
 /* Provide a dummy definition to avoid build failures. */
 static inline void crash_setup_regs(struct pt_regs *newregs,
 					struct pt_regs *oldregs) { }
@@ -51,20 +55,24 @@ struct s390_load_data {
 	/* Pointer to the kernel buffer. Used to register cmdline etc.. */
 	void *kernel_buf;
 
+	/* Load address of the kernel_buf. */
+	unsigned long kernel_mem;
+
+	/* Parmarea in the kernel buffer. */
+	struct parmarea *parm;
+
 	/* Total size of loaded segments in memory. Used as an offset. */
 	size_t memsz;
 
-	/* Load address of initrd. Used to register INITRD_START in kernel. */
-	unsigned long initrd_load_addr;
+	struct ipl_report *report;
 };
 
-int kexec_file_add_purgatory(struct kimage *image,
-			     struct s390_load_data *data);
-int kexec_file_add_initrd(struct kimage *image,
-			  struct s390_load_data *data,
-			  char *initrd, unsigned long initrd_len);
-int *kexec_file_update_kernel(struct kimage *iamge,
-			      struct s390_load_data *data);
+int s390_verify_sig(const char *kernel, unsigned long kernel_len);
+void *kexec_file_add_components(struct kimage *image,
+				int (*add_kernel)(struct kimage *image,
+						  struct s390_load_data *data));
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+			 unsigned long addr);
 
 extern const struct kexec_file_ops s390_kexec_image_ops;
 extern const struct kexec_file_ops s390_kexec_elf_ops;
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index 1b95da3fdd64..7f22262b0e46 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -28,5 +28,12 @@
 	.long	(_target) - . ;		\
 	.previous
 
+#define EX_TABLE_DMA(_fault, _target)	\
+	.section .dma.ex_table, "a" ;	\
+	.align	4 ;			\
+	.long	(_fault) - . ;		\
+	.long	(_target) - . ;		\
+	.previous
+
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 5b9f10b1e55d..237ee0c4169f 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -129,7 +129,7 @@ struct lowcore {
 	/* SMP info area */
 	__u32	cpu_nr;				/* 0x03a0 */
 	__u32	softirq_pending;		/* 0x03a4 */
-	__u32	preempt_count;			/* 0x03a8 */
+	__s32	preempt_count;			/* 0x03a8 */
 	__u32	spinlock_lockval;		/* 0x03ac */
 	__u32	spinlock_index;			/* 0x03b0 */
 	__u32	fpu_flags;			/* 0x03b4 */
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index 123dac3717b3..0033dcd663b1 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -32,23 +32,23 @@ _LC_BR_R1 = __LC_BR_R1
 	.endm
 
 	.macro __THUNK_PROLOG_BR r1,r2
-	__THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1
+	__THUNK_PROLOG_NAME __s390_indirect_jump_r\r2\()use_r\r1
 	.endm
 
 	.macro __THUNK_PROLOG_BC d0,r1,r2
-	__THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+	__THUNK_PROLOG_NAME __s390_indirect_branch_\d0\()_\r2\()use_\r1
 	.endm
 
 	.macro __THUNK_BR r1,r2
-	jg	__s390x_indirect_jump_r\r2\()use_r\r1
+	jg	__s390_indirect_jump_r\r2\()use_r\r1
 	.endm
 
 	.macro __THUNK_BC d0,r1,r2
-	jg	__s390x_indirect_branch_\d0\()_\r2\()use_\r1
+	jg	__s390_indirect_branch_\d0\()_\r2\()use_\r1
 	.endm
 
 	.macro __THUNK_BRASL r1,r2,r3
-	brasl	\r1,__s390x_indirect_jump_r\r3\()use_r\r2
+	brasl	\r1,__s390_indirect_jump_r\r3\()use_r\r2
 	.endm
 
 	.macro	__DECODE_RR expand,reg,ruse
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 4e0efebc56a9..305befd55326 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -26,6 +26,9 @@ int pci_proc_domain(struct pci_bus *);
 #define ZPCI_BUS_NR			0	/* default bus number */
 #define ZPCI_DEVFN			0	/* default device number */
 
+#define ZPCI_NR_DMA_SPACES		1
+#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
+
 /* PCI Function Controls */
 #define ZPCI_FC_FN_ENABLED		0x80
 #define ZPCI_FC_ERROR			0x40
@@ -83,6 +86,8 @@ enum zpci_state {
 
 struct zpci_bar_struct {
 	struct resource *res;		/* bus resource */
+	void __iomem	*mio_wb;
+	void __iomem	*mio_wt;
 	u32		val;		/* bar start & 3 flag bits */
 	u16		map_idx;	/* index into bar mapping array */
 	u8		size;		/* order 2 exponent */
@@ -112,6 +117,8 @@ struct zpci_dev {
 	/* IRQ stuff */
 	u64		msi_addr;	/* MSI address */
 	unsigned int	max_msi;	/* maximum number of MSI's */
+	unsigned int	msi_first_bit;
+	unsigned int	msi_nr_irqs;
 	struct airq_iv *aibv;		/* adapter interrupt bit vector */
 	unsigned long	aisb;		/* number of the summary bit */
 
@@ -130,6 +137,7 @@ struct zpci_dev {
 	struct iommu_device iommu_dev;  /* IOMMU core handle */
 
 	char res_name[16];
+	bool mio_capable;
 	struct zpci_bar_struct bars[PCI_BAR_COUNT];
 
 	u64		start_dma;	/* Start of available DMA addresses */
@@ -158,6 +166,7 @@ static inline bool zdev_enabled(struct zpci_dev *zdev)
 }
 
 extern const struct attribute_group *zpci_attr_groups[];
+extern unsigned int s390_pci_force_floating __initdata;
 
 /* -----------------------------------------------------------------------------
   Prototypes
@@ -219,6 +228,9 @@ struct zpci_dev *get_zdev_by_fid(u32);
 int zpci_dma_init(void);
 void zpci_dma_exit(void);
 
+int __init zpci_irq_init(void);
+void __init zpci_irq_exit(void);
+
 /* FMB */
 int zpci_fmb_enable_device(struct zpci_dev *);
 int zpci_fmb_disable_device(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index b3b31b31f0d3..3ec52a05d500 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -43,6 +43,8 @@ struct clp_fh_list_entry {
 
 #define CLP_SET_ENABLE_PCI_FN	0	/* Yes, 0 enables it */
 #define CLP_SET_DISABLE_PCI_FN	1	/* Yes, 1 disables it */
+#define CLP_SET_ENABLE_MIO	2
+#define CLP_SET_DISABLE_MIO	3
 
 #define CLP_UTIL_STR_LEN	64
 #define CLP_PFIP_NR_SEGMENTS	4
@@ -80,7 +82,8 @@ struct clp_req_query_pci {
 struct clp_rsp_query_pci {
 	struct clp_rsp_hdr hdr;
 	u16 vfn;			/* virtual fn number */
-	u16			:  7;
+	u16			:  6;
+	u16 mio_addr_avail	:  1;
 	u16 util_str_avail	:  1;	/* utility string available? */
 	u16 pfgid		:  8;	/* pci function group id */
 	u32 fid;			/* pci function id */
@@ -96,6 +99,15 @@ struct clp_rsp_query_pci {
 	u32 reserved[11];
 	u32 uid;			/* user defined id */
 	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
+	u32 reserved2[16];
+	u32 mio_valid : 6;
+	u32 : 26;
+	u32 : 32;
+	struct {
+		u64 wb;
+		u64 wt;
+	} addr[PCI_BAR_COUNT];
+	u32 reserved3[6];
 } __packed;
 
 /* Query PCI function group request */
@@ -118,7 +130,11 @@ struct clp_rsp_query_pci_grp {
 	u8 refresh		:  1;	/* TLB refresh mode */
 	u16 reserved2;
 	u16 mui;
-	u64 reserved3;
+	u16			: 16;
+	u16 maxfaal;
+	u16			:  4;
+	u16 dnoi		: 12;
+	u16 maxcpu;
 	u64 dasm;			/* dma address space mask */
 	u64 msia;			/* MSI address */
 	u64 reserved4;
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index ba22a6ea51a1..ff81ed19c506 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_S390_PCI_INSN_H
 #define _ASM_S390_PCI_INSN_H
 
+#include <linux/jump_label.h>
+
 /* Load/Store status codes */
 #define ZPCI_PCI_ST_FUNC_NOT_ENABLED		4
 #define ZPCI_PCI_ST_FUNC_IN_ERR			8
@@ -38,6 +40,8 @@
 #define ZPCI_MOD_FC_RESET_ERROR	7
 #define ZPCI_MOD_FC_RESET_BLOCK	9
 #define ZPCI_MOD_FC_SET_MEASURE	10
+#define ZPCI_MOD_FC_REG_INT_D	16
+#define ZPCI_MOD_FC_DEREG_INT_D	17
 
 /* FIB function controls */
 #define ZPCI_FIB_FC_ENABLED	0x80
@@ -51,16 +55,7 @@
 #define ZPCI_FIB_FC_LS_BLOCKED	0x20
 #define ZPCI_FIB_FC_DMAAS_REG	0x10
 
-/* Function Information Block */
-struct zpci_fib {
-	u32 fmt		:  8;	/* format */
-	u32		: 24;
-	u32		: 32;
-	u8 fc;			/* function controls */
-	u64		: 56;
-	u64 pba;		/* PCI base address */
-	u64 pal;		/* PCI address limit */
-	u64 iota;		/* I/O Translation Anchor */
+struct zpci_fib_fmt0 {
 	u32		:  1;
 	u32 isc		:  3;	/* Interrupt subclass */
 	u32 noi		: 12;	/* Number of interrupts */
@@ -72,16 +67,90 @@ struct zpci_fib {
 	u32		: 32;
 	u64 aibv;		/* Adapter int bit vector address */
 	u64 aisb;		/* Adapter int summary bit address */
+};
+
+struct zpci_fib_fmt1 {
+	u32		:  4;
+	u32 noi		: 12;
+	u32		: 16;
+	u32 dibvo	: 16;
+	u32		: 16;
+	u64		: 64;
+	u64		: 64;
+};
+
+/* Function Information Block */
+struct zpci_fib {
+	u32 fmt		:  8;	/* format */
+	u32		: 24;
+	u32		: 32;
+	u8 fc;			/* function controls */
+	u64		: 56;
+	u64 pba;		/* PCI base address */
+	u64 pal;		/* PCI address limit */
+	u64 iota;		/* I/O Translation Anchor */
+	union {
+		struct zpci_fib_fmt0 fmt0;
+		struct zpci_fib_fmt1 fmt1;
+	};
 	u64 fmb_addr;		/* Function measurement block address and key */
 	u32		: 32;
 	u32 gd;
 } __packed __aligned(8);
 
+/* directed interruption information block */
+struct zpci_diib {
+	u32 : 1;
+	u32 isc : 3;
+	u32 : 28;
+	u16 : 16;
+	u16 nr_cpus;
+	u64 disb_addr;
+	u64 : 64;
+	u64 : 64;
+} __packed __aligned(8);
+
+/* cpu directed interruption information block */
+struct zpci_cdiib {
+	u64 : 64;
+	u64 dibv_addr;
+	u64 : 64;
+	u64 : 64;
+	u64 : 64;
+} __packed __aligned(8);
+
+union zpci_sic_iib {
+	struct zpci_diib diib;
+	struct zpci_cdiib cdiib;
+};
+
+DECLARE_STATIC_KEY_FALSE(have_mio);
+
 u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status);
 int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
-int zpci_load(u64 *data, u64 req, u64 offset);
-int zpci_store(u64 data, u64 req, u64 offset);
-int zpci_store_block(const u64 *data, u64 req, u64 offset);
-int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
+int __zpci_load(u64 *data, u64 req, u64 offset);
+int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len);
+int __zpci_store(u64 data, u64 req, u64 offset);
+int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len);
+int __zpci_store_block(const u64 *data, u64 req, u64 offset);
+void zpci_barrier(void);
+int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
+
+static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
+{
+	union zpci_sic_iib iib = {{0}};
+
+	return __zpci_set_irq_ctrl(ctl, isc, &iib);
+}
+
+#ifdef CONFIG_PCI
+static inline void enable_mio_ctl(void)
+{
+	if (static_branch_likely(&have_mio))
+		__ctl_set_bit(2, 5);
+}
+#else /* CONFIG_PCI */
+static inline void enable_mio_ctl(void) {}
+#endif /* CONFIG_PCI */
 
 #endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cbb9cb9c6547..cd060b5dd8fd 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -37,12 +37,10 @@ extern struct zpci_iomap_entry *zpci_iomap_start;
 #define zpci_read(LENGTH, RETTYPE)						\
 static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
 {										\
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
 	u64 data;								\
 	int rc;									\
 										\
-	rc = zpci_load(&data, req, ZPCI_OFFSET(addr));				\
+	rc = zpci_load(&data, addr, LENGTH);					\
 	if (rc)									\
 		data = -1ULL;							\
 	return (RETTYPE) data;							\
@@ -52,11 +50,9 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
 static inline void zpci_write_##VALTYPE(VALTYPE val,				\
 					const volatile void __iomem *addr)	\
 {										\
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
 	u64 data = (VALTYPE) val;						\
 										\
-	zpci_store(data, req, ZPCI_OFFSET(addr));				\
+	zpci_store(addr, data, LENGTH);						\
 }
 
 zpci_read(8, u64)
@@ -68,36 +64,38 @@ zpci_write(4, u32)
 zpci_write(2, u16)
 zpci_write(1, u8)
 
-static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len)
+static inline int zpci_write_single(volatile void __iomem *dst, const void *src,
+				    unsigned long len)
 {
 	u64 val;
 
 	switch (len) {
 	case 1:
-		val = (u64) *((u8 *) data);
+		val = (u64) *((u8 *) src);
 		break;
 	case 2:
-		val = (u64) *((u16 *) data);
+		val = (u64) *((u16 *) src);
 		break;
 	case 4:
-		val = (u64) *((u32 *) data);
+		val = (u64) *((u32 *) src);
 		break;
 	case 8:
-		val = (u64) *((u64 *) data);
+		val = (u64) *((u64 *) src);
 		break;
 	default:
 		val = 0;		/* let FW report error */
 		break;
 	}
-	return zpci_store(val, req, offset);
+	return zpci_store(dst, val, len);
 }
 
-static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
+static inline int zpci_read_single(void *dst, const volatile void __iomem *src,
+				   unsigned long len)
 {
 	u64 data;
 	int cc;
 
-	cc = zpci_load(&data, req, offset);
+	cc = zpci_load(&data, src, len);
 	if (cc)
 		goto out;
 
@@ -119,10 +117,8 @@ out:
 	return cc;
 }
 
-static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
-{
-	return zpci_store_block(data, req, offset);
-}
+int zpci_write_block(volatile void __iomem *dst, const void *src,
+		     unsigned long len);
 
 static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
 {
@@ -140,18 +136,15 @@ static inline int zpci_memcpy_fromio(void *dst,
 				     const volatile void __iomem *src,
 				     unsigned long n)
 {
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(src)];
-	u64 req, offset = ZPCI_OFFSET(src);
 	int size, rc = 0;
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) src,
 					       (u64) dst, n, 8);
-		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
-		rc = zpci_read_single(req, dst, offset, size);
+		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
-		offset += size;
+		src += size;
 		dst += size;
 		n -= size;
 	}
@@ -161,8 +154,6 @@ static inline int zpci_memcpy_fromio(void *dst,
 static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 				   const void *src, unsigned long n)
 {
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
-	u64 req, offset = ZPCI_OFFSET(dst);
 	int size, rc = 0;
 
 	if (!src)
@@ -171,16 +162,14 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) dst,
 					       (u64) src, n, 128);
-		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
-
 		if (size > 8) /* main path */
-			rc = zpci_write_block(req, src, offset);
+			rc = zpci_write_block(dst, src, size);
 		else
-			rc = zpci_write_single(req, src, offset, size);
+			rc = zpci_write_single(dst, src, size);
 		if (rc)
 			break;
-		offset += size;
 		src += size;
+		dst += size;
 		n -= size;
 	}
 	return rc;
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 76dc344edb8c..9f0195d5fa16 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -238,7 +238,7 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_NOEXEC	0x100	/* region no-execute bit	    */
 #define _REGION_ENTRY_OFFSET	0xc0	/* region table offset		    */
 #define _REGION_ENTRY_INVALID	0x20	/* invalid region table entry	    */
-#define _REGION_ENTRY_TYPE_MASK	0x0c	/* region/segment table type mask   */
+#define _REGION_ENTRY_TYPE_MASK	0x0c	/* region table type mask	    */
 #define _REGION_ENTRY_TYPE_R1	0x0c	/* region first table type	    */
 #define _REGION_ENTRY_TYPE_R2	0x08	/* region second table type	    */
 #define _REGION_ENTRY_TYPE_R3	0x04	/* region third table type	    */
@@ -277,6 +277,7 @@ static inline int is_module_addr(void *addr)
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */
 #define _SEGMENT_ENTRY_NOEXEC	0x100	/* segment no-execute bit	    */
 #define _SEGMENT_ENTRY_INVALID	0x20	/* invalid segment table entry	    */
+#define _SEGMENT_ENTRY_TYPE_MASK 0x0c	/* segment table type mask	    */
 
 #define _SEGMENT_ENTRY		(0)
 #define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INVALID)
@@ -614,15 +615,9 @@ static inline int pgd_none(pgd_t pgd)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	/*
-	 * With dynamic page table levels the pgd can be a region table
-	 * entry or a segment table entry. Check for the bit that are
-	 * invalid for either table entry.
-	 */
-	unsigned long mask =
-		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
-		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
-	return (pgd_val(pgd) & mask) != 0;
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1)
+		return 0;
+	return (pgd_val(pgd) & ~_REGION_ENTRY_BITS) != 0;
 }
 
 static inline unsigned long pgd_pfn(pgd_t pgd)
@@ -703,6 +698,8 @@ static inline int pmd_large(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
+	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0)
+		return 1;
 	if (pmd_large(pmd))
 		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
@@ -710,8 +707,12 @@ static inline int pmd_bad(pmd_t pmd)
 
 static inline int pud_bad(pud_t pud)
 {
-	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
-		return pmd_bad(__pmd(pud_val(pud)));
+	unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
+
+	if (type > _REGION_ENTRY_TYPE_R3)
+		return 1;
+	if (type < _REGION_ENTRY_TYPE_R3)
+		return 0;
 	if (pud_large(pud))
 		return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
 	return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
@@ -719,8 +720,12 @@ static inline int pud_bad(pud_t pud)
 
 static inline int p4d_bad(p4d_t p4d)
 {
-	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
-		return pud_bad(__pud(p4d_val(p4d)));
+	unsigned long type = p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK;
+
+	if (type > _REGION_ENTRY_TYPE_R2)
+		return 1;
+	if (type < _REGION_ENTRY_TYPE_R2)
+		return 0;
 	return (p4d_val(p4d) & ~_REGION_ENTRY_BITS) != 0;
 }
 
@@ -1204,41 +1209,78 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
 #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
 #define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
 
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-#define pgd_offset_raw(pgd, addr) ((pgd) + pgd_index(addr))
-
 #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
 #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
 #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
 #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+/*
+ * The pgd_offset function *always* adds the index for the top-level
+ * region/segment table. This is done to get a sequence like the
+ * following to work:
+ *	pgdp = pgd_offset(current->mm, addr);
+ *	pgd = READ_ONCE(*pgdp);
+ *	p4dp = p4d_offset(&pgd, addr);
+ *	...
+ * The subsequent p4d_offset, pud_offset and pmd_offset functions
+ * only add an index if they dereferenced the pointer.
+ */
+static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
 {
-	p4d_t *p4d = (p4d_t *) pgd;
+	unsigned long rste;
+	unsigned int shift;
 
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
-		p4d = (p4d_t *) pgd_deref(*pgd);
-	return p4d + p4d_index(address);
+	/* Get the first entry of the top level table */
+	rste = pgd_val(*pgd);
+	/* Pick up the shift from the table type of the first entry */
+	shift = ((rste & _REGION_ENTRY_TYPE_MASK) >> 2) * 11 + 20;
+	return pgd + ((address >> shift) & (PTRS_PER_PGD - 1));
 }
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+#define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	pud_t *pud = (pud_t *) p4d;
+	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
+	return (p4d_t *) pgd;
+}
 
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
-		pud = (pud_t *) p4d_deref(*p4d);
-	return pud + pud_index(address);
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
+	return (pud_t *) p4d;
 }
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 {
-	pmd_t *pmd = (pmd_t *) pud;
+	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
+	return (pmd_t *) pud;
+}
 
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		pmd = (pmd_t *) pud_deref(*pud);
-	return pmd + pmd_index(address);
+static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
+{
+	return (pte_t *) pmd_deref(*pmd) + pte_index(address);
+}
+
+#define pte_offset_kernel(pmd, address) pte_offset(pmd, address)
+#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
+#define pte_unmap(pte) do { } while (0)
+
+static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (end < start)
+		return false;
+	return end <= current->mm->context.asce_limit;
 }
+#define gup_fast_permitted gup_fast_permitted
 
 #define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot))
 #define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
@@ -1249,12 +1291,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d))
 #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
 
-/* Find an entry in the lowest level page table.. */
-#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
-#define pte_offset_kernel(pmd, address) pte_offset(pmd,address)
-#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
-
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	pmd_val(pmd) &= ~_SEGMENT_ENTRY_WRITE;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 81038ab357ce..b0fcbc37b637 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -156,25 +156,6 @@ struct thread_struct {
 
 typedef struct thread_struct thread_struct;
 
-/*
- * Stack layout of a C stack frame.
- */
-#ifndef __PACK_STACK
-struct stack_frame {
-	unsigned long back_chain;
-	unsigned long empty1[5];
-	unsigned long gprs[10];
-	unsigned int  empty2[8];
-};
-#else
-struct stack_frame {
-	unsigned long empty1[5];
-	unsigned int  empty2[8];
-	unsigned long gprs[10];
-	unsigned long back_chain;
-};
-#endif
-
 #define ARCH_MIN_TASKALIGN	8
 
 #define INIT_THREAD {							\
@@ -206,11 +187,7 @@ struct mm_struct;
 struct seq_file;
 struct pt_regs;
 
-typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable);
-void dump_trace(dump_trace_func_t func, void *data,
-		struct task_struct *task, unsigned long sp);
 void show_registers(struct pt_regs *regs);
-
 void show_cacheinfo(struct seq_file *m);
 
 /* Free all resources held by a thread. */
@@ -244,55 +221,6 @@ static __no_kasan_or_inline unsigned short stap(void)
 	return cpu_address;
 }
 
-#define CALL_ARGS_0()							\
-	register unsigned long r2 asm("2")
-#define CALL_ARGS_1(arg1)						\
-	register unsigned long r2 asm("2") = (unsigned long)(arg1)
-#define CALL_ARGS_2(arg1, arg2)						\
-	CALL_ARGS_1(arg1);						\
-	register unsigned long r3 asm("3") = (unsigned long)(arg2)
-#define CALL_ARGS_3(arg1, arg2, arg3)					\
-	CALL_ARGS_2(arg1, arg2);					\
-	register unsigned long r4 asm("4") = (unsigned long)(arg3)
-#define CALL_ARGS_4(arg1, arg2, arg3, arg4)				\
-	CALL_ARGS_3(arg1, arg2, arg3);					\
-	register unsigned long r4 asm("5") = (unsigned long)(arg4)
-#define CALL_ARGS_5(arg1, arg2, arg3, arg4, arg5)			\
-	CALL_ARGS_4(arg1, arg2, arg3, arg4);				\
-	register unsigned long r4 asm("6") = (unsigned long)(arg5)
-
-#define CALL_FMT_0
-#define CALL_FMT_1 CALL_FMT_0, "0" (r2)
-#define CALL_FMT_2 CALL_FMT_1, "d" (r3)
-#define CALL_FMT_3 CALL_FMT_2, "d" (r4)
-#define CALL_FMT_4 CALL_FMT_3, "d" (r5)
-#define CALL_FMT_5 CALL_FMT_4, "d" (r6)
-
-#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
-#define CALL_CLOBBER_4 CALL_CLOBBER_5
-#define CALL_CLOBBER_3 CALL_CLOBBER_4, "5"
-#define CALL_CLOBBER_2 CALL_CLOBBER_3, "4"
-#define CALL_CLOBBER_1 CALL_CLOBBER_2, "3"
-#define CALL_CLOBBER_0 CALL_CLOBBER_1
-
-#define CALL_ON_STACK(fn, stack, nr, args...)				\
-({									\
-	CALL_ARGS_##nr(args);						\
-	unsigned long prev;						\
-									\
-	asm volatile(							\
-		"	la	%[_prev],0(15)\n"			\
-		"	la	15,0(%[_stack])\n"			\
-		"	stg	%[_prev],%[_bc](15)\n"			\
-		"	brasl	14,%[_fn]\n"				\
-		"	la	15,0(%[_prev])\n"			\
-		: "+&d" (r2), [_prev] "=&a" (prev)			\
-		: [_stack] "a" (stack),					\
-		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
-		  [_fn] "X" (fn) CALL_FMT_##nr : CALL_CLOBBER_##nr);	\
-	r2;								\
-})
-
 /*
  * Give up the time slice of the virtual PU.
  */
@@ -339,10 +267,10 @@ static __no_kasan_or_inline void __load_psw_mask(unsigned long mask)
 
 	asm volatile(
 		"	larl	%0,1f\n"
-		"	stg	%0,%O1+8(%R1)\n"
-		"	lpswe	%1\n"
+		"	stg	%0,%1\n"
+		"	lpswe	%2\n"
 		"1:"
-		: "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc");
+		: "=&d" (addr), "=Q" (psw.addr) : "Q" (psw) : "memory", "cc");
 }
 
 /*
@@ -387,12 +315,12 @@ void enabled_wait(void);
 /*
  * Function to drop a processor into disabled wait state
  */
-static inline void __noreturn disabled_wait(unsigned long code)
+static inline void __noreturn disabled_wait(void)
 {
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_MASK_WAIT | PSW_MASK_BA | PSW_MASK_EA;
-	psw.addr = code;
+	psw.addr = _THIS_IP_;
 	__load_psw(psw);
 	while (1);
 }
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index ef4c9dec06a4..f577c5f6031a 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -79,6 +79,9 @@ struct sclp_info {
 	unsigned char has_kss : 1;
 	unsigned char has_gisaf : 1;
 	unsigned char has_diag318 : 1;
+	unsigned char has_sipl : 1;
+	unsigned char has_sipl_g2 : 1;
+	unsigned char has_dirq : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 7afe4620685c..42de04ad9c07 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -2,8 +2,20 @@
 #ifndef _S390_SECTIONS_H
 #define _S390_SECTIONS_H
 
+#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed
+
 #include <asm-generic/sections.h>
 
+extern bool initmem_freed;
+
+static inline int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+	if (!initmem_freed)
+		return 0;
+	return addr >= (unsigned long)__init_begin &&
+	       addr < (unsigned long)__init_end;
+}
+
 /*
  * .boot.data section contains variables "shared" between the decompressor and
  * the decompressed kernel. The decompressor will store values in them, and
@@ -16,4 +28,14 @@
  */
 #define __bootdata(var) __section(.boot.data.var) var
 
+/*
+ * .boot.preserved.data is similar to .boot.data, but it is not part of the
+ * .init section and thus will be preserved for later use in the decompressed
+ * kernel.
+ */
+#define __bootdata_preserved(var) __section(.boot.preserved.data.var) var
+
+extern unsigned long __sdma, __edma;
+extern unsigned long __stext_dma, __etext_dma;
+
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index efda97804aa4..925889d360c1 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -12,7 +12,10 @@
 #define EP_OFFSET		0x10008
 #define EP_STRING		"S390EP"
 #define PARMAREA		0x10400
-#define PARMAREA_END		0x11000
+#define EARLY_SCCB_OFFSET	0x11000
+#define HEAD_END		0x12000
+
+#define EARLY_SCCB_SIZE		PAGE_SIZE
 
 /*
  * Machine features detected in early.c
@@ -65,6 +68,16 @@
 #define OLDMEM_SIZE	(*(unsigned long *)  (OLDMEM_SIZE_OFFSET))
 #define COMMAND_LINE	((char *)	     (COMMAND_LINE_OFFSET))
 
+struct parmarea {
+	unsigned long ipl_device;			/* 0x10400 */
+	unsigned long initrd_start;			/* 0x10408 */
+	unsigned long initrd_size;			/* 0x10410 */
+	unsigned long oldmem_base;			/* 0x10418 */
+	unsigned long oldmem_size;			/* 0x10420 */
+	char pad1[0x10480 - 0x10428];			/* 0x10428 - 0x10480 */
+	char command_line[ARCH_COMMAND_LINE_SIZE];	/* 0x10480 */
+};
+
 extern int noexec_disabled;
 extern int memory_end_set;
 extern unsigned long memory_end;
@@ -134,6 +147,12 @@ extern void (*_machine_restart)(char *command);
 extern void (*_machine_halt)(void);
 extern void (*_machine_power_off)(void);
 
+extern unsigned long __kaslr_offset;
+static inline unsigned long kaslr_offset(void)
+{
+	return __kaslr_offset;
+}
+
 #else /* __ASSEMBLY__ */
 
 #define IPL_DEVICE	(IPL_DEVICE_OFFSET)
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
new file mode 100644
index 000000000000..49634bfbecdd
--- /dev/null
+++ b/arch/s390/include/asm/stacktrace.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_STACKTRACE_H
+#define _ASM_S390_STACKTRACE_H
+
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <asm/switch_to.h>
+
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_TASK,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_NODAT,
+	STACK_TYPE_RESTART,
+};
+
+struct stack_info {
+	enum stack_type type;
+	unsigned long begin, end;
+};
+
+const char *stack_type_name(enum stack_type type);
+int get_stack_info(unsigned long sp, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask);
+
+static inline bool on_stack(struct stack_info *info,
+			    unsigned long addr, size_t len)
+{
+	if (info->type == STACK_TYPE_UNKNOWN)
+		return false;
+	if (addr + len < addr)
+		return false;
+	return addr >= info->begin && addr + len < info->end;
+}
+
+static inline unsigned long get_stack_pointer(struct task_struct *task,
+					      struct pt_regs *regs)
+{
+	if (regs)
+		return (unsigned long) kernel_stack_pointer(regs);
+	if (task == current)
+		return current_stack_pointer();
+	return (unsigned long) task->thread.ksp;
+}
+
+/*
+ * Stack layout of a C stack frame.
+ */
+#ifndef __PACK_STACK
+struct stack_frame {
+	unsigned long back_chain;
+	unsigned long empty1[5];
+	unsigned long gprs[10];
+	unsigned int  empty2[8];
+};
+#else
+struct stack_frame {
+	unsigned long empty1[5];
+	unsigned int  empty2[8];
+	unsigned long gprs[10];
+	unsigned long back_chain;
+};
+#endif
+
+#define CALL_ARGS_0()							\
+	register unsigned long r2 asm("2")
+#define CALL_ARGS_1(arg1)						\
+	register unsigned long r2 asm("2") = (unsigned long)(arg1)
+#define CALL_ARGS_2(arg1, arg2)						\
+	CALL_ARGS_1(arg1);						\
+	register unsigned long r3 asm("3") = (unsigned long)(arg2)
+#define CALL_ARGS_3(arg1, arg2, arg3)					\
+	CALL_ARGS_2(arg1, arg2);					\
+	register unsigned long r4 asm("4") = (unsigned long)(arg3)
+#define CALL_ARGS_4(arg1, arg2, arg3, arg4)				\
+	CALL_ARGS_3(arg1, arg2, arg3);					\
+	register unsigned long r4 asm("5") = (unsigned long)(arg4)
+#define CALL_ARGS_5(arg1, arg2, arg3, arg4, arg5)			\
+	CALL_ARGS_4(arg1, arg2, arg3, arg4);				\
+	register unsigned long r4 asm("6") = (unsigned long)(arg5)
+
+#define CALL_FMT_0 "=&d" (r2) :
+#define CALL_FMT_1 "+&d" (r2) :
+#define CALL_FMT_2 CALL_FMT_1 "d" (r3),
+#define CALL_FMT_3 CALL_FMT_2 "d" (r4),
+#define CALL_FMT_4 CALL_FMT_3 "d" (r5),
+#define CALL_FMT_5 CALL_FMT_4 "d" (r6),
+
+#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
+#define CALL_CLOBBER_4 CALL_CLOBBER_5
+#define CALL_CLOBBER_3 CALL_CLOBBER_4, "5"
+#define CALL_CLOBBER_2 CALL_CLOBBER_3, "4"
+#define CALL_CLOBBER_1 CALL_CLOBBER_2, "3"
+#define CALL_CLOBBER_0 CALL_CLOBBER_1
+
+#define CALL_ON_STACK(fn, stack, nr, args...)				\
+({									\
+	CALL_ARGS_##nr(args);						\
+	unsigned long prev;						\
+									\
+	asm volatile(							\
+		"	la	%[_prev],0(15)\n"			\
+		"	la	15,0(%[_stack])\n"			\
+		"	stg	%[_prev],%[_bc](15)\n"			\
+		"	brasl	14,%[_fn]\n"				\
+		"	la	15,0(%[_prev])\n"			\
+		: [_prev] "=&a" (prev), CALL_FMT_##nr			\
+		  [_stack] "a" (stack),					\
+		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
+		  [_fn] "X" (fn) : CALL_CLOBBER_##nr);			\
+	r2;								\
+})
+
+#endif /* _ASM_S390_STACKTRACE_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 59c3e91f2cdb..ab3407aa4fd8 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -14,13 +14,8 @@
 #include <linux/err.h>
 #include <asm/ptrace.h>
 
-/*
- * The syscall table always contains 32 bit pointers since we know that the
- * address of the function to be called is (way) below 4GB.  So the "int"
- * type here is what we want [need] for both 32 bit and 64 bit systems.
- */
-extern const unsigned int sys_call_table[];
-extern const unsigned int sys_call_table_emu[];
+extern const unsigned long sys_call_table[];
+extern const unsigned long sys_call_table_emu[];
 
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
index 5596c5c625d2..3c3d6fe8e2f0 100644
--- a/arch/s390/include/asm/syscall_wrapper.h
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -119,8 +119,8 @@
 		      "Type aliasing is used to sanitize syscall arguments");\
 	asmlinkage long __s390x_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_sys##name))));		\
-	ALLOW_ERROR_INJECTION(__s390x_sys##name, ERRNO);				\
-	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	ALLOW_ERROR_INJECTION(__s390x_sys##name, ERRNO);			\
+	long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));			\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
 	__S390_SYS_STUBx(x, name, __VA_ARGS__)					\
 	asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b31c779cf581..aa406c05a350 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -22,98 +22,39 @@
  * Pages used for the page tables is a different story. FIXME: more
  */
 
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/processor.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-struct mmu_gather {
-	struct mm_struct *mm;
-	struct mmu_table_batch *batch;
-	unsigned int fullmm;
-	unsigned long start, end;
-};
-
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-	tlb->batch = NULL;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	__tlb_flush_mm_lazy(tlb->mm);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	tlb_table_flush(tlb);
-}
-
+void __tlb_remove_table(void *_table);
+static inline void tlb_flush(struct mmu_gather *tlb);
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size);
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
+#define tlb_start_vma(tlb, vma)			do { } while (0)
+#define tlb_end_vma(tlb, vma)			do { } while (0)
 
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->start = start;
-		tlb->end = end;
-	}
+#define tlb_flush tlb_flush
+#define pte_free_tlb pte_free_tlb
+#define pmd_free_tlb pmd_free_tlb
+#define p4d_free_tlb p4d_free_tlb
+#define pud_free_tlb pud_free_tlb
 
-	tlb_flush_mmu(tlb);
-}
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm-generic/tlb.h>
 
 /*
  * Release the page cache reference for a pte removed by
  * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
  * has already been freed, so just do free_page_and_swap_cache.
  */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-}
-
 static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
 					  struct page *page, int page_size)
 {
-	return __tlb_remove_page(tlb, page);
+	free_page_and_swap_cache(page);
+	return false;
 }
 
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
+static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	return tlb_remove_page(tlb, page);
+	__tlb_flush_mm_lazy(tlb->mm);
 }
 
 /*
@@ -121,8 +62,17 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
  * page table from the tlb.
  */
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-				unsigned long address)
+                                unsigned long address)
 {
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_ptes = 1;
+	/*
+	 * page_table_free_rcu takes care of the allocation bit masks
+	 * of the 2K table fragments in the 4K page table page,
+	 * then calls tlb_remove_table.
+	 */
 	page_table_free_rcu(tlb, (unsigned long *) pte, address);
 }
 
@@ -139,6 +89,10 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_puds = 1;
 	tlb_remove_table(tlb, pmd);
 }
 
@@ -154,6 +108,10 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 {
 	if (mm_p4d_folded(tlb->mm))
 		return;
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_p4ds = 1;
 	tlb_remove_table(tlb, p4d);
 }
 
@@ -169,21 +127,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 {
 	if (mm_pud_folded(tlb->mm))
 		return;
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_puds = 1;
 	tlb_remove_table(tlb, pud);
 }
 
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-#define tlb_remove_tlb_entry(tlb, ptep, addr)	do { } while (0)
-#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr)	do { } while (0)
-#define tlb_migrate_finish(mm)			do { } while (0)
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
 
 #endif /* _S390_TLB_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 007fcb9aeeb8..bd2fd9a7821d 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -55,8 +55,10 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n);
 unsigned long __must_check
 raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 
+#ifndef CONFIG_KASAN
 #define INLINE_COPY_FROM_USER
 #define INLINE_COPY_TO_USER
+#endif
 
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 
diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h
new file mode 100644
index 000000000000..6eb2ef105d87
--- /dev/null
+++ b/arch/s390/include/asm/unwind.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_UNWIND_H
+#define _ASM_S390_UNWIND_H
+
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+
+/*
+ * To use the stack unwinder it has to be initialized with unwind_start.
+ * There four combinations for task and regs:
+ * 1) task==NULL, regs==NULL: the unwind starts for the task that is currently
+ *    running, sp/ip picked up from the CPU registers
+ * 2) task==NULL, regs!=NULL: the unwind starts from the sp/ip found in
+ *    the struct pt_regs of an interrupt frame for the current task
+ * 3) task!=NULL, regs==NULL: the unwind starts for an inactive task with
+ *    the sp picked up from task->thread.ksp and the ip picked up from the
+ *    return address stored by __switch_to
+ * 4) task!=NULL, regs!=NULL: the sp/ip are picked up from the interrupt
+ *    frame 'regs' of a inactive task
+ * If 'first_frame' is not zero unwind_start skips unwind frames until it
+ * reaches the specified stack pointer.
+ * The end of the unwinding is indicated with unwind_done, this can be true
+ * right after unwind_start, e.g. with first_frame!=0 that can not be found.
+ * unwind_next_frame skips to the next frame.
+ * Once the unwind is completed unwind_error() can be used to check if there
+ * has been a situation where the unwinder could not correctly understand
+ * the tasks call chain.
+ */
+
+struct unwind_state {
+	struct stack_info stack_info;
+	unsigned long stack_mask;
+	struct task_struct *task;
+	struct pt_regs *regs;
+	unsigned long sp, ip;
+	int graph_idx;
+	bool reliable;
+	bool error;
+};
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long first_frame);
+bool unwind_next_frame(struct unwind_state *state);
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+	return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline bool unwind_error(struct unwind_state *state)
+{
+	return state->error;
+}
+
+static inline void unwind_start(struct unwind_state *state,
+				struct task_struct *task,
+				struct pt_regs *regs,
+				unsigned long sp)
+{
+	sp = sp ? : get_stack_pointer(task, regs);
+	__unwind_start(state, task, regs, sp);
+}
+
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+	return unwind_done(state) ? NULL : state->regs;
+}
+
+#define unwind_for_each_frame(state, task, regs, first_frame)	\
+	for (unwind_start(state, task, regs, first_frame);	\
+	     !unwind_done(state);				\
+	     unwind_next_frame(state))
+
+static inline void unwind_init(void) {}
+static inline void unwind_module_init(struct module *mod, void *orc_ip,
+				      size_t orc_ip_size, void *orc,
+				      size_t orc_size) {}
+
+#ifdef CONFIG_KASAN
+/*
+ * This disables KASAN checking when reading a value from another task's stack,
+ * since the other task could be running on another CPU and could have poisoned
+ * the stack in the meantime.
+ */
+#define READ_ONCE_TASK_STACK(task, x)			\
+({							\
+	unsigned long val;				\
+	if (task == current)				\
+		val = READ_ONCE(x);			\
+	else						\
+		val = READ_ONCE_NOCHECK(x);		\
+	val;						\
+})
+#else
+#define READ_ONCE_TASK_STACK(task, x) READ_ONCE(x)
+#endif
+
+#endif /* _ASM_S390_UNWIND_H */
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
new file mode 100644
index 000000000000..ef3c00b049ab
--- /dev/null
+++ b/arch/s390/include/asm/uv.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor Interfaces
+ *
+ * Copyright IBM Corp. 2019
+ *
+ * Author(s):
+ *	Vasily Gorbik <gor@linux.ibm.com>
+ *	Janosch Frank <frankja@linux.ibm.com>
+ */
+#ifndef _ASM_S390_UV_H
+#define _ASM_S390_UV_H
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/bug.h>
+#include <asm/page.h>
+
+#define UVC_RC_EXECUTED		0x0001
+#define UVC_RC_INV_CMD		0x0002
+#define UVC_RC_INV_STATE	0x0003
+#define UVC_RC_INV_LEN		0x0005
+#define UVC_RC_NO_RESUME	0x0007
+
+#define UVC_CMD_QUI			0x0001
+#define UVC_CMD_SET_SHARED_ACCESS	0x1000
+#define UVC_CMD_REMOVE_SHARED_ACCESS	0x1001
+
+/* Bits in installed uv calls */
+enum uv_cmds_inst {
+	BIT_UVC_CMD_QUI = 0,
+	BIT_UVC_CMD_SET_SHARED_ACCESS = 8,
+	BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9,
+};
+
+struct uv_cb_header {
+	u16 len;
+	u16 cmd;	/* Command Code */
+	u16 rc;		/* Response Code */
+	u16 rrc;	/* Return Reason Code */
+} __packed __aligned(8);
+
+struct uv_cb_qui {
+	struct uv_cb_header header;
+	u64 reserved08;
+	u64 inst_calls_list[4];
+	u64 reserved30[15];
+} __packed __aligned(8);
+
+struct uv_cb_share {
+	struct uv_cb_header header;
+	u64 reserved08[3];
+	u64 paddr;
+	u64 reserved28;
+} __packed __aligned(8);
+
+static inline int uv_call(unsigned long r1, unsigned long r2)
+{
+	int cc;
+
+	asm volatile(
+		"0:	.insn rrf,0xB9A40000,%[r1],%[r2],0,0\n"
+		"		brc	3,0b\n"
+		"		ipm	%[cc]\n"
+		"		srl	%[cc],28\n"
+		: [cc] "=d" (cc)
+		: [r1] "a" (r1), [r2] "a" (r2)
+		: "memory", "cc");
+	return cc;
+}
+
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+extern int prot_virt_guest;
+
+static inline int is_prot_virt_guest(void)
+{
+	return prot_virt_guest;
+}
+
+static inline int share(unsigned long addr, u16 cmd)
+{
+	struct uv_cb_share uvcb = {
+		.header.cmd = cmd,
+		.header.len = sizeof(uvcb),
+		.paddr = addr
+	};
+
+	if (!is_prot_virt_guest())
+		return -ENOTSUPP;
+	/*
+	 * Sharing is page wise, if we encounter addresses that are
+	 * not page aligned, we assume something went wrong. If
+	 * malloced structs are passed to this function, we could leak
+	 * data to the hypervisor.
+	 */
+	BUG_ON(addr & ~PAGE_MASK);
+
+	if (!uv_call(0, (u64)&uvcb))
+		return 0;
+	return -EINVAL;
+}
+
+/*
+ * Guest 2 request to the Ultravisor to make a page shared with the
+ * hypervisor for IO.
+ *
+ * @addr: Real or absolute address of the page to be shared
+ */
+static inline int uv_set_shared(unsigned long addr)
+{
+	return share(addr, UVC_CMD_SET_SHARED_ACCESS);
+}
+
+/*
+ * Guest 2 request to the Ultravisor to make a page unshared.
+ *
+ * @addr: Real or absolute address of the page to be unshared
+ */
+static inline int uv_remove_shared(unsigned long addr)
+{
+	return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS);
+}
+
+void uv_query_info(void);
+#else
+#define is_prot_virt_guest() 0
+static inline int uv_set_shared(unsigned long addr) { return 0; }
+static inline int uv_remove_shared(unsigned long addr) { return 0; }
+static inline void uv_query_info(void) {}
+#endif
+
+#endif /* _ASM_S390_UV_H */
diff --git a/arch/s390/include/asm/vmlinux.lds.h b/arch/s390/include/asm/vmlinux.lds.h
index 2d127f900352..cbe670a6861b 100644
--- a/arch/s390/include/asm/vmlinux.lds.h
+++ b/arch/s390/include/asm/vmlinux.lds.h
@@ -18,3 +18,16 @@
 		*(SORT_BY_ALIGNMENT(SORT_BY_NAME(.boot.data*)))		\
 		__boot_data_end = .;					\
 	}
+
+/*
+ * .boot.preserved.data is similar to .boot.data, but it is not part of the
+ * .init section and thus will be preserved for later use in the decompressed
+ * kernel.
+ */
+#define BOOT_DATA_PRESERVED						\
+	. = ALIGN(PAGE_SIZE);						\
+	.boot.preserved.data : {					\
+		__boot_data_preserved_start = .;			\
+		*(SORT_BY_ALIGNMENT(SORT_BY_NAME(.boot.preserved.data*))) \
+		__boot_data_preserved_end = .;				\
+	}
diff --git a/arch/s390/include/uapi/asm/ipl.h b/arch/s390/include/uapi/asm/ipl.h
new file mode 100644
index 000000000000..fd32b1cd80d2
--- /dev/null
+++ b/arch/s390/include/uapi/asm/ipl.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_UAPI_IPL_H
+#define _ASM_S390_UAPI_IPL_H
+
+#include <linux/types.h>
+
+/* IPL Parameter List header */
+struct ipl_pl_hdr {
+	__u32 len;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  version;
+} __packed;
+
+#define IPL_PL_FLAG_IPLPS	0x80
+#define IPL_PL_FLAG_SIPL	0x40
+#define IPL_PL_FLAG_IPLSR	0x20
+
+/* IPL Parameter Block header */
+struct ipl_pb_hdr {
+	__u32 len;
+	__u8  pbt;
+} __packed;
+
+/* IPL Parameter Block types */
+enum ipl_pbt {
+	IPL_PBT_FCP = 0,
+	IPL_PBT_SCP_DATA = 1,
+	IPL_PBT_CCW = 2,
+};
+
+/* IPL Parameter Block 0 with common fields */
+struct ipl_pb0_common {
+	__u32 len;
+	__u8  pbt;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  loadparm[8];
+	__u8  reserved2[84];
+} __packed;
+
+#define IPL_PB0_FLAG_LOADPARM	0x80
+
+/* IPL Parameter Block 0 for FCP */
+struct ipl_pb0_fcp {
+	__u32 len;
+	__u8  pbt;
+	__u8  reserved1[3];
+	__u8  loadparm[8];
+	__u8  reserved2[304];
+	__u8  opt;
+	__u8  reserved3[3];
+	__u8  cssid;
+	__u8  reserved4[1];
+	__u16 devno;
+	__u8  reserved5[4];
+	__u64 wwpn;
+	__u64 lun;
+	__u32 bootprog;
+	__u8  reserved6[12];
+	__u64 br_lba;
+	__u32 scp_data_len;
+	__u8  reserved7[260];
+	__u8  scp_data[];
+} __packed;
+
+#define IPL_PB0_FCP_OPT_IPL	0x10
+#define IPL_PB0_FCP_OPT_DUMP	0x20
+
+/* IPL Parameter Block 0 for CCW */
+struct ipl_pb0_ccw {
+	__u32 len;
+	__u8  pbt;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  loadparm[8];
+	__u8  reserved2[84];
+	__u16 reserved3 : 13;
+	__u8  ssid : 3;
+	__u16 devno;
+	__u8  vm_flags;
+	__u8  reserved4[3];
+	__u32 vm_parm_len;
+	__u8  nss_name[8];
+	__u8  vm_parm[64];
+	__u8  reserved5[8];
+} __packed;
+
+#define IPL_PB0_CCW_VM_FLAG_NSS		0x80
+#define IPL_PB0_CCW_VM_FLAG_VP		0x40
+
+/* IPL Parameter Block 1 for additional SCP data */
+struct ipl_pb1_scp_data {
+	__u32 len;
+	__u8  pbt;
+	__u8  scp_data[];
+} __packed;
+
+/* IPL Report List header */
+struct ipl_rl_hdr {
+	__u32 len;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  version;
+	__u8  reserved2[8];
+} __packed;
+
+/* IPL Report Block header */
+struct ipl_rb_hdr {
+	__u32 len;
+	__u8  rbt;
+	__u8  reserved1[11];
+} __packed;
+
+/* IPL Report Block types */
+enum ipl_rbt {
+	IPL_RBT_CERTIFICATES = 1,
+	IPL_RBT_COMPONENTS = 2,
+};
+
+/* IPL Report Block for the certificate list */
+struct ipl_rb_certificate_entry {
+	__u64 addr;
+	__u64 len;
+} __packed;
+
+struct ipl_rb_certificates {
+	__u32 len;
+	__u8  rbt;
+	__u8  reserved1[11];
+	struct ipl_rb_certificate_entry entries[];
+} __packed;
+
+/* IPL Report Block for the component list */
+struct ipl_rb_component_entry {
+	__u64 addr;
+	__u64 len;
+	__u8  flags;
+	__u8  reserved1[5];
+	__u16 certificate_index;
+	__u8  reserved2[8];
+};
+
+#define IPL_RB_COMPONENT_FLAG_SIGNED	0x80
+#define IPL_RB_COMPONENT_FLAG_VERIFIED	0x40
+
+struct ipl_rb_components {
+	__u32 len;
+	__u8  rbt;
+	__u8  reserved1[11];
+	struct ipl_rb_component_entry entries[];
+} __packed;
+
+#endif
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 8a62c7f72e1b..b0478d01a0c5 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -39,6 +39,7 @@ CFLAGS_smp.o		:= -Wno-nonnull
 #
 CFLAGS_stacktrace.o	+= -fno-optimize-sibling-calls
 CFLAGS_dumpstack.o	+= -fno-optimize-sibling-calls
+CFLAGS_unwind_bc.o	+= -fno-optimize-sibling-calls
 
 #
 # Pass UTS_MACHINE for user_regset definition
@@ -51,7 +52,7 @@ obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
 obj-y	+= sysinfo.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
-obj-y	+= nospec-branch.o ipl_vmparm.o
+obj-y	+= nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
 
 extra-y				+= head64.o vmlinux.lds
 
@@ -77,6 +78,8 @@ obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 obj-$(CONFIG_KEXEC_FILE)	+= machine_kexec_file.o kexec_image.o
 obj-$(CONFIG_KEXEC_FILE)	+= kexec_elf.o
 
+obj-$(CONFIG_IMA)		+= ima_arch.o
+
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf_common.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o perf_regs.o
@@ -86,7 +89,7 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 
 # vdso
 obj-y				+= vdso64/
-obj-$(CONFIG_COMPAT)		+= vdso32/
+obj-$(CONFIG_COMPAT_VDSO)	+= vdso32/
 
 chkbss := head64.o early_nobss.o
 include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 164bec175628..41ac4ad21311 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -16,6 +16,7 @@
 #include <asm/pgtable.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
+#include <asm/stacktrace.h>
 
 int main(void)
 {
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index f268fca67e82..2f39ea57f358 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -28,6 +28,7 @@ ENTRY(s390_base_mcck_handler)
 1:	la	%r1,4095
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
 	lpswe	__LC_MCK_OLD_PSW
+ENDPROC(s390_base_mcck_handler)
 
 	.section .bss
 	.align 8
@@ -48,6 +49,7 @@ ENTRY(s390_base_ext_handler)
 1:	lmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	ni	__LC_EXT_OLD_PSW+1,0xfd	# clear wait state bit
 	lpswe	__LC_EXT_OLD_PSW
+ENDPROC(s390_base_ext_handler)
 
 	.section .bss
 	.align 8
@@ -68,6 +70,7 @@ ENTRY(s390_base_pgm_handler)
 	lmg	%r0,%r15,__LC_SAVE_AREA_SYNC
 	lpswe	__LC_PGM_OLD_PSW
 1:	lpswe	disabled_wait_psw-0b(%r13)
+ENDPROC(s390_base_pgm_handler)
 
 	.align	8
 disabled_wait_psw:
@@ -79,71 +82,3 @@ disabled_wait_psw:
 s390_base_pgm_handler_fn:
 	.quad	0
 	.previous
-
-#
-# Calls diag 308 subcode 1 and continues execution
-#
-ENTRY(diag308_reset)
-	larl	%r4,.Lctlregs		# Save control registers
-	stctg	%c0,%c15,0(%r4)
-	lg	%r2,0(%r4)		# Disable lowcore protection
-	nilh	%r2,0xefff
-	larl	%r4,.Lctlreg0
-	stg	%r2,0(%r4)
-	lctlg	%c0,%c0,0(%r4)
-	larl	%r4,.Lfpctl		# Floating point control register
-	stfpc	0(%r4)
-	larl	%r4,.Lprefix		# Save prefix register
-	stpx	0(%r4)
-	larl	%r4,.Lprefix_zero	# Set prefix register to 0
-	spx	0(%r4)
-	larl	%r4,.Lcontinue_psw	# Save PSW flags
-	epsw	%r2,%r3
-	stm	%r2,%r3,0(%r4)
-	larl	%r4,.Lrestart_psw	# Setup restart PSW at absolute 0
-	lghi	%r3,0
-	lg	%r4,0(%r4)		# Save PSW
-	sturg	%r4,%r3			# Use sturg, because of large pages
-	lghi	%r1,1
-	lghi	%r0,0
-	diag	%r0,%r1,0x308
-.Lrestart_part2:
-	lhi	%r0,0			# Load r0 with zero
-	lhi	%r1,2			# Use mode 2 = ESAME (dump)
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to ESAME mode
-	sam64				# Switch to 64 bit addressing mode
-	larl	%r4,.Lctlregs		# Restore control registers
-	lctlg	%c0,%c15,0(%r4)
-	larl	%r4,.Lfpctl		# Restore floating point ctl register
-	lfpc	0(%r4)
-	larl	%r4,.Lprefix		# Restore prefix register
-	spx	0(%r4)
-	larl	%r4,.Lcontinue_psw	# Restore PSW flags
-	lpswe	0(%r4)
-.Lcontinue:
-	BR_EX	%r14
-.align 16
-.Lrestart_psw:
-	.long	0x00080000,0x80000000 + .Lrestart_part2
-
-	.section .data..nosave,"aw",@progbits
-.align 8
-.Lcontinue_psw:
-	.quad	0,.Lcontinue
-	.previous
-
-	.section .bss
-.align 8
-.Lctlreg0:
-	.quad	0
-.Lctlregs:
-	.rept	16
-	.quad	0
-	.endr
-.Lfpctl:
-	.long	0
-.Lprefix:
-	.long	0
-.Lprefix_zero:
-	.long	0
-	.previous
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 7edaa733a77f..e9dac9a24d3f 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -13,6 +13,7 @@
 #include <linux/debugfs.h>
 #include <asm/diag.h>
 #include <asm/trace/diag.h>
+#include <asm/sections.h>
 
 struct diag_stat {
 	unsigned int counter[NR_DIAG_STAT];
@@ -49,6 +50,9 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
 	[DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" },
 };
 
+struct diag_ops __bootdata_preserved(diag_dma_ops);
+struct diag210 *__bootdata_preserved(__diag210_tmp_dma);
+
 static int show_diag_stat(struct seq_file *m, void *v)
 {
 	struct diag_stat *stat;
@@ -139,30 +143,10 @@ EXPORT_SYMBOL(diag_stat_inc_norecursion);
 /*
  * Diagnose 14: Input spool file manipulation
  */
-static inline int __diag14(unsigned long rx, unsigned long ry1,
-			   unsigned long subcode)
-{
-	register unsigned long _ry1 asm("2") = ry1;
-	register unsigned long _ry2 asm("3") = subcode;
-	int rc = 0;
-
-	asm volatile(
-		"   sam31\n"
-		"   diag    %2,2,0x14\n"
-		"   sam64\n"
-		"   ipm     %0\n"
-		"   srl     %0,28\n"
-		: "=d" (rc), "+d" (_ry2)
-		: "d" (rx), "d" (_ry1)
-		: "cc");
-
-	return rc;
-}
-
 int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
 {
 	diag_stat_inc(DIAG_STAT_X014);
-	return __diag14(rx, ry1, subcode);
+	return diag_dma_ops.diag14(rx, ry1, subcode);
 }
 EXPORT_SYMBOL(diag14);
 
@@ -195,30 +179,17 @@ EXPORT_SYMBOL(diag204);
  */
 int diag210(struct diag210 *addr)
 {
-	/*
-	 * diag 210 needs its data below the 2GB border, so we
-	 * use a static data area to be sure
-	 */
-	static struct diag210 diag210_tmp;
 	static DEFINE_SPINLOCK(diag210_lock);
 	unsigned long flags;
 	int ccode;
 
 	spin_lock_irqsave(&diag210_lock, flags);
-	diag210_tmp = *addr;
+	*__diag210_tmp_dma = *addr;
 
 	diag_stat_inc(DIAG_STAT_X210);
-	asm volatile(
-		"	lhi	%0,-1\n"
-		"	sam31\n"
-		"	diag	%1,0,0x210\n"
-		"0:	ipm	%0\n"
-		"	srl	%0,28\n"
-		"1:	sam64\n"
-		EX_TABLE(0b, 1b)
-		: "=&d" (ccode) : "a" (&diag210_tmp) : "cc", "memory");
-
-	*addr = diag210_tmp;
+	ccode = diag_dma_ops.diag210(__diag210_tmp_dma);
+
+	*addr = *__diag210_tmp_dma;
 	spin_unlock_irqrestore(&diag210_lock, flags);
 
 	return ccode;
@@ -243,27 +214,9 @@ EXPORT_SYMBOL(diag224);
 /*
  * Diagnose 26C: Access Certain System Information
  */
-static inline int __diag26c(void *req, void *resp, enum diag26c_sc subcode)
-{
-	register unsigned long _req asm("2") = (addr_t) req;
-	register unsigned long _resp asm("3") = (addr_t) resp;
-	register unsigned long _subcode asm("4") = subcode;
-	register unsigned long _rc asm("5") = -EOPNOTSUPP;
-
-	asm volatile(
-		"	sam31\n"
-		"	diag	%[rx],%[ry],0x26c\n"
-		"0:	sam64\n"
-		EX_TABLE(0b,0b)
-		: "+d" (_rc)
-		: [rx] "d" (_req), "d" (_resp), [ry] "d" (_subcode)
-		: "cc", "memory");
-	return _rc;
-}
-
 int diag26c(void *req, void *resp, enum diag26c_sc subcode)
 {
 	diag_stat_inc(DIAG_STAT_X26C);
-	return __diag26c(req, resp, subcode);
+	return diag_dma_ops.diag26c(req, resp, subcode);
 }
 EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index cb7f55bbe06e..9e87b68be21c 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -21,95 +21,124 @@
 #include <asm/debug.h>
 #include <asm/dis.h>
 #include <asm/ipl.h>
+#include <asm/unwind.h>
 
-/*
- * For dump_trace we have tree different stack to consider:
- *   - the panic stack which is used if the kernel stack has overflown
- *   - the asynchronous interrupt stack (cpu related)
- *   - the synchronous kernel stack (process related)
- * The stack trace can start at any of the three stacks and can potentially
- * touch all of them. The order is: panic stack, async stack, sync stack.
- */
-static unsigned long __no_sanitize_address
-__dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
-	     unsigned long low, unsigned long high)
+const char *stack_type_name(enum stack_type type)
 {
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-
-	while (1) {
-		if (sp < low || sp > high - sizeof(*sf))
-			return sp;
-		sf = (struct stack_frame *) sp;
-		if (func(data, sf->gprs[8], 0))
-			return sp;
-		/* Follow the backchain. */
-		while (1) {
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *) sp;
-			if (func(data, sf->gprs[8], 1))
-				return sp;
-		}
-		/* Zero backchain detected, check for interrupt frame. */
-		sp = (unsigned long) (sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *) sp;
-		if (!user_mode(regs)) {
-			if (func(data, regs->psw.addr, 1))
-				return sp;
-		}
-		low = sp;
-		sp = regs->gprs[15];
+	switch (type) {
+	case STACK_TYPE_TASK:
+		return "task";
+	case STACK_TYPE_IRQ:
+		return "irq";
+	case STACK_TYPE_NODAT:
+		return "nodat";
+	case STACK_TYPE_RESTART:
+		return "restart";
+	default:
+		return "unknown";
 	}
 }
 
-void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
-		unsigned long sp)
+static inline bool in_stack(unsigned long sp, struct stack_info *info,
+			    enum stack_type type, unsigned long low,
+			    unsigned long high)
+{
+	if (sp < low || sp >= high)
+		return false;
+	info->type = type;
+	info->begin = low;
+	info->end = high;
+	return true;
+}
+
+static bool in_task_stack(unsigned long sp, struct task_struct *task,
+			  struct stack_info *info)
+{
+	unsigned long stack;
+
+	stack = (unsigned long) task_stack_page(task);
+	return in_stack(sp, info, STACK_TYPE_TASK, stack, stack + THREAD_SIZE);
+}
+
+static bool in_irq_stack(unsigned long sp, struct stack_info *info)
 {
-	unsigned long frame_size;
+	unsigned long frame_size, top;
 
 	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-#ifdef CONFIG_CHECK_STACK
-	sp = __dump_trace(func, data, sp,
-			  S390_lowcore.nodat_stack + frame_size - THREAD_SIZE,
-			  S390_lowcore.nodat_stack + frame_size);
-#endif
-	sp = __dump_trace(func, data, sp,
-			  S390_lowcore.async_stack + frame_size - THREAD_SIZE,
-			  S390_lowcore.async_stack + frame_size);
-	task = task ?: current;
-	__dump_trace(func, data, sp,
-		     (unsigned long)task_stack_page(task),
-		     (unsigned long)task_stack_page(task) + THREAD_SIZE);
+	top = S390_lowcore.async_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_IRQ, top - THREAD_SIZE, top);
+}
+
+static bool in_nodat_stack(unsigned long sp, struct stack_info *info)
+{
+	unsigned long frame_size, top;
+
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	top = S390_lowcore.nodat_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top);
 }
-EXPORT_SYMBOL_GPL(dump_trace);
 
-static int show_address(void *data, unsigned long address, int reliable)
+static bool in_restart_stack(unsigned long sp, struct stack_info *info)
 {
-	if (reliable)
-		printk(" [<%016lx>] %pSR \n", address, (void *)address);
-	else
-		printk("([<%016lx>] %pSR)\n", address, (void *)address);
+	unsigned long frame_size, top;
+
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	top = S390_lowcore.restart_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_RESTART, top - THREAD_SIZE, top);
+}
+
+int get_stack_info(unsigned long sp, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask)
+{
+	if (!sp)
+		goto unknown;
+
+	task = task ? : current;
+
+	/* Check per-task stack */
+	if (in_task_stack(sp, task, info))
+		goto recursion_check;
+
+	if (task != current)
+		goto unknown;
+
+	/* Check per-cpu stacks */
+	if (!in_irq_stack(sp, info) &&
+	    !in_nodat_stack(sp, info) &&
+	    !in_restart_stack(sp, info))
+		goto unknown;
+
+recursion_check:
+	/*
+	 * Make sure we don't iterate through any given stack more than once.
+	 * If it comes up a second time then there's something wrong going on:
+	 * just break out and report an unknown stack type.
+	 */
+	if (*visit_mask & (1UL << info->type)) {
+		printk_deferred_once(KERN_WARNING
+			"WARNING: stack recursion on stack type %d\n",
+			info->type);
+		goto unknown;
+	}
+	*visit_mask |= 1UL << info->type;
 	return 0;
+unknown:
+	info->type = STACK_TYPE_UNKNOWN;
+	return -EINVAL;
 }
 
 void show_stack(struct task_struct *task, unsigned long *stack)
 {
-	unsigned long sp = (unsigned long) stack;
+	struct unwind_state state;
 
-	if (!sp)
-		sp = task ? task->thread.ksp : current_stack_pointer();
 	printk("Call Trace:\n");
-	dump_trace(show_address, NULL, task, sp);
 	if (!task)
 		task = current;
-	debug_show_held_locks(task);
+	unwind_for_each_frame(&state, task, NULL, (unsigned long) stack)
+		printk(state.reliable ? " [<%016lx>] %pSR \n" :
+					"([<%016lx>] %pSR)\n",
+		       state.ip, (void *) state.ip);
+	debug_show_held_locks(task ? : current);
 }
 
 static void show_last_breaking_event(struct pt_regs *regs)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index d6edf45f93b9..629f173f60cd 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,6 +30,7 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
+#include <asm/pci_insn.h>
 #include "entry.h"
 
 /*
@@ -138,9 +139,9 @@ static void early_pgm_check_handler(void)
 	unsigned long addr;
 
 	addr = S390_lowcore.program_old_psw.addr;
-	fixup = search_exception_tables(addr);
+	fixup = s390_search_extables(addr);
 	if (!fixup)
-		disabled_wait(0);
+		disabled_wait();
 	/* Disable low address protection before storing into lowcore. */
 	__ctl_store(cr0, 0, 0);
 	cr0_new = cr0 & ~(1UL << 28);
@@ -235,6 +236,7 @@ static __init void detect_machine_facilities(void)
 		clock_comparator_max = -1ULL >> 1;
 		__ctl_set_bit(0, 53);
 	}
+	enable_mio_ctl();
 }
 
 static inline void save_vector_registers(void)
@@ -296,7 +298,7 @@ static void __init check_image_bootable(void)
 	sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
 	sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
 	sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
-	disabled_wait(0xbadb007);
+	disabled_wait();
 }
 
 void __init startup_init(void)
@@ -309,7 +311,6 @@ void __init startup_init(void)
 	setup_facility_list();
 	detect_machine_type();
 	setup_arch_string();
-	ipl_store_parameters();
 	setup_boot_command_line();
 	detect_diag9c();
 	detect_diag44();
diff --git a/arch/s390/kernel/early_nobss.c b/arch/s390/kernel/early_nobss.c
index 8d73f7fae16e..52a3ef959341 100644
--- a/arch/s390/kernel/early_nobss.c
+++ b/arch/s390/kernel/early_nobss.c
@@ -25,7 +25,7 @@ static void __init reset_tod_clock(void)
 		return;
 	/* TOD clock not running. Set the clock to Unix Epoch. */
 	if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
-		disabled_wait(0);
+		disabled_wait();
 
 	memset(tod_clock_base, 0, 16);
 	*(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 583d65ef5007..3f4d272577d3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -224,6 +224,7 @@ ENTRY(__bpon)
 	.globl __bpon
 	BPON
 	BR_EX	%r14
+ENDPROC(__bpon)
 
 /*
  * Scheduler resume function, called by switch_to
@@ -248,6 +249,7 @@ ENTRY(__switch_to)
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
 	BR_EX	%r14
+ENDPROC(__switch_to)
 
 .L__critical_start:
 
@@ -324,6 +326,7 @@ sie_exit:
 	EX_TABLE(.Lrewind_pad4,.Lsie_fault)
 	EX_TABLE(.Lrewind_pad2,.Lsie_fault)
 	EX_TABLE(sie_exit,.Lsie_fault)
+ENDPROC(sie64a)
 EXPORT_SYMBOL(sie64a)
 EXPORT_SYMBOL(sie_exit)
 #endif
@@ -358,19 +361,19 @@ ENTRY(system_call)
 	# load address of system call table
 	lg	%r10,__THREAD_sysc_table(%r13,%r12)
 	llgh	%r8,__PT_INT_CODE+2(%r11)
-	slag	%r8,%r8,2			# shift and test for svc 0
+	slag	%r8,%r8,3			# shift and test for svc 0
 	jnz	.Lsysc_nr_ok
 	# svc 0: system call number in %r1
 	llgfr	%r1,%r1				# clear high word in r1
 	cghi	%r1,NR_syscalls
 	jnl	.Lsysc_nr_ok
 	sth	%r1,__PT_INT_CODE+2(%r11)
-	slag	%r8,%r1,2
+	slag	%r8,%r1,3
 .Lsysc_nr_ok:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	stg	%r2,__PT_ORIG_GPR2(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
-	lgf	%r9,0(%r8,%r10)			# get system call add.
+	lg	%r9,0(%r8,%r10)			# get system call add.
 	TSTMSK	__TI_flags(%r12),_TIF_TRACE
 	jnz	.Lsysc_tracesys
 	BASR_EX	%r14,%r9			# call sys_xxxx
@@ -556,8 +559,8 @@ ENTRY(system_call)
 	lghi	%r0,NR_syscalls
 	clgr	%r0,%r2
 	jnh	.Lsysc_tracenogo
-	sllg	%r8,%r2,2
-	lgf	%r9,0(%r8,%r10)
+	sllg	%r8,%r2,3
+	lg	%r9,0(%r8,%r10)
 .Lsysc_tracego:
 	lmg	%r3,%r7,__PT_R3(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
@@ -570,6 +573,7 @@ ENTRY(system_call)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	larl	%r14,.Lsysc_return
 	jg	do_syscall_trace_exit
+ENDPROC(system_call)
 
 #
 # a new process exits the kernel with ret_from_fork
@@ -584,10 +588,16 @@ ENTRY(ret_from_fork)
 	jne	.Lsysc_tracenogo
 	# it's a kernel thread
 	lmg	%r9,%r10,__PT_R9(%r11)	# load gprs
+	la	%r2,0(%r10)
+	BASR_EX	%r14,%r9
+	j	.Lsysc_tracenogo
+ENDPROC(ret_from_fork)
+
 ENTRY(kernel_thread_starter)
 	la	%r2,0(%r10)
 	BASR_EX	%r14,%r9
 	j	.Lsysc_tracenogo
+ENDPROC(kernel_thread_starter)
 
 /*
  * Program check handler routine
@@ -665,9 +675,9 @@ ENTRY(pgm_check_handler)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
 	nill	%r10,0x007f
-	sll	%r10,2
+	sll	%r10,3
 	je	.Lpgm_return
-	lgf	%r9,0(%r10,%r1)		# load address of handler routine
+	lg	%r9,0(%r10,%r1)		# load address of handler routine
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	BASR_EX	%r14,%r9		# branch to interrupt-handler
 .Lpgm_return:
@@ -698,6 +708,7 @@ ENTRY(pgm_check_handler)
 	stg	%r14,__LC_RETURN_PSW+8
 	lghi	%r14,_PIF_SYSCALL | _PIF_PER_TRAP
 	lpswe	__LC_RETURN_PSW		# branch to .Lsysc_per and enable irqs
+ENDPROC(pgm_check_handler)
 
 /*
  * IO interrupt handler routine
@@ -926,6 +937,7 @@ ENTRY(io_int_handler)
 	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
 	j	.Lio_return
+ENDPROC(io_int_handler)
 
 /*
  * External interrupt handler routine
@@ -965,6 +977,7 @@ ENTRY(ext_int_handler)
 	lghi	%r3,EXT_INTERRUPT
 	brasl	%r14,do_IRQ
 	j	.Lio_return
+ENDPROC(ext_int_handler)
 
 /*
  * Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
@@ -989,6 +1002,7 @@ ENTRY(psw_idle)
 	lpswe	__SF_EMPTY(%r15)
 	BR_EX	%r14
 .Lpsw_idle_end:
+ENDPROC(psw_idle)
 
 /*
  * Store floating-point controls and floating-point or vector register
@@ -1031,6 +1045,7 @@ ENTRY(save_fpu_regs)
 .Lsave_fpu_regs_exit:
 	BR_EX	%r14
 .Lsave_fpu_regs_end:
+ENDPROC(save_fpu_regs)
 EXPORT_SYMBOL(save_fpu_regs)
 
 /*
@@ -1077,6 +1092,7 @@ load_fpu_regs:
 .Lload_fpu_regs_exit:
 	BR_EX	%r14
 .Lload_fpu_regs_end:
+ENDPROC(load_fpu_regs)
 
 .L__critical_end:
 
@@ -1206,6 +1222,7 @@ ENTRY(mcck_int_handler)
 	lg	%r15,__LC_NODAT_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	j	.Lmcck_skip
+ENDPROC(mcck_int_handler)
 
 #
 # PSW restart interrupt handler
@@ -1232,6 +1249,7 @@ ENTRY(restart_int_handler)
 2:	sigp	%r4,%r3,SIGP_STOP		# sigp stop to current cpu
 	brc	2,2b
 3:	j	3b
+ENDPROC(restart_int_handler)
 
 	.section .kprobes.text, "ax"
 
@@ -1241,7 +1259,7 @@ ENTRY(restart_int_handler)
  * No need to properly save the registers, we are going to panic anyway.
  * Setup a pt_regs so that show_trace can provide a good call trace.
  */
-stack_overflow:
+ENTRY(stack_overflow)
 	lg	%r15,__LC_NODAT_STACK	# change to panic stack
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
@@ -1251,9 +1269,10 @@ stack_overflow:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	jg	kernel_stack_overflow
+ENDPROC(stack_overflow)
 #endif
 
-cleanup_critical:
+ENTRY(cleanup_critical)
 #if IS_ENABLED(CONFIG_KVM)
 	clg	%r9,BASED(.Lcleanup_table_sie)	# .Lsie_gmap
 	jl	0f
@@ -1289,6 +1308,7 @@ cleanup_critical:
 	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
 	jl	.Lcleanup_load_fpu_regs
 0:	BR_EX	%r14,%r11
+ENDPROC(cleanup_critical)
 
 	.align	8
 .Lcleanup_table:
@@ -1512,7 +1532,7 @@ cleanup_critical:
 	.quad   .Lsie_skip - .Lsie_entry
 #endif
 	.section .rodata, "a"
-#define SYSCALL(esame,emu)	.long __s390x_ ## esame
+#define SYSCALL(esame,emu)	.quad __s390x_ ## esame
 	.globl	sys_call_table
 sys_call_table:
 #include "asm/syscall_table.h"
@@ -1520,7 +1540,7 @@ sys_call_table:
 
 #ifdef CONFIG_COMPAT
 
-#define SYSCALL(esame,emu)	.long __s390_ ## emu
+#define SYSCALL(esame,emu)	.quad __s390_ ## emu
 	.globl	sys_call_table_emu
 sys_call_table_emu:
 #include "asm/syscall_table.h"
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index c3816ae108b0..20420c2b8a14 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -65,7 +65,7 @@ int setup_profiling_timer(unsigned int multiplier);
 void __init time_init(void);
 int pfn_is_nosave(unsigned long);
 void s390_early_resume(void);
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip);
 
 struct s390_mmap_arg_struct;
 struct fadvise64_64_args;
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 39b13d71a8fe..1bb85f60c0dd 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -201,17 +201,18 @@ device_initcall(ftrace_plt_init);
  * Hook the return address and push it in the stack of return addresses
  * in current thread info.
  */
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
+unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp,
+				    unsigned long ip)
 {
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 	ip -= MCOUNT_INSN_SIZE;
-	if (!function_graph_enter(parent, ip, 0, NULL))
-		parent = (unsigned long) return_to_handler;
+	if (!function_graph_enter(ra, ip, 0, (void *) sp))
+		ra = (unsigned long) return_to_handler;
 out:
-	return parent;
+	return ra;
 }
 NOKPROBE_SYMBOL(prepare_ftrace_return);
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 56491e636eab..5aea1a527443 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -26,7 +26,6 @@ ENTRY(startup_continue)
 0:	larl	%r1,tod_clock_base
 	mvc	0(16,%r1),__LC_BOOT_CLOCK
 	larl	%r13,.LPG1		# get base
-	lctlg	%c0,%c15,.Lctl-.LPG1(%r13)	# load control registers
 	larl	%r0,boot_vdso_data
 	stg	%r0,__LC_VDSO_PER_CPU
 #
@@ -61,22 +60,6 @@ ENTRY(startup_continue)
 
 	.align	16
 .LPG1:
-.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
-	.quad	0			# cr1: primary space segment table
-	.quad	.Lduct			# cr2: dispatchable unit control table
-	.quad	0			# cr3: instruction authorization
-	.quad	0xffff			# cr4: instruction authorization
-	.quad	.Lduct			# cr5: primary-aste origin
-	.quad	0			# cr6:	I/O interrupts
-	.quad	0			# cr7:	secondary space segment table
-	.quad	0			# cr8:	access registers translation
-	.quad	0			# cr9:	tracing off
-	.quad	0			# cr10: tracing off
-	.quad	0			# cr11: tracing off
-	.quad	0			# cr12: tracing off
-	.quad	0			# cr13: home space segment table
-	.quad	0xc0000000		# cr14: machine check handling off
-	.quad	.Llinkage_stack		# cr15: linkage stack operations
 .Lpcmsk:.quad	0x0000000180000000
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
@@ -84,14 +67,5 @@ ENTRY(startup_continue)
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
-.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
-	.long	0,0,0,0,0,0,0,0
-.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
-	.align	128
-.Lduald:.rept	8
-	.long	0x80000000,0,0,0	# invalid access-list entries
-	.endr
-.Llinkage_stack:
-	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
 .Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/ima_arch.c b/arch/s390/kernel/ima_arch.c
new file mode 100644
index 000000000000..f3c3e6e1c5d3
--- /dev/null
+++ b/arch/s390/kernel/ima_arch.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ima.h>
+#include <asm/boot_data.h>
+
+bool arch_ima_get_secureboot(void)
+{
+	return ipl_secure_flag;
+}
+
+const char * const *arch_get_ima_policy(void)
+{
+	return NULL;
+}
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 18a5d6317acc..d836af3ccc38 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -31,6 +31,7 @@
 #include <asm/os_info.h>
 #include <asm/sections.h>
 #include <asm/boot_data.h>
+#include <asm/uv.h>
 #include "entry.h"
 
 #define IPL_PARM_BLOCK_VERSION 0
@@ -119,11 +120,15 @@ static char *dump_type_str(enum dump_type type)
 	}
 }
 
-struct ipl_parameter_block __bootdata(early_ipl_block);
-int __bootdata(early_ipl_block_valid);
+int __bootdata_preserved(ipl_block_valid);
+struct ipl_parameter_block __bootdata_preserved(ipl_block);
+int __bootdata_preserved(ipl_secure_flag);
 
-static int ipl_block_valid;
-static struct ipl_parameter_block ipl_block;
+unsigned long __bootdata_preserved(ipl_cert_list_addr);
+unsigned long __bootdata_preserved(ipl_cert_list_size);
+
+unsigned long __bootdata(early_ipl_comp_list_addr);
+unsigned long __bootdata(early_ipl_comp_list_size);
 
 static int reipl_capabilities = IPL_TYPE_UNKNOWN;
 
@@ -246,11 +251,11 @@ static __init enum ipl_type get_ipl_type(void)
 	if (!ipl_block_valid)
 		return IPL_TYPE_UNKNOWN;
 
-	switch (ipl_block.hdr.pbt) {
-	case DIAG308_IPL_TYPE_CCW:
+	switch (ipl_block.pb0_hdr.pbt) {
+	case IPL_PBT_CCW:
 		return IPL_TYPE_CCW;
-	case DIAG308_IPL_TYPE_FCP:
-		if (ipl_block.ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP)
+	case IPL_PBT_FCP:
+		if (ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
 			return IPL_TYPE_FCP_DUMP;
 		else
 			return IPL_TYPE_FCP;
@@ -269,12 +274,35 @@ static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr,
 
 static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type);
 
+static ssize_t ipl_secure_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%i\n", !!ipl_secure_flag);
+}
+
+static struct kobj_attribute sys_ipl_secure_attr =
+	__ATTR(secure, 0444, ipl_secure_show, NULL);
+
+static ssize_t ipl_has_secure_show(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *page)
+{
+	if (MACHINE_IS_LPAR)
+		return sprintf(page, "%i\n", !!sclp.has_sipl);
+	else if (MACHINE_IS_VM)
+		return sprintf(page, "%i\n", !!sclp.has_sipl_g2);
+	else
+		return sprintf(page, "%i\n", 0);
+}
+
+static struct kobj_attribute sys_ipl_has_secure_attr =
+	__ATTR(has_secure, 0444, ipl_has_secure_show, NULL);
+
 static ssize_t ipl_vm_parm_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *page)
 {
 	char parm[DIAG308_VMPARM_SIZE + 1] = {};
 
-	if (ipl_block_valid && (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW))
+	if (ipl_block_valid && (ipl_block.pb0_hdr.pbt == IPL_PBT_CCW))
 		ipl_block_get_ascii_vmparm(parm, sizeof(parm), &ipl_block);
 	return sprintf(page, "%s\n", parm);
 }
@@ -287,12 +315,11 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
 {
 	switch (ipl_info.type) {
 	case IPL_TYPE_CCW:
-		return sprintf(page, "0.%x.%04x\n", ipl_block.ipl_info.ccw.ssid,
-			       ipl_block.ipl_info.ccw.devno);
+		return sprintf(page, "0.%x.%04x\n", ipl_block.ccw.ssid,
+			       ipl_block.ccw.devno);
 	case IPL_TYPE_FCP:
 	case IPL_TYPE_FCP_DUMP:
-		return sprintf(page, "0.0.%04x\n",
-			       ipl_block.ipl_info.fcp.devno);
+		return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno);
 	default:
 		return 0;
 	}
@@ -316,8 +343,8 @@ static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj,
 				 struct bin_attribute *attr, char *buf,
 				 loff_t off, size_t count)
 {
-	unsigned int size = ipl_block.ipl_info.fcp.scp_data_len;
-	void *scp_data = &ipl_block.ipl_info.fcp.scp_data;
+	unsigned int size = ipl_block.fcp.scp_data_len;
+	void *scp_data = &ipl_block.fcp.scp_data;
 
 	return memory_read_from_buffer(buf, count, &off, scp_data, size);
 }
@@ -333,13 +360,13 @@ static struct bin_attribute *ipl_fcp_bin_attrs[] = {
 /* FCP ipl device attributes */
 
 DEFINE_IPL_ATTR_RO(ipl_fcp, wwpn, "0x%016llx\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.wwpn);
+		   (unsigned long long)ipl_block.fcp.wwpn);
 DEFINE_IPL_ATTR_RO(ipl_fcp, lun, "0x%016llx\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.lun);
+		   (unsigned long long)ipl_block.fcp.lun);
 DEFINE_IPL_ATTR_RO(ipl_fcp, bootprog, "%lld\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.bootprog);
+		   (unsigned long long)ipl_block.fcp.bootprog);
 DEFINE_IPL_ATTR_RO(ipl_fcp, br_lba, "%lld\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.br_lba);
+		   (unsigned long long)ipl_block.fcp.br_lba);
 
 static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *page)
@@ -365,6 +392,8 @@ static struct attribute *ipl_fcp_attrs[] = {
 	&sys_ipl_fcp_bootprog_attr.attr,
 	&sys_ipl_fcp_br_lba_attr.attr,
 	&sys_ipl_ccw_loadparm_attr.attr,
+	&sys_ipl_secure_attr.attr,
+	&sys_ipl_has_secure_attr.attr,
 	NULL,
 };
 
@@ -380,6 +409,8 @@ static struct attribute *ipl_ccw_attrs_vm[] = {
 	&sys_ipl_device_attr.attr,
 	&sys_ipl_ccw_loadparm_attr.attr,
 	&sys_ipl_vm_parm_attr.attr,
+	&sys_ipl_secure_attr.attr,
+	&sys_ipl_has_secure_attr.attr,
 	NULL,
 };
 
@@ -387,6 +418,8 @@ static struct attribute *ipl_ccw_attrs_lpar[] = {
 	&sys_ipl_type_attr.attr,
 	&sys_ipl_device_attr.attr,
 	&sys_ipl_ccw_loadparm_attr.attr,
+	&sys_ipl_secure_attr.attr,
+	&sys_ipl_has_secure_attr.attr,
 	NULL,
 };
 
@@ -495,14 +528,14 @@ static ssize_t reipl_generic_vmparm_store(struct ipl_parameter_block *ipb,
 		if (!(isalnum(buf[i]) || isascii(buf[i]) || isprint(buf[i])))
 			return -EINVAL;
 
-	memset(ipb->ipl_info.ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
-	ipb->ipl_info.ccw.vm_parm_len = ip_len;
+	memset(ipb->ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
+	ipb->ccw.vm_parm_len = ip_len;
 	if (ip_len > 0) {
-		ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
-		memcpy(ipb->ipl_info.ccw.vm_parm, buf, ip_len);
-		ASCEBC(ipb->ipl_info.ccw.vm_parm, ip_len);
+		ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
+		memcpy(ipb->ccw.vm_parm, buf, ip_len);
+		ASCEBC(ipb->ccw.vm_parm, ip_len);
 	} else {
-		ipb->ipl_info.ccw.vm_flags &= ~DIAG308_VM_FLAGS_VP_VALID;
+		ipb->ccw.vm_flags &= ~IPL_PB0_CCW_VM_FLAG_VP;
 	}
 
 	return len;
@@ -549,8 +582,8 @@ static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj,
 				      struct bin_attribute *attr,
 				      char *buf, loff_t off, size_t count)
 {
-	size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len;
-	void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data;
+	size_t size = reipl_block_fcp->fcp.scp_data_len;
+	void *scp_data = reipl_block_fcp->fcp.scp_data;
 
 	return memory_read_from_buffer(buf, count, &off, scp_data, size);
 }
@@ -566,17 +599,17 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
 	if (off)
 		return -EINVAL;
 
-	memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf, count);
+	memcpy(reipl_block_fcp->fcp.scp_data, buf, count);
 	if (scpdata_len % 8) {
 		padding = 8 - (scpdata_len % 8);
-		memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len,
+		memset(reipl_block_fcp->fcp.scp_data + scpdata_len,
 		       0, padding);
 		scpdata_len += padding;
 	}
 
-	reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len;
-	reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len;
-	reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len;
+	reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN + scpdata_len;
+	reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN + scpdata_len;
+	reipl_block_fcp->fcp.scp_data_len = scpdata_len;
 
 	return count;
 }
@@ -590,20 +623,20 @@ static struct bin_attribute *reipl_fcp_bin_attrs[] = {
 };
 
 DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n",
-		   reipl_block_fcp->ipl_info.fcp.wwpn);
+		   reipl_block_fcp->fcp.wwpn);
 DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n",
-		   reipl_block_fcp->ipl_info.fcp.lun);
+		   reipl_block_fcp->fcp.lun);
 DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n",
-		   reipl_block_fcp->ipl_info.fcp.bootprog);
+		   reipl_block_fcp->fcp.bootprog);
 DEFINE_IPL_ATTR_RW(reipl_fcp, br_lba, "%lld\n", "%lld\n",
-		   reipl_block_fcp->ipl_info.fcp.br_lba);
+		   reipl_block_fcp->fcp.br_lba);
 DEFINE_IPL_ATTR_RW(reipl_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
-		   reipl_block_fcp->ipl_info.fcp.devno);
+		   reipl_block_fcp->fcp.devno);
 
 static void reipl_get_ascii_loadparm(char *loadparm,
 				     struct ipl_parameter_block *ibp)
 {
-	memcpy(loadparm, ibp->hdr.loadparm, LOADPARM_LEN);
+	memcpy(loadparm, ibp->common.loadparm, LOADPARM_LEN);
 	EBCASC(loadparm, LOADPARM_LEN);
 	loadparm[LOADPARM_LEN] = 0;
 	strim(loadparm);
@@ -638,11 +671,11 @@ static ssize_t reipl_generic_loadparm_store(struct ipl_parameter_block *ipb,
 		return -EINVAL;
 	}
 	/* initialize loadparm with blanks */
-	memset(ipb->hdr.loadparm, ' ', LOADPARM_LEN);
+	memset(ipb->common.loadparm, ' ', LOADPARM_LEN);
 	/* copy and convert to ebcdic */
-	memcpy(ipb->hdr.loadparm, buf, lp_len);
-	ASCEBC(ipb->hdr.loadparm, LOADPARM_LEN);
-	ipb->hdr.flags |= DIAG308_FLAGS_LP_VALID;
+	memcpy(ipb->common.loadparm, buf, lp_len);
+	ASCEBC(ipb->common.loadparm, LOADPARM_LEN);
+	ipb->common.flags |= IPL_PB0_FLAG_LOADPARM;
 	return len;
 }
 
@@ -680,7 +713,7 @@ static struct attribute_group reipl_fcp_attr_group = {
 };
 
 /* CCW reipl device attributes */
-DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ipl_info.ccw);
+DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw);
 
 /* NSS wrapper */
 static ssize_t reipl_nss_loadparm_show(struct kobject *kobj,
@@ -742,7 +775,7 @@ static struct attribute_group reipl_ccw_attr_group_lpar = {
 static void reipl_get_ascii_nss_name(char *dst,
 				     struct ipl_parameter_block *ipb)
 {
-	memcpy(dst, ipb->ipl_info.ccw.nss_name, NSS_NAME_SIZE);
+	memcpy(dst, ipb->ccw.nss_name, NSS_NAME_SIZE);
 	EBCASC(dst, NSS_NAME_SIZE);
 	dst[NSS_NAME_SIZE] = 0;
 }
@@ -770,16 +803,14 @@ static ssize_t reipl_nss_name_store(struct kobject *kobj,
 	if (nss_len > NSS_NAME_SIZE)
 		return -EINVAL;
 
-	memset(reipl_block_nss->ipl_info.ccw.nss_name, 0x40, NSS_NAME_SIZE);
+	memset(reipl_block_nss->ccw.nss_name, 0x40, NSS_NAME_SIZE);
 	if (nss_len > 0) {
-		reipl_block_nss->ipl_info.ccw.vm_flags |=
-			DIAG308_VM_FLAGS_NSS_VALID;
-		memcpy(reipl_block_nss->ipl_info.ccw.nss_name, buf, nss_len);
-		ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
-		EBC_TOUPPER(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
+		reipl_block_nss->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_NSS;
+		memcpy(reipl_block_nss->ccw.nss_name, buf, nss_len);
+		ASCEBC(reipl_block_nss->ccw.nss_name, nss_len);
+		EBC_TOUPPER(reipl_block_nss->ccw.nss_name, nss_len);
 	} else {
-		reipl_block_nss->ipl_info.ccw.vm_flags &=
-			~DIAG308_VM_FLAGS_NSS_VALID;
+		reipl_block_nss->ccw.vm_flags &= ~IPL_PB0_CCW_VM_FLAG_NSS;
 	}
 
 	return len;
@@ -866,15 +897,21 @@ static void __reipl_run(void *unused)
 {
 	switch (reipl_type) {
 	case IPL_TYPE_CCW:
+		uv_set_shared(__pa(reipl_block_ccw));
 		diag308(DIAG308_SET, reipl_block_ccw);
+		uv_remove_shared(__pa(reipl_block_ccw));
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_FCP:
+		uv_set_shared(__pa(reipl_block_fcp));
 		diag308(DIAG308_SET, reipl_block_fcp);
+		uv_remove_shared(__pa(reipl_block_fcp));
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_NSS:
+		uv_set_shared(__pa(reipl_block_nss));
 		diag308(DIAG308_SET, reipl_block_nss);
+		uv_remove_shared(__pa(reipl_block_nss));
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_UNKNOWN:
@@ -883,7 +920,7 @@ static void __reipl_run(void *unused)
 	case IPL_TYPE_FCP_DUMP:
 		break;
 	}
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 }
 
 static void reipl_run(struct shutdown_trigger *trigger)
@@ -893,10 +930,10 @@ static void reipl_run(struct shutdown_trigger *trigger)
 
 static void reipl_block_ccw_init(struct ipl_parameter_block *ipb)
 {
-	ipb->hdr.len = IPL_PARM_BLK_CCW_LEN;
+	ipb->hdr.len = IPL_BP_CCW_LEN;
 	ipb->hdr.version = IPL_PARM_BLOCK_VERSION;
-	ipb->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
-	ipb->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+	ipb->pb0_hdr.len = IPL_BP0_CCW_LEN;
+	ipb->pb0_hdr.pbt = IPL_PBT_CCW;
 }
 
 static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
@@ -904,21 +941,20 @@ static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
 	/* LOADPARM */
 	/* check if read scp info worked and set loadparm */
 	if (sclp_ipl_info.is_valid)
-		memcpy(ipb->hdr.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
+		memcpy(ipb->ccw.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
 	else
 		/* read scp info failed: set empty loadparm (EBCDIC blanks) */
-		memset(ipb->hdr.loadparm, 0x40, LOADPARM_LEN);
-	ipb->hdr.flags = DIAG308_FLAGS_LP_VALID;
+		memset(ipb->ccw.loadparm, 0x40, LOADPARM_LEN);
+	ipb->ccw.flags = IPL_PB0_FLAG_LOADPARM;
 
 	/* VM PARM */
 	if (MACHINE_IS_VM && ipl_block_valid &&
-	    (ipl_block.ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID)) {
+	    (ipl_block.ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP)) {
 
-		ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
-		ipb->ipl_info.ccw.vm_parm_len =
-					ipl_block.ipl_info.ccw.vm_parm_len;
-		memcpy(ipb->ipl_info.ccw.vm_parm,
-		       ipl_block.ipl_info.ccw.vm_parm, DIAG308_VMPARM_SIZE);
+		ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
+		ipb->ccw.vm_parm_len = ipl_block.ccw.vm_parm_len;
+		memcpy(ipb->ccw.vm_parm,
+		       ipl_block.ccw.vm_parm, DIAG308_VMPARM_SIZE);
 	}
 }
 
@@ -958,8 +994,8 @@ static int __init reipl_ccw_init(void)
 
 	reipl_block_ccw_init(reipl_block_ccw);
 	if (ipl_info.type == IPL_TYPE_CCW) {
-		reipl_block_ccw->ipl_info.ccw.ssid = ipl_block.ipl_info.ccw.ssid;
-		reipl_block_ccw->ipl_info.ccw.devno = ipl_block.ipl_info.ccw.devno;
+		reipl_block_ccw->ccw.ssid = ipl_block.ccw.ssid;
+		reipl_block_ccw->ccw.devno = ipl_block.ccw.devno;
 		reipl_block_ccw_fill_parms(reipl_block_ccw);
 	}
 
@@ -997,14 +1033,14 @@ static int __init reipl_fcp_init(void)
 		 * is invalid in the SCSI IPL parameter block, so take it
 		 * always from sclp_ipl_info.
 		 */
-		memcpy(reipl_block_fcp->hdr.loadparm, sclp_ipl_info.loadparm,
+		memcpy(reipl_block_fcp->fcp.loadparm, sclp_ipl_info.loadparm,
 		       LOADPARM_LEN);
 	} else {
-		reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+		reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN;
 		reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
-		reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
-		reipl_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
-		reipl_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_IPL;
+		reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN;
+		reipl_block_fcp->fcp.pbt = IPL_PBT_FCP;
+		reipl_block_fcp->fcp.opt = IPL_PB0_FCP_OPT_IPL;
 	}
 	reipl_capabilities |= IPL_TYPE_FCP;
 	return 0;
@@ -1022,10 +1058,10 @@ static int __init reipl_type_init(void)
 	/*
 	 * If we have an OS info reipl block, this will be used
 	 */
-	if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_FCP) {
+	if (reipl_block->pb0_hdr.pbt == IPL_PBT_FCP) {
 		memcpy(reipl_block_fcp, reipl_block, size);
 		reipl_type = IPL_TYPE_FCP;
-	} else if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_CCW) {
+	} else if (reipl_block->pb0_hdr.pbt == IPL_PBT_CCW) {
 		memcpy(reipl_block_ccw, reipl_block, size);
 		reipl_type = IPL_TYPE_CCW;
 	}
@@ -1070,15 +1106,15 @@ static struct shutdown_action __refdata reipl_action = {
 /* FCP dump device attributes */
 
 DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n",
-		   dump_block_fcp->ipl_info.fcp.wwpn);
+		   dump_block_fcp->fcp.wwpn);
 DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n",
-		   dump_block_fcp->ipl_info.fcp.lun);
+		   dump_block_fcp->fcp.lun);
 DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n",
-		   dump_block_fcp->ipl_info.fcp.bootprog);
+		   dump_block_fcp->fcp.bootprog);
 DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n",
-		   dump_block_fcp->ipl_info.fcp.br_lba);
+		   dump_block_fcp->fcp.br_lba);
 DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
-		   dump_block_fcp->ipl_info.fcp.devno);
+		   dump_block_fcp->fcp.devno);
 
 static struct attribute *dump_fcp_attrs[] = {
 	&sys_dump_fcp_device_attr.attr,
@@ -1095,7 +1131,7 @@ static struct attribute_group dump_fcp_attr_group = {
 };
 
 /* CCW dump device attributes */
-DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ipl_info.ccw);
+DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ccw);
 
 static struct attribute *dump_ccw_attrs[] = {
 	&sys_dump_ccw_device_attr.attr,
@@ -1145,7 +1181,9 @@ static struct kset *dump_kset;
 
 static void diag308_dump(void *dump_block)
 {
+	uv_set_shared(__pa(dump_block));
 	diag308(DIAG308_SET, dump_block);
+	uv_remove_shared(__pa(dump_block));
 	while (1) {
 		if (diag308(DIAG308_LOAD_NORMAL_DUMP, NULL) != 0x302)
 			break;
@@ -1187,10 +1225,10 @@ static int __init dump_ccw_init(void)
 		free_page((unsigned long)dump_block_ccw);
 		return rc;
 	}
-	dump_block_ccw->hdr.len = IPL_PARM_BLK_CCW_LEN;
+	dump_block_ccw->hdr.len = IPL_BP_CCW_LEN;
 	dump_block_ccw->hdr.version = IPL_PARM_BLOCK_VERSION;
-	dump_block_ccw->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
-	dump_block_ccw->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+	dump_block_ccw->ccw.len = IPL_BP0_CCW_LEN;
+	dump_block_ccw->ccw.pbt = IPL_PBT_CCW;
 	dump_capabilities |= DUMP_TYPE_CCW;
 	return 0;
 }
@@ -1209,11 +1247,11 @@ static int __init dump_fcp_init(void)
 		free_page((unsigned long)dump_block_fcp);
 		return rc;
 	}
-	dump_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+	dump_block_fcp->hdr.len = IPL_BP_FCP_LEN;
 	dump_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
-	dump_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
-	dump_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
-	dump_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_DUMP;
+	dump_block_fcp->fcp.len = IPL_BP0_FCP_LEN;
+	dump_block_fcp->fcp.pbt = IPL_PBT_FCP;
+	dump_block_fcp->fcp.opt = IPL_PB0_FCP_OPT_DUMP;
 	dump_capabilities |= DUMP_TYPE_FCP;
 	return 0;
 }
@@ -1337,7 +1375,7 @@ static void stop_run(struct shutdown_trigger *trigger)
 {
 	if (strcmp(trigger->name, ON_PANIC_STR) == 0 ||
 	    strcmp(trigger->name, ON_RESTART_STR) == 0)
-		disabled_wait((unsigned long) __builtin_return_address(0));
+		disabled_wait();
 	smp_stop_cpu();
 }
 
@@ -1572,7 +1610,7 @@ static int __init s390_ipl_init(void)
 	 * READ SCP info provides the correct value.
 	 */
 	if (memcmp(sclp_ipl_info.loadparm, str, sizeof(str)) == 0 && ipl_block_valid)
-		memcpy(sclp_ipl_info.loadparm, ipl_block.hdr.loadparm, LOADPARM_LEN);
+		memcpy(sclp_ipl_info.loadparm, ipl_block.ccw.loadparm, LOADPARM_LEN);
 	shutdown_actions_init();
 	shutdown_triggers_init();
 	return 0;
@@ -1657,15 +1695,15 @@ void __init setup_ipl(void)
 	ipl_info.type = get_ipl_type();
 	switch (ipl_info.type) {
 	case IPL_TYPE_CCW:
-		ipl_info.data.ccw.dev_id.ssid = ipl_block.ipl_info.ccw.ssid;
-		ipl_info.data.ccw.dev_id.devno = ipl_block.ipl_info.ccw.devno;
+		ipl_info.data.ccw.dev_id.ssid = ipl_block.ccw.ssid;
+		ipl_info.data.ccw.dev_id.devno = ipl_block.ccw.devno;
 		break;
 	case IPL_TYPE_FCP:
 	case IPL_TYPE_FCP_DUMP:
 		ipl_info.data.fcp.dev_id.ssid = 0;
-		ipl_info.data.fcp.dev_id.devno = ipl_block.ipl_info.fcp.devno;
-		ipl_info.data.fcp.wwpn = ipl_block.ipl_info.fcp.wwpn;
-		ipl_info.data.fcp.lun = ipl_block.ipl_info.fcp.lun;
+		ipl_info.data.fcp.dev_id.devno = ipl_block.fcp.devno;
+		ipl_info.data.fcp.wwpn = ipl_block.fcp.wwpn;
+		ipl_info.data.fcp.lun = ipl_block.fcp.lun;
 		break;
 	case IPL_TYPE_NSS:
 	case IPL_TYPE_UNKNOWN:
@@ -1675,14 +1713,6 @@ void __init setup_ipl(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
 }
 
-void __init ipl_store_parameters(void)
-{
-	if (early_ipl_block_valid) {
-		memcpy(&ipl_block, &early_ipl_block, sizeof(ipl_block));
-		ipl_block_valid = 1;
-	}
-}
-
 void s390_reset_system(void)
 {
 	/* Disable prefixing */
@@ -1690,5 +1720,139 @@ void s390_reset_system(void)
 
 	/* Disable lowcore protection */
 	__ctl_clear_bit(0, 28);
-	diag308_reset();
+	diag_dma_ops.diag308_reset();
+}
+
+#ifdef CONFIG_KEXEC_FILE
+
+int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf,
+			     unsigned char flags, unsigned short cert)
+{
+	struct ipl_report_component *comp;
+
+	comp = vzalloc(sizeof(*comp));
+	if (!comp)
+		return -ENOMEM;
+	list_add_tail(&comp->list, &report->components);
+
+	comp->entry.addr = kbuf->mem;
+	comp->entry.len = kbuf->memsz;
+	comp->entry.flags = flags;
+	comp->entry.certificate_index = cert;
+
+	report->size += sizeof(comp->entry);
+
+	return 0;
+}
+
+int ipl_report_add_certificate(struct ipl_report *report, void *key,
+			       unsigned long addr, unsigned long len)
+{
+	struct ipl_report_certificate *cert;
+
+	cert = vzalloc(sizeof(*cert));
+	if (!cert)
+		return -ENOMEM;
+	list_add_tail(&cert->list, &report->certificates);
+
+	cert->entry.addr = addr;
+	cert->entry.len = len;
+	cert->key = key;
+
+	report->size += sizeof(cert->entry);
+	report->size += cert->entry.len;
+
+	return 0;
+}
+
+struct ipl_report *ipl_report_init(struct ipl_parameter_block *ipib)
+{
+	struct ipl_report *report;
+
+	report = vzalloc(sizeof(*report));
+	if (!report)
+		return ERR_PTR(-ENOMEM);
+
+	report->ipib = ipib;
+	INIT_LIST_HEAD(&report->components);
+	INIT_LIST_HEAD(&report->certificates);
+
+	report->size = ALIGN(ipib->hdr.len, 8);
+	report->size += sizeof(struct ipl_rl_hdr);
+	report->size += sizeof(struct ipl_rb_components);
+	report->size += sizeof(struct ipl_rb_certificates);
+
+	return report;
+}
+
+void *ipl_report_finish(struct ipl_report *report)
+{
+	struct ipl_report_certificate *cert;
+	struct ipl_report_component *comp;
+	struct ipl_rb_certificates *certs;
+	struct ipl_parameter_block *ipib;
+	struct ipl_rb_components *comps;
+	struct ipl_rl_hdr *rl_hdr;
+	void *buf, *ptr;
+
+	buf = vzalloc(report->size);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+	ptr = buf;
+
+	memcpy(ptr, report->ipib, report->ipib->hdr.len);
+	ipib = ptr;
+	if (ipl_secure_flag)
+		ipib->hdr.flags |= IPL_PL_FLAG_SIPL;
+	ipib->hdr.flags |= IPL_PL_FLAG_IPLSR;
+	ptr += report->ipib->hdr.len;
+	ptr = PTR_ALIGN(ptr, 8);
+
+	rl_hdr = ptr;
+	ptr += sizeof(*rl_hdr);
+
+	comps = ptr;
+	comps->rbt = IPL_RBT_COMPONENTS;
+	ptr += sizeof(*comps);
+	list_for_each_entry(comp, &report->components, list) {
+		memcpy(ptr, &comp->entry, sizeof(comp->entry));
+		ptr += sizeof(comp->entry);
+	}
+	comps->len = ptr - (void *)comps;
+
+	certs = ptr;
+	certs->rbt = IPL_RBT_CERTIFICATES;
+	ptr += sizeof(*certs);
+	list_for_each_entry(cert, &report->certificates, list) {
+		memcpy(ptr, &cert->entry, sizeof(cert->entry));
+		ptr += sizeof(cert->entry);
+	}
+	certs->len = ptr - (void *)certs;
+	rl_hdr->len = ptr - (void *)rl_hdr;
+
+	list_for_each_entry(cert, &report->certificates, list) {
+		memcpy(ptr, cert->key, cert->entry.len);
+		ptr += cert->entry.len;
+	}
+
+	BUG_ON(ptr > buf + report->size);
+	return buf;
+}
+
+int ipl_report_free(struct ipl_report *report)
+{
+	struct ipl_report_component *comp, *ncomp;
+	struct ipl_report_certificate *cert, *ncert;
+
+	list_for_each_entry_safe(comp, ncomp, &report->components, list)
+		vfree(comp);
+
+	list_for_each_entry_safe(cert, ncert, &report->certificates, list)
+		vfree(cert);
+
+	vfree(report);
+
+	return 0;
 }
+
+#endif
diff --git a/arch/s390/kernel/ipl_vmparm.c b/arch/s390/kernel/ipl_vmparm.c
index 411838c0a0af..af43535a976d 100644
--- a/arch/s390/kernel/ipl_vmparm.c
+++ b/arch/s390/kernel/ipl_vmparm.c
@@ -11,11 +11,11 @@ size_t ipl_block_get_ascii_vmparm(char *dest, size_t size,
 	char has_lowercase = 0;
 
 	len = 0;
-	if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) &&
-	    (ipb->ipl_info.ccw.vm_parm_len > 0)) {
+	if ((ipb->ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP) &&
+	    (ipb->ccw.vm_parm_len > 0)) {
 
-		len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len);
-		memcpy(dest, ipb->ipl_info.ccw.vm_parm, len);
+		len = min_t(size_t, size - 1, ipb->ccw.vm_parm_len);
+		memcpy(dest, ipb->ccw.vm_parm, len);
 		/* If at least one character is lowercase, we assume mixed
 		 * case; otherwise we convert everything to lowercase.
 		 */
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 0cd5a5f96729..8371855042dc 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -26,6 +26,7 @@
 #include <asm/lowcore.h>
 #include <asm/irq.h>
 #include <asm/hw_irq.h>
+#include <asm/stacktrace.h>
 #include "entry.h"
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -73,7 +74,6 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQEXT_CMC, .name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"},
 	{.irq = IRQEXT_FTP, .name = "FTP", .desc = "[EXT] HMC FTP Service"},
 	{.irq = IRQIO_CIO,  .name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"},
-	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"},
 	{.irq = IRQIO_DAS,  .name = "DAS", .desc = "[I/O] DASD"},
 	{.irq = IRQIO_C15,  .name = "C15", .desc = "[I/O] 3215"},
 	{.irq = IRQIO_C70,  .name = "C70", .desc = "[I/O] 3270"},
@@ -81,14 +81,16 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQIO_VMR,  .name = "VMR", .desc = "[I/O] Unit Record Devices"},
 	{.irq = IRQIO_LCS,  .name = "LCS", .desc = "[I/O] LCS"},
 	{.irq = IRQIO_CTC,  .name = "CTC", .desc = "[I/O] CTC"},
-	{.irq = IRQIO_APB,  .name = "APB", .desc = "[I/O] AP Bus"},
 	{.irq = IRQIO_ADM,  .name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	{.irq = IRQIO_CSC,  .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
-	{.irq = IRQIO_PCI,  .name = "PCI", .desc = "[I/O] PCI Interrupt" },
-	{.irq = IRQIO_MSI,  .name = "MSI", .desc = "[I/O] MSI Interrupt" },
 	{.irq = IRQIO_VIR,  .name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
-	{.irq = IRQIO_VAI,  .name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"},
-	{.irq = IRQIO_GAL,  .name = "GAL", .desc = "[I/O] GIB Alert"},
+	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[AIO] QDIO Adapter Interrupt"},
+	{.irq = IRQIO_APB,  .name = "APB", .desc = "[AIO] AP Bus"},
+	{.irq = IRQIO_PCF,  .name = "PCF", .desc = "[AIO] PCI Floating Interrupt"},
+	{.irq = IRQIO_PCD,  .name = "PCD", .desc = "[AIO] PCI Directed Interrupt"},
+	{.irq = IRQIO_MSI,  .name = "MSI", .desc = "[AIO] MSI Interrupt"},
+	{.irq = IRQIO_VAI,  .name = "VAI", .desc = "[AIO] Virtual I/O Devices AI"},
+	{.irq = IRQIO_GAL,  .name = "GAL", .desc = "[AIO] GIB Alert"},
 	{.irq = NMI_NMI,    .name = "NMI", .desc = "[NMI] Machine Check"},
 	{.irq = CPU_RST,    .name = "RST", .desc = "[CPU] CPU Restart"},
 };
@@ -116,6 +118,34 @@ void do_IRQ(struct pt_regs *regs, int irq)
 	set_irq_regs(old_regs);
 }
 
+static void show_msi_interrupt(struct seq_file *p, int irq)
+{
+	struct irq_desc *desc;
+	unsigned long flags;
+	int cpu;
+
+	irq_lock_sparse();
+	desc = irq_to_desc(irq);
+	if (!desc)
+		goto out;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	seq_printf(p, "%3d: ", irq);
+	for_each_online_cpu(cpu)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+
+	if (desc->irq_data.chip)
+		seq_printf(p, " %8s", desc->irq_data.chip->name);
+
+	if (desc->action)
+		seq_printf(p, "  %s", desc->action->name);
+
+	seq_putc(p, '\n');
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+out:
+	irq_unlock_sparse();
+}
+
 /*
  * show_interrupts is needed by /proc/interrupts.
  */
@@ -128,7 +158,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (index == 0) {
 		seq_puts(p, "           ");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "CPU%d       ", cpu);
+			seq_printf(p, "CPU%-8d", cpu);
 		seq_putc(p, '\n');
 	}
 	if (index < NR_IRQS_BASE) {
@@ -139,9 +169,10 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 		goto out;
 	}
-	if (index > NR_IRQS_BASE)
+	if (index < nr_irqs) {
+		show_msi_interrupt(p, index);
 		goto out;
-
+	}
 	for (index = 0; index < NR_ARCH_IRQS; index++) {
 		seq_printf(p, "%s: ", irqclass_sub_desc[index].name);
 		irq = irqclass_sub_desc[index].irq;
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
index 5a286b012043..6d0635ceddd0 100644
--- a/arch/s390/kernel/kexec_elf.c
+++ b/arch/s390/kernel/kexec_elf.c
@@ -10,19 +10,26 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
-static int kexec_file_add_elf_kernel(struct kimage *image,
-				     struct s390_load_data *data,
-				     char *kernel, unsigned long kernel_len)
+static int kexec_file_add_kernel_elf(struct kimage *image,
+				     struct s390_load_data *data)
 {
 	struct kexec_buf buf;
 	const Elf_Ehdr *ehdr;
 	const Elf_Phdr *phdr;
+	Elf_Addr entry;
+	void *kernel;
 	int i, ret;
 
+	kernel = image->kernel_buf;
 	ehdr = (Elf_Ehdr *)kernel;
 	buf.image = image;
+	if (image->type == KEXEC_TYPE_CRASH)
+		entry = STARTUP_KDUMP_OFFSET;
+	else
+		entry = ehdr->e_entry;
 
 	phdr = (void *)ehdr + ehdr->e_phoff;
 	for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
@@ -33,30 +40,27 @@ static int kexec_file_add_elf_kernel(struct kimage *image,
 		buf.bufsz = phdr->p_filesz;
 
 		buf.mem = ALIGN(phdr->p_paddr, phdr->p_align);
+		if (image->type == KEXEC_TYPE_CRASH)
+			buf.mem += crashk_res.start;
 		buf.memsz = phdr->p_memsz;
+		data->memsz = ALIGN(data->memsz, phdr->p_align) + buf.memsz;
 
-		if (phdr->p_paddr == 0) {
+		if (entry - phdr->p_paddr < phdr->p_memsz) {
 			data->kernel_buf = buf.buffer;
-			data->memsz += STARTUP_NORMAL_OFFSET;
-
-			buf.buffer += STARTUP_NORMAL_OFFSET;
-			buf.bufsz -= STARTUP_NORMAL_OFFSET;
-
-			buf.mem += STARTUP_NORMAL_OFFSET;
-			buf.memsz -= STARTUP_NORMAL_OFFSET;
+			data->kernel_mem = buf.mem;
+			data->parm = buf.buffer + PARMAREA;
 		}
 
-		if (image->type == KEXEC_TYPE_CRASH)
-			buf.mem += crashk_res.start;
-
+		ipl_report_add_component(data->report, &buf,
+					 IPL_RB_COMPONENT_FLAG_SIGNED |
+					 IPL_RB_COMPONENT_FLAG_VERIFIED,
+					 IPL_RB_CERT_UNKNOWN);
 		ret = kexec_add_buffer(&buf);
 		if (ret)
 			return ret;
-
-		data->memsz += buf.memsz;
 	}
 
-	return 0;
+	return data->memsz ? 0 : -EINVAL;
 }
 
 static void *s390_elf_load(struct kimage *image,
@@ -64,11 +68,10 @@ static void *s390_elf_load(struct kimage *image,
 			   char *initrd, unsigned long initrd_len,
 			   char *cmdline, unsigned long cmdline_len)
 {
-	struct s390_load_data data = {0};
 	const Elf_Ehdr *ehdr;
 	const Elf_Phdr *phdr;
 	size_t size;
-	int i, ret;
+	int i;
 
 	/* image->fobs->probe already checked for valid ELF magic number. */
 	ehdr = (Elf_Ehdr *)kernel;
@@ -101,24 +104,7 @@ static void *s390_elf_load(struct kimage *image,
 	if (size > kernel_len)
 		return ERR_PTR(-EINVAL);
 
-	ret = kexec_file_add_elf_kernel(image, &data, kernel, kernel_len);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (!data.memsz)
-		return ERR_PTR(-EINVAL);
-
-	if (initrd) {
-		ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
-		if (ret)
-			return ERR_PTR(ret);
-	}
-
-	ret = kexec_file_add_purgatory(image, &data);
-	if (ret)
-		return ERR_PTR(ret);
-
-	return kexec_file_update_kernel(image, &data);
+	return kexec_file_add_components(image, kexec_file_add_kernel_elf);
 }
 
 static int s390_elf_probe(const char *buf, unsigned long len)
@@ -144,4 +130,7 @@ static int s390_elf_probe(const char *buf, unsigned long len)
 const struct kexec_file_ops s390_kexec_elf_ops = {
 	.probe = s390_elf_probe,
 	.load = s390_elf_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 };
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
index 3800852595e8..58318bf89fd9 100644
--- a/arch/s390/kernel/kexec_image.c
+++ b/arch/s390/kernel/kexec_image.c
@@ -10,31 +10,34 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
-static int kexec_file_add_image_kernel(struct kimage *image,
-				       struct s390_load_data *data,
-				       char *kernel, unsigned long kernel_len)
+static int kexec_file_add_kernel_image(struct kimage *image,
+				       struct s390_load_data *data)
 {
 	struct kexec_buf buf;
-	int ret;
 
 	buf.image = image;
 
-	buf.buffer = kernel + STARTUP_NORMAL_OFFSET;
-	buf.bufsz = kernel_len - STARTUP_NORMAL_OFFSET;
+	buf.buffer = image->kernel_buf;
+	buf.bufsz = image->kernel_buf_len;
 
-	buf.mem = STARTUP_NORMAL_OFFSET;
+	buf.mem = 0;
 	if (image->type == KEXEC_TYPE_CRASH)
 		buf.mem += crashk_res.start;
 	buf.memsz = buf.bufsz;
 
-	ret = kexec_add_buffer(&buf);
+	data->kernel_buf = image->kernel_buf;
+	data->kernel_mem = buf.mem;
+	data->parm = image->kernel_buf + PARMAREA;
+	data->memsz += buf.memsz;
 
-	data->kernel_buf = kernel;
-	data->memsz += buf.memsz + STARTUP_NORMAL_OFFSET;
-
-	return ret;
+	ipl_report_add_component(data->report, &buf,
+				 IPL_RB_COMPONENT_FLAG_SIGNED |
+				 IPL_RB_COMPONENT_FLAG_VERIFIED,
+				 IPL_RB_CERT_UNKNOWN);
+	return kexec_add_buffer(&buf);
 }
 
 static void *s390_image_load(struct kimage *image,
@@ -42,24 +45,7 @@ static void *s390_image_load(struct kimage *image,
 			     char *initrd, unsigned long initrd_len,
 			     char *cmdline, unsigned long cmdline_len)
 {
-	struct s390_load_data data = {0};
-	int ret;
-
-	ret = kexec_file_add_image_kernel(image, &data, kernel, kernel_len);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (initrd) {
-		ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
-		if (ret)
-			return ERR_PTR(ret);
-	}
-
-	ret = kexec_file_add_purgatory(image, &data);
-	if (ret)
-		return ERR_PTR(ret);
-
-	return kexec_file_update_kernel(image, &data);
+	return kexec_file_add_components(image, kexec_file_add_kernel_image);
 }
 
 static int s390_image_probe(const char *buf, unsigned long len)
@@ -73,4 +59,7 @@ static int s390_image_probe(const char *buf, unsigned long len)
 const struct kexec_file_ops s390_kexec_image_ops = {
 	.probe = s390_image_probe,
 	.load = s390_image_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 };
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 7c0a095e9c5f..6f1388391620 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -27,29 +27,30 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = { };
 
-DEFINE_INSN_CACHE_OPS(dmainsn);
+DEFINE_INSN_CACHE_OPS(s390_insn);
 
-static void *alloc_dmainsn_page(void)
-{
-	void *page;
+static int insn_page_in_use;
+static char insn_page[PAGE_SIZE] __aligned(PAGE_SIZE);
 
-	page = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
-	if (page)
-		set_memory_x((unsigned long) page, 1);
-	return page;
+static void *alloc_s390_insn_page(void)
+{
+	if (xchg(&insn_page_in_use, 1) == 1)
+		return NULL;
+	set_memory_x((unsigned long) &insn_page, 1);
+	return &insn_page;
 }
 
-static void free_dmainsn_page(void *page)
+static void free_s390_insn_page(void *page)
 {
 	set_memory_nx((unsigned long) page, 1);
-	free_page((unsigned long)page);
+	xchg(&insn_page_in_use, 0);
 }
 
-struct kprobe_insn_cache kprobe_dmainsn_slots = {
-	.mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex),
-	.alloc = alloc_dmainsn_page,
-	.free = free_dmainsn_page,
-	.pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages),
+struct kprobe_insn_cache kprobe_s390_insn_slots = {
+	.mutex = __MUTEX_INITIALIZER(kprobe_s390_insn_slots.mutex),
+	.alloc = alloc_s390_insn_page,
+	.free = free_s390_insn_page,
+	.pages = LIST_HEAD_INIT(kprobe_s390_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 };
 
@@ -102,7 +103,7 @@ static int s390_get_insn_slot(struct kprobe *p)
 	 */
 	p->ainsn.insn = NULL;
 	if (is_kernel_addr(p->addr))
-		p->ainsn.insn = get_dmainsn_slot();
+		p->ainsn.insn = get_s390_insn_slot();
 	else if (is_module_addr(p->addr))
 		p->ainsn.insn = get_insn_slot();
 	return p->ainsn.insn ? 0 : -ENOMEM;
@@ -114,7 +115,7 @@ static void s390_free_insn_slot(struct kprobe *p)
 	if (!p->ainsn.insn)
 		return;
 	if (is_kernel_addr(p->addr))
-		free_dmainsn_slot(p->ainsn.insn, 0);
+		free_s390_insn_slot(p->ainsn.insn, 0);
 	else
 		free_insn_slot(p->ainsn.insn, 0);
 	p->ainsn.insn = NULL;
@@ -572,7 +573,7 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		entry = search_exception_tables(regs->psw.addr);
+		entry = s390_search_extables(regs->psw.addr);
 		if (entry) {
 			regs->psw.addr = extable_fixup(entry);
 			return 1;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index cb582649aba6..8a1ae140c5e2 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/os_info.h>
 #include <asm/set_memory.h>
+#include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/nmi.h>
 
@@ -95,7 +96,7 @@ static void __do_machine_kdump(void *image)
 	start_kdump(1);
 
 	/* Die if start_kdump returns */
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 }
 
 /*
@@ -253,6 +254,9 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
 	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
+	vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
+	vmcoreinfo_append_str("EDMA=%lx\n", __edma);
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 }
 
 void machine_shutdown(void)
@@ -280,7 +284,7 @@ static void __do_machine_kexec(void *data)
 	(*data_mover)(&image->head, image->start);
 
 	/* Die if kexec returns */
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 }
 
 /*
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 32023b4f9dc0..fbdd3ea73667 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -8,7 +8,12 @@
  */
 
 #include <linux/elf.h>
+#include <linux/errno.h>
 #include <linux/kexec.h>
+#include <linux/module.h>
+#include <linux/verification.h>
+#include <asm/boot_data.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
 const struct kexec_file_ops * const kexec_file_loaders[] = {
@@ -17,38 +22,78 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 	NULL,
 };
 
-int *kexec_file_update_kernel(struct kimage *image,
-			      struct s390_load_data *data)
-{
-	unsigned long *loc;
-
-	if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE)
-		return ERR_PTR(-EINVAL);
-
-	if (image->cmdline_buf_len)
-		memcpy(data->kernel_buf + COMMAND_LINE_OFFSET,
-		       image->cmdline_buf, image->cmdline_buf_len);
-
-	if (image->type == KEXEC_TYPE_CRASH) {
-		loc = (unsigned long *)(data->kernel_buf + OLDMEM_BASE_OFFSET);
-		*loc = crashk_res.start;
-
-		loc = (unsigned long *)(data->kernel_buf + OLDMEM_SIZE_OFFSET);
-		*loc = crashk_res.end - crashk_res.start + 1;
-	}
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+/*
+ * Module signature information block.
+ *
+ * The constituents of the signature section are, in order:
+ *
+ *	- Signer's name
+ *	- Key identifier
+ *	- Signature data
+ *	- Information block
+ */
+struct module_signature {
+	u8	algo;		/* Public-key crypto algorithm [0] */
+	u8	hash;		/* Digest algorithm [0] */
+	u8	id_type;	/* Key identifier type [PKEY_ID_PKCS7] */
+	u8	signer_len;	/* Length of signer's name [0] */
+	u8	key_id_len;	/* Length of key identifier [0] */
+	u8	__pad[3];
+	__be32	sig_len;	/* Length of signature data */
+};
 
-	if (image->initrd_buf) {
-		loc = (unsigned long *)(data->kernel_buf + INITRD_START_OFFSET);
-		*loc = data->initrd_load_addr;
+#define PKEY_ID_PKCS7 2
 
-		loc = (unsigned long *)(data->kernel_buf + INITRD_SIZE_OFFSET);
-		*loc = image->initrd_buf_len;
+int s390_verify_sig(const char *kernel, unsigned long kernel_len)
+{
+	const unsigned long marker_len = sizeof(MODULE_SIG_STRING) - 1;
+	struct module_signature *ms;
+	unsigned long sig_len;
+
+	/* Skip signature verification when not secure IPLed. */
+	if (!ipl_secure_flag)
+		return 0;
+
+	if (marker_len > kernel_len)
+		return -EKEYREJECTED;
+
+	if (memcmp(kernel + kernel_len - marker_len, MODULE_SIG_STRING,
+		   marker_len))
+		return -EKEYREJECTED;
+	kernel_len -= marker_len;
+
+	ms = (void *)kernel + kernel_len - sizeof(*ms);
+	kernel_len -= sizeof(*ms);
+
+	sig_len = be32_to_cpu(ms->sig_len);
+	if (sig_len >= kernel_len)
+		return -EKEYREJECTED;
+	kernel_len -= sig_len;
+
+	if (ms->id_type != PKEY_ID_PKCS7)
+		return -EKEYREJECTED;
+
+	if (ms->algo != 0 ||
+	    ms->hash != 0 ||
+	    ms->signer_len != 0 ||
+	    ms->key_id_len != 0 ||
+	    ms->__pad[0] != 0 ||
+	    ms->__pad[1] != 0 ||
+	    ms->__pad[2] != 0) {
+		return -EBADMSG;
 	}
 
-	return NULL;
+	return verify_pkcs7_signature(kernel, kernel_len,
+				      kernel + kernel_len, sig_len,
+				      VERIFY_USE_PLATFORM_KEYRING,
+				      VERIFYING_MODULE_SIGNATURE,
+				      NULL, NULL);
 }
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 
-static int kexec_file_update_purgatory(struct kimage *image)
+static int kexec_file_update_purgatory(struct kimage *image,
+				       struct s390_load_data *data)
 {
 	u64 entry, type;
 	int ret;
@@ -90,7 +135,8 @@ static int kexec_file_update_purgatory(struct kimage *image)
 	return ret;
 }
 
-int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
+static int kexec_file_add_purgatory(struct kimage *image,
+				    struct s390_load_data *data)
 {
 	struct kexec_buf buf;
 	int ret;
@@ -105,21 +151,21 @@ int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
 	ret = kexec_load_purgatory(image, &buf);
 	if (ret)
 		return ret;
+	data->memsz += buf.memsz;
 
-	ret = kexec_file_update_purgatory(image);
-	return ret;
+	return kexec_file_update_purgatory(image, data);
 }
 
-int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
-			  char *initrd, unsigned long initrd_len)
+static int kexec_file_add_initrd(struct kimage *image,
+				 struct s390_load_data *data)
 {
 	struct kexec_buf buf;
 	int ret;
 
 	buf.image = image;
 
-	buf.buffer = initrd;
-	buf.bufsz = initrd_len;
+	buf.buffer = image->initrd_buf;
+	buf.bufsz = image->initrd_buf_len;
 
 	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
 	buf.mem = data->memsz;
@@ -127,11 +173,115 @@ int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
 		buf.mem += crashk_res.start;
 	buf.memsz = buf.bufsz;
 
-	data->initrd_load_addr = buf.mem;
+	data->parm->initrd_start = buf.mem;
+	data->parm->initrd_size = buf.memsz;
 	data->memsz += buf.memsz;
 
 	ret = kexec_add_buffer(&buf);
-	return ret;
+	if (ret)
+		return ret;
+
+	return ipl_report_add_component(data->report, &buf, 0, 0);
+}
+
+static int kexec_file_add_ipl_report(struct kimage *image,
+				     struct s390_load_data *data)
+{
+	__u32 *lc_ipl_parmblock_ptr;
+	unsigned int len, ncerts;
+	struct kexec_buf buf;
+	unsigned long addr;
+	void *ptr, *end;
+
+	buf.image = image;
+
+	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+	buf.mem = data->memsz;
+	if (image->type == KEXEC_TYPE_CRASH)
+		buf.mem += crashk_res.start;
+
+	ptr = (void *)ipl_cert_list_addr;
+	end = ptr + ipl_cert_list_size;
+	ncerts = 0;
+	while (ptr < end) {
+		ncerts++;
+		len = *(unsigned int *)ptr;
+		ptr += sizeof(len);
+		ptr += len;
+	}
+
+	addr = data->memsz + data->report->size;
+	addr += ncerts * sizeof(struct ipl_rb_certificate_entry);
+	ptr = (void *)ipl_cert_list_addr;
+	while (ptr < end) {
+		len = *(unsigned int *)ptr;
+		ptr += sizeof(len);
+		ipl_report_add_certificate(data->report, ptr, addr, len);
+		addr += len;
+		ptr += len;
+	}
+
+	buf.buffer = ipl_report_finish(data->report);
+	buf.bufsz = data->report->size;
+	buf.memsz = buf.bufsz;
+
+	data->memsz += buf.memsz;
+
+	lc_ipl_parmblock_ptr =
+		data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
+	*lc_ipl_parmblock_ptr = (__u32)buf.mem;
+
+	return kexec_add_buffer(&buf);
+}
+
+void *kexec_file_add_components(struct kimage *image,
+				int (*add_kernel)(struct kimage *image,
+						  struct s390_load_data *data))
+{
+	struct s390_load_data data = {0};
+	int ret;
+
+	data.report = ipl_report_init(&ipl_block);
+	if (IS_ERR(data.report))
+		return data.report;
+
+	ret = add_kernel(image, &data);
+	if (ret)
+		goto out;
+
+	if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE) {
+		ret = -EINVAL;
+		goto out;
+	}
+	memcpy(data.parm->command_line, image->cmdline_buf,
+	       image->cmdline_buf_len);
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		data.parm->oldmem_base = crashk_res.start;
+		data.parm->oldmem_size = crashk_res.end - crashk_res.start + 1;
+	}
+
+	if (image->initrd_buf) {
+		ret = kexec_file_add_initrd(image, &data);
+		if (ret)
+			goto out;
+	}
+
+	ret = kexec_file_add_purgatory(image, &data);
+	if (ret)
+		goto out;
+
+	if (data.kernel_mem == 0) {
+		unsigned long restart_psw =  0x0008000080000000UL;
+		restart_psw += image->start;
+		memcpy(data.kernel_buf, &restart_psw, sizeof(restart_psw));
+		image->start = 0;
+	}
+
+	ret = kexec_file_add_ipl_report(image, &data);
+out:
+	ipl_report_free(data.report);
+	return ERR_PTR(ret);
 }
 
 int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
@@ -140,7 +290,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 				     const Elf_Shdr *symtab)
 {
 	Elf_Rela *relas;
-	int i;
+	int i, r_type;
 
 	relas = (void *)pi->ehdr + relsec->sh_offset;
 
@@ -174,46 +324,8 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 
 		addr = section->sh_addr + relas[i].r_offset;
 
-		switch (ELF64_R_TYPE(relas[i].r_info)) {
-		case R_390_8:		/* Direct 8 bit.   */
-			*(u8 *)loc = val;
-			break;
-		case R_390_12:		/* Direct 12 bit.  */
-			*(u16 *)loc &= 0xf000;
-			*(u16 *)loc |= val & 0xfff;
-			break;
-		case R_390_16:		/* Direct 16 bit.  */
-			*(u16 *)loc = val;
-			break;
-		case R_390_20:		/* Direct 20 bit.  */
-			*(u32 *)loc &= 0xf00000ff;
-			*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
-			*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
-			break;
-		case R_390_32:		/* Direct 32 bit.  */
-			*(u32 *)loc = val;
-			break;
-		case R_390_64:		/* Direct 64 bit.  */
-			*(u64 *)loc = val;
-			break;
-		case R_390_PC16:	/* PC relative 16 bit.	*/
-			*(u16 *)loc = (val - addr);
-			break;
-		case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
-			*(u16 *)loc = (val - addr) >> 1;
-			break;
-		case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
-			*(u32 *)loc = (val - addr) >> 1;
-			break;
-		case R_390_PC32:	/* PC relative 32 bit.	*/
-			*(u32 *)loc = (val - addr);
-			break;
-		case R_390_PC64:	/* PC relative 64 bit.	*/
-			*(u64 *)loc = (val - addr);
-			break;
-		default:
-			break;
-		}
+		r_type = ELF64_R_TYPE(relas[i].r_info);
+		arch_kexec_do_relocs(r_type, loc, val, addr);
 	}
 	return 0;
 }
@@ -225,10 +337,8 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 	 * load memory in head.S will be accessed, e.g. to register the next
 	 * command line. If the next kernel were smaller the current kernel
 	 * will panic at load.
-	 *
-	 * 0x11000 = sizeof(head.S)
 	 */
-	if (buf_len < 0x11000)
+	if (buf_len < HEAD_END)
 		return -ENOEXEC;
 
 	return kexec_image_probe_default(image, buf, buf_len);
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
new file mode 100644
index 000000000000..1dded39239f8
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/elf.h>
+
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+			 unsigned long addr)
+{
+	switch (r_type) {
+	case R_390_NONE:
+		break;
+	case R_390_8:		/* Direct 8 bit.   */
+		*(u8 *)loc = val;
+		break;
+	case R_390_12:		/* Direct 12 bit.  */
+		*(u16 *)loc &= 0xf000;
+		*(u16 *)loc |= val & 0xfff;
+		break;
+	case R_390_16:		/* Direct 16 bit.  */
+		*(u16 *)loc = val;
+		break;
+	case R_390_20:		/* Direct 20 bit.  */
+		*(u32 *)loc &= 0xf00000ff;
+		*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
+		*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
+		break;
+	case R_390_32:		/* Direct 32 bit.  */
+		*(u32 *)loc = val;
+		break;
+	case R_390_64:		/* Direct 64 bit.  */
+		*(u64 *)loc = val;
+		break;
+	case R_390_PC16:	/* PC relative 16 bit.	*/
+		*(u16 *)loc = (val - addr);
+		break;
+	case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
+		*(u16 *)loc = (val - addr) >> 1;
+		break;
+	case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
+		*(u32 *)loc = (val - addr) >> 1;
+		break;
+	case R_390_PC32:	/* PC relative 32 bit.	*/
+		*(u32 *)loc = (val - addr);
+		break;
+	case R_390_PC64:	/* PC relative 64 bit.	*/
+		*(u64 *)loc = (val - addr);
+		break;
+	case R_390_RELATIVE:
+		*(unsigned long *) loc = val;
+		break;
+	default:
+		return 1;
+	}
+	return 0;
+}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index e93fbf02490c..9e1660a6b9db 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -20,6 +20,7 @@
 
 ENTRY(ftrace_stub)
 	BR_EX	%r14
+ENDPROC(ftrace_stub)
 
 #define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
 #define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
@@ -28,7 +29,7 @@ ENTRY(ftrace_stub)
 
 ENTRY(_mcount)
 	BR_EX	%r14
-
+ENDPROC(_mcount)
 EXPORT_SYMBOL(_mcount)
 
 ENTRY(ftrace_caller)
@@ -61,10 +62,11 @@ ENTRY(ftrace_caller)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 # The j instruction gets runtime patched to a nop instruction.
 # See ftrace_enable_ftrace_graph_caller.
-ENTRY(ftrace_graph_caller)
+	.globl ftrace_graph_caller
+ftrace_graph_caller:
 	j	ftrace_graph_caller_end
-	lg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
-	lg	%r3,(STACK_PTREGS_PSW+8)(%r15)
+	lmg	%r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15)
+	lg	%r4,(STACK_PTREGS_PSW+8)(%r15)
 	brasl	%r14,prepare_ftrace_return
 	stg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
 ftrace_graph_caller_end:
@@ -73,6 +75,7 @@ ftrace_graph_caller_end:
 	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
 	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
 	BR_EX	%r1
+ENDPROC(ftrace_caller)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
@@ -86,5 +89,6 @@ ENTRY(return_to_handler)
 	lgr	%r14,%r2
 	lmg	%r2,%r5,32(%r15)
 	BR_EX	%r14
+ENDPROC(return_to_handler)
 
 #endif
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 8c867b43c8eb..0a487fae763e 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -125,7 +125,7 @@ void nmi_free_per_cpu(struct lowcore *lc)
 static notrace void s390_handle_damage(void)
 {
 	smp_emergency_stop();
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 	while (1);
 }
 NOKPROBE_SYMBOL(s390_handle_damage);
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index bdddaae96559..29e511f5bf06 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/cpu.h>
 #include <asm/nospec-branch.h>
 
 static int __init nobp_setup_early(char *str)
@@ -37,7 +38,7 @@ static int __init nospec_report(void)
 {
 	if (test_facility(156))
 		pr_info("Spectre V2 mitigation: etokens\n");
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable)
 		pr_info("Spectre V2 mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
 		pr_info("Spectre V2 mitigation: limited branch prediction\n");
@@ -58,15 +59,15 @@ early_param("nospectre_v2", nospectre_v2_setup_early);
 
 void __init nospec_auto_detect(void)
 {
-	if (test_facility(156)) {
+	if (test_facility(156) || cpu_mitigations_off()) {
 		/*
 		 * The machine supports etokens.
 		 * Disable expolines and disable nobp.
 		 */
-		if (IS_ENABLED(CC_USING_EXPOLINE))
+		if (__is_defined(CC_USING_EXPOLINE))
 			nospec_disable = 1;
 		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
-	} else if (IS_ENABLED(CC_USING_EXPOLINE)) {
+	} else if (__is_defined(CC_USING_EXPOLINE)) {
 		/*
 		 * The kernel has been compiled with expolines.
 		 * Keep expolines enabled and disable nobp.
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index e30e580ae362..48f472bf9290 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -15,7 +15,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 {
 	if (test_facility(156))
 		return sprintf(buf, "Mitigation: etokens\n");
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable)
 		return sprintf(buf, "Mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
 		return sprintf(buf, "Mitigation: limited branch prediction\n");
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index e1c54d28713a..48d48b6187c0 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -2,8 +2,8 @@
 /*
  * Performance event support for s390x - CPU-measurement Counter Facility
  *
- *  Copyright IBM Corp. 2012, 2017
- *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *  Copyright IBM Corp. 2012, 2019
+ *  Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
  */
 #define KMSG_COMPONENT	"cpum_cf"
 #define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
@@ -26,7 +26,7 @@ static enum cpumf_ctr_set get_counter_set(u64 event)
 		set = CPUMF_CTR_SET_USER;
 	else if (event < 128)
 		set = CPUMF_CTR_SET_CRYPTO;
-	else if (event < 256)
+	else if (event < 288)
 		set = CPUMF_CTR_SET_EXT;
 	else if (event >= 448 && event < 496)
 		set = CPUMF_CTR_SET_MT_DIAG;
@@ -50,12 +50,19 @@ static int validate_ctr_version(const struct hw_perf_event *hwc)
 			err = -EOPNOTSUPP;
 		break;
 	case CPUMF_CTR_SET_CRYPTO:
+		if ((cpuhw->info.csvn >= 1 && cpuhw->info.csvn <= 5 &&
+		     hwc->config > 79) ||
+		    (cpuhw->info.csvn >= 6 && hwc->config > 83))
+			err = -EOPNOTSUPP;
+		break;
 	case CPUMF_CTR_SET_EXT:
 		if (cpuhw->info.csvn < 1)
 			err = -EOPNOTSUPP;
 		if ((cpuhw->info.csvn == 1 && hwc->config > 159) ||
 		    (cpuhw->info.csvn == 2 && hwc->config > 175) ||
-		    (cpuhw->info.csvn  > 2 && hwc->config > 255))
+		    (cpuhw->info.csvn >= 3 && cpuhw->info.csvn <= 5
+		     && hwc->config > 255) ||
+		    (cpuhw->info.csvn >= 6 && hwc->config > 287))
 			err = -EOPNOTSUPP;
 		break;
 	case CPUMF_CTR_SET_MT_DIAG:
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index b6854812d2ed..d4e031f7b9c8 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -306,15 +306,20 @@ static size_t cf_diag_ctrset_size(enum cpumf_ctr_set ctrset,
 			ctrset_size = 2;
 		break;
 	case CPUMF_CTR_SET_CRYPTO:
-		ctrset_size = 16;
+		if (info->csvn >= 1 && info->csvn <= 5)
+			ctrset_size = 16;
+		else if (info->csvn == 6)
+			ctrset_size = 20;
 		break;
 	case CPUMF_CTR_SET_EXT:
 		if (info->csvn == 1)
 			ctrset_size = 32;
 		else if (info->csvn == 2)
 			ctrset_size = 48;
-		else if (info->csvn >= 3)
+		else if (info->csvn >= 3 && info->csvn <= 5)
 			ctrset_size = 128;
+		else if (info->csvn == 6)
+			ctrset_size = 160;
 		break;
 	case CPUMF_CTR_SET_MT_DIAG:
 		if (info->csvn > 3)
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index b45238c89728..34cc96449b30 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -31,22 +31,26 @@ CPUMF_EVENT_ATTR(cf_fvn3, PROBLEM_STATE_CPU_CYCLES, 0x0020);
 CPUMF_EVENT_ATTR(cf_fvn3, PROBLEM_STATE_INSTRUCTIONS, 0x0021);
 CPUMF_EVENT_ATTR(cf_fvn3, L1D_DIR_WRITES, 0x0004);
 CPUMF_EVENT_ATTR(cf_fvn3, L1D_PENALTY_CYCLES, 0x0005);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_FUNCTIONS, 0x0040);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_CYCLES, 0x0041);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_BLOCKED_FUNCTIONS, 0x0042);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_BLOCKED_CYCLES, 0x0043);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_FUNCTIONS, 0x0044);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_CYCLES, 0x0045);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_BLOCKED_FUNCTIONS, 0x0046);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_BLOCKED_CYCLES, 0x0047);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_FUNCTIONS, 0x0048);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_CYCLES, 0x0049);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_BLOCKED_FUNCTIONS, 0x004a);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_BLOCKED_CYCLES, 0x004b);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_FUNCTIONS, 0x004c);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_CYCLES, 0x004d);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_BLOCKED_FUNCTIONS, 0x004e);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_FUNCTIONS, 0x0040);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_CYCLES, 0x0041);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS, 0x0042);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_BLOCKED_CYCLES, 0x0043);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_FUNCTIONS, 0x0044);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_CYCLES, 0x0045);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS, 0x0046);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_BLOCKED_CYCLES, 0x0047);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_FUNCTIONS, 0x0048);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_CYCLES, 0x0049);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS, 0x004a);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_BLOCKED_CYCLES, 0x004b);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_FUNCTIONS, 0x004c);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_CYCLES, 0x004d);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS, 0x004e);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_FUNCTION_COUNT, 0x0050);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_CYCLES_COUNT, 0x0051);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_BLOCKED_FUNCTION_COUNT, 0x0052);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_BLOCKED_CYCLES_COUNT, 0x0053);
 CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080);
 CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081);
 CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082);
@@ -262,23 +266,47 @@ static struct attribute *cpumcf_fvn3_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
-static struct attribute *cpumcf_svn_generic_pmu_event_attr[] __initdata = {
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_BLOCKED_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_BLOCKED_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_BLOCKED_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_BLOCKED_CYCLES),
+static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_CYCLES),
+	NULL,
+};
+
+static struct attribute *cpumcf_svn_6_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_FUNCTION_COUNT),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_CYCLES_COUNT),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_BLOCKED_FUNCTION_COUNT),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_BLOCKED_CYCLES_COUNT),
 	NULL,
 };
 
@@ -562,7 +590,18 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	default:
 		cfvn = none;
 	}
-	csvn = cpumcf_svn_generic_pmu_event_attr;
+
+	/* Determine version specific crypto set */
+	switch (ci.csvn) {
+	case 1 ... 5:
+		csvn = cpumcf_svn_12345_pmu_event_attr;
+		break;
+	case 6:
+		csvn = cpumcf_svn_6_pmu_event_attr;
+		break;
+	default:
+		csvn = none;
+	}
 
 	/* Determine model-specific counter set(s) */
 	get_cpu_id(&cpu_id);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 0d770e513abf..fcb6c2e92b07 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -21,6 +21,7 @@
 #include <asm/lowcore.h>
 #include <asm/processor.h>
 #include <asm/sysinfo.h>
+#include <asm/unwind.h>
 
 const char *perf_pmu_name(void)
 {
@@ -219,20 +220,13 @@ static int __init service_level_perf_register(void)
 }
 arch_initcall(service_level_perf_register);
 
-static int __perf_callchain_kernel(void *data, unsigned long address, int reliable)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-
-	perf_callchain_store(entry, address);
-	return 0;
-}
-
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
-	if (user_mode(regs))
-		return;
-	dump_trace(__perf_callchain_kernel, entry, NULL, regs->gprs[15]);
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, regs, 0)
+		perf_callchain_store(entry, state.ip);
 }
 
 /* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 3e62aae34ea3..59dee9d3bebf 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -7,7 +7,7 @@
 
 #include <linux/linkage.h>
 
-#define PGM_CHECK(handler)	.long handler
+#define PGM_CHECK(handler)	.quad handler
 #define PGM_CHECK_DEFAULT	PGM_CHECK(default_trap_handler)
 
 /*
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 6e758bb6cd29..63873aa6693f 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -37,6 +37,7 @@
 #include <asm/irq.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
+#include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
 #include "entry.h"
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 6fe2e1875058..5de13307b703 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -109,7 +109,8 @@ static void show_cpu_summary(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs"
+		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs",
+		"vxe2", "vxp", "sort", "dflt"
 	};
 	static const char * const int_hwcap_str[] = {
 		"sie"
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 7f14adf512c6..4a22163962eb 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -73,6 +73,7 @@ ENTRY(store_status)
 	lgr	%r9,%r2
 	lgr	%r2,%r3
 	BR_EX	%r9
+ENDPROC(store_status)
 
 	.section .bss
 	.align	8
diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S
index c97c2d40fe15..fe396673e8a6 100644
--- a/arch/s390/kernel/relocate_kernel.S
+++ b/arch/s390/kernel/relocate_kernel.S
@@ -58,11 +58,15 @@ ENTRY(relocate_kernel)
 		j	.base
 	.done:
 		sgr	%r0,%r0		# clear register r0
+		cghi	%r3,0
+		je	.diag
 		la	%r4,load_psw-.base(%r13)	# load psw-address into the register
 		o	%r3,4(%r4)	# or load address into psw
 		st	%r3,4(%r4)
 		mvc	0(8,%r0),0(%r4)	# copy psw to absolute address 0
+	.diag:
 		diag	%r0,%r0,0x308
+ENDPROC(relocate_kernel)
 
 		.align	8
 	load_psw:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 2c642af526ce..f8544d517430 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -50,6 +50,7 @@
 #include <linux/compat.h>
 #include <linux/start_kernel.h>
 
+#include <asm/boot_data.h>
 #include <asm/ipl.h>
 #include <asm/facility.h>
 #include <asm/smp.h>
@@ -65,11 +66,13 @@
 #include <asm/diag.h>
 #include <asm/os_info.h>
 #include <asm/sclp.h>
+#include <asm/stacktrace.h>
 #include <asm/sysinfo.h>
 #include <asm/numa.h>
 #include <asm/alternative.h>
 #include <asm/nospec-branch.h>
 #include <asm/mem_detect.h>
+#include <asm/uv.h>
 #include "entry.h"
 
 /*
@@ -89,12 +92,25 @@ char elf_platform[ELF_PLATFORM_SIZE];
 
 unsigned long int_hwcap = 0;
 
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+int __bootdata_preserved(prot_virt_guest);
+#endif
+
 int __bootdata(noexec_disabled);
 int __bootdata(memory_end_set);
 unsigned long __bootdata(memory_end);
 unsigned long __bootdata(max_physmem_end);
 struct mem_detect_info __bootdata(mem_detect);
 
+struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table);
+struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table);
+unsigned long __bootdata_preserved(__swsusp_reset_dma);
+unsigned long __bootdata_preserved(__stext_dma);
+unsigned long __bootdata_preserved(__etext_dma);
+unsigned long __bootdata_preserved(__sdma);
+unsigned long __bootdata_preserved(__edma);
+unsigned long __bootdata_preserved(__kaslr_offset);
+
 unsigned long VMALLOC_START;
 EXPORT_SYMBOL(VMALLOC_START);
 
@@ -736,6 +752,15 @@ static void __init reserve_initrd(void)
 #endif
 }
 
+/*
+ * Reserve the memory area used to pass the certificate lists
+ */
+static void __init reserve_certificate_list(void)
+{
+	if (ipl_cert_list_addr)
+		memblock_reserve(ipl_cert_list_addr, ipl_cert_list_size);
+}
+
 static void __init reserve_mem_detect_info(void)
 {
 	unsigned long start, size;
@@ -814,9 +839,10 @@ static void __init reserve_kernel(void)
 {
 	unsigned long start_pfn = PFN_UP(__pa(_end));
 
-	memblock_reserve(0, PARMAREA_END);
+	memblock_reserve(0, HEAD_END);
 	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
 			 - (unsigned long)_stext);
+	memblock_reserve(__sdma, __edma - __sdma);
 }
 
 static void __init setup_memory(void)
@@ -914,7 +940,15 @@ static int __init setup_hwcaps(void)
 			elf_hwcap |= HWCAP_S390_VXRS_EXT;
 		if (test_facility(135))
 			elf_hwcap |= HWCAP_S390_VXRS_BCD;
+		if (test_facility(148))
+			elf_hwcap |= HWCAP_S390_VXRS_EXT2;
+		if (test_facility(152))
+			elf_hwcap |= HWCAP_S390_VXRS_PDE;
 	}
+	if (test_facility(150))
+		elf_hwcap |= HWCAP_S390_SORT;
+	if (test_facility(151))
+		elf_hwcap |= HWCAP_S390_DFLT;
 
 	/*
 	 * Guarded storage support HWCAP_S390_GS is bit 12.
@@ -1023,6 +1057,38 @@ static void __init setup_control_program_code(void)
 }
 
 /*
+ * Print the component list from the IPL report
+ */
+static void __init log_component_list(void)
+{
+	struct ipl_rb_component_entry *ptr, *end;
+	char *str;
+
+	if (!early_ipl_comp_list_addr)
+		return;
+	if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+		pr_info("Linux is running with Secure-IPL enabled\n");
+	else
+		pr_info("Linux is running with Secure-IPL disabled\n");
+	ptr = (void *) early_ipl_comp_list_addr;
+	end = (void *) ptr + early_ipl_comp_list_size;
+	pr_info("The IPL report contains the following components:\n");
+	while (ptr < end) {
+		if (ptr->flags & IPL_RB_COMPONENT_FLAG_SIGNED) {
+			if (ptr->flags & IPL_RB_COMPONENT_FLAG_VERIFIED)
+				str = "signed, verified";
+			else
+				str = "signed, verification failed";
+		} else {
+			str = "not signed";
+		}
+		pr_info("%016llx - %016llx (%s)\n",
+			ptr->addr, ptr->addr + ptr->len, str);
+		ptr++;
+	}
+}
+
+/*
  * Setup function called from init/main.c just after the banner
  * was printed.
  */
@@ -1042,6 +1108,8 @@ void __init setup_arch(char **cmdline_p)
 	else
 		pr_info("Linux is running as a guest in 64-bit mode\n");
 
+	log_component_list();
+
 	/* Have one command line that is parsed and saved in /proc/cmdline */
 	/* boot_command_line has been already set up in early.c */
 	*cmdline_p = boot_command_line;
@@ -1073,6 +1141,7 @@ void __init setup_arch(char **cmdline_p)
 	reserve_oldmem();
 	reserve_kernel();
 	reserve_initrd();
+	reserve_certificate_list();
 	reserve_mem_detect_info();
 	memblock_allow_resize();
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index bd197baf1dc3..35fafa2b91a8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -53,6 +53,7 @@
 #include <asm/sigp.h>
 #include <asm/idle.h>
 #include <asm/nmi.h>
+#include <asm/stacktrace.h>
 #include <asm/topology.h>
 #include "entry.h"
 
@@ -689,7 +690,7 @@ void __init smp_save_dump_cpus(void)
 			smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
 	}
 	memblock_free(page, PAGE_SIZE);
-	diag308_reset();
+	diag_dma_ops.diag308_reset();
 	pcpu_set_smt(0);
 }
 #endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 460dcfba7d4e..f6a620f854e1 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -11,65 +11,52 @@
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
 #include <linux/export.h>
-
-static int __save_address(void *data, unsigned long address, int nosched)
-{
-	struct stack_trace *trace = data;
-
-	if (nosched && in_sched_functions(address))
-		return 0;
-	if (trace->skip > 0) {
-		trace->skip--;
-		return 0;
-	}
-	if (trace->nr_entries < trace->max_entries) {
-		trace->entries[trace->nr_entries++] = address;
-		return 0;
-	}
-	return 1;
-}
-
-static int save_address(void *data, unsigned long address, int reliable)
-{
-	return __save_address(data, address, 0);
-}
-
-static int save_address_nosched(void *data, unsigned long address, int reliable)
-{
-	return __save_address(data, address, 1);
-}
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
 
 void save_stack_trace(struct stack_trace *trace)
 {
-	unsigned long sp;
-
-	sp = current_stack_pointer();
-	dump_trace(save_address, trace, NULL, sp);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, NULL, 0) {
+		if (trace->nr_entries >= trace->max_entries)
+			break;
+		if (trace->skip > 0)
+			trace->skip--;
+		else
+			trace->entries[trace->nr_entries++] = state.ip;
+	}
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	unsigned long sp;
-
-	sp = tsk->thread.ksp;
-	if (tsk == current)
-		sp = current_stack_pointer();
-	dump_trace(save_address_nosched, trace, tsk, sp);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, tsk, NULL, 0) {
+		if (trace->nr_entries >= trace->max_entries)
+			break;
+		if (in_sched_functions(state.ip))
+			continue;
+		if (trace->skip > 0)
+			trace->skip--;
+		else
+			trace->entries[trace->nr_entries++] = state.ip;
+	}
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 {
-	unsigned long sp;
-
-	sp = kernel_stack_pointer(regs);
-	dump_trace(save_address, trace, NULL, sp);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, regs, 0) {
+		if (trace->nr_entries >= trace->max_entries)
+			break;
+		if (trace->skip > 0)
+			trace->skip--;
+		else
+			trace->entries[trace->nr_entries++] = state.ip;
+	}
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index 993100c31d65..19a3c427801a 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -108,6 +108,7 @@ ENTRY(swsusp_arch_suspend)
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
 	BR_EX	%r14
+ENDPROC(swsusp_arch_suspend)
 
 /*
  * Restore saved memory image to correct place and restore register context.
@@ -154,20 +155,13 @@ ENTRY(swsusp_arch_resume)
 	ptlb				/* flush tlb */
 
 	/* Reset System */
-	larl	%r1,restart_entry
-	larl	%r2,.Lrestart_diag308_psw
-	og	%r1,0(%r2)
-	stg	%r1,0(%r0)
 	larl	%r1,.Lnew_pgm_check_psw
 	epsw	%r2,%r3
 	stm	%r2,%r3,0(%r1)
 	mvc	__LC_PGM_NEW_PSW(16,%r0),0(%r1)
-	lghi	%r0,0
-	diag	%r0,%r0,0x308
-restart_entry:
-	lhi	%r1,1
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
-	sam64
+	larl	%r1,__swsusp_reset_dma
+	lg	%r1,0(%r1)
+	BASR_EX	%r14,%r1
 #ifdef CONFIG_SMP
 	larl	%r1,smp_cpu_mt_shift
 	icm	%r1,15,0(%r1)
@@ -267,6 +261,7 @@ restore_registers:
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
 	BR_EX	%r14
+ENDPROC(swsusp_arch_resume)
 
 	.section .data..nosave,"aw",@progbits
 	.align	8
@@ -275,8 +270,6 @@ restore_registers:
 .Lpanic_string:
 	.asciz	"Resume not possible because suspend CPU is no longer available\n"
 	.align	8
-.Lrestart_diag308_psw:
-	.long	0x00080000,0x80000000
 .Lrestart_suspend_psw:
 	.quad	0x0000000180000000,restart_suspend
 .Lnew_pgm_check_psw:
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 8003b38c1688..82e81a9f7112 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -49,7 +49,7 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 		report_user_fault(regs, si_signo, 0);
         } else {
                 const struct exception_table_entry *fixup;
-		fixup = search_exception_tables(regs->psw.addr);
+		fixup = s390_search_extables(regs->psw.addr);
                 if (fixup)
 			regs->psw.addr = extable_fixup(fixup);
 		else {
@@ -263,5 +263,6 @@ NOKPROBE_SYMBOL(kernel_stack_overflow);
 
 void __init trap_init(void)
 {
+	sort_extable(__start_dma_ex_table, __stop_dma_ex_table);
 	local_mcck_enable();
 }
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
new file mode 100644
index 000000000000..57fd4e902f1f
--- /dev/null
+++ b/arch/s390/kernel/unwind_bc.c
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/interrupt.h>
+#include <asm/sections.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return 0;
+	return __kernel_text_address(state->ip) ? state->ip : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+static bool outside_of_stack(struct unwind_state *state, unsigned long sp)
+{
+	return (sp <= state->sp) ||
+		(sp + sizeof(struct stack_frame) > state->stack_info.end);
+}
+
+static bool update_stack_info(struct unwind_state *state, unsigned long sp)
+{
+	struct stack_info *info = &state->stack_info;
+	unsigned long *mask = &state->stack_mask;
+
+	/* New stack pointer leaves the current stack */
+	if (get_stack_info(sp, state->task, info, mask) != 0 ||
+	    !on_stack(info, sp, sizeof(struct stack_frame)))
+		/* 'sp' does not point to a valid stack */
+		return false;
+	return true;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+	struct stack_info *info = &state->stack_info;
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+	unsigned long sp, ip;
+	bool reliable;
+
+	regs = state->regs;
+	if (unlikely(regs)) {
+		sp = READ_ONCE_TASK_STACK(state->task, regs->gprs[15]);
+		if (unlikely(outside_of_stack(state, sp))) {
+			if (!update_stack_info(state, sp))
+				goto out_err;
+		}
+		sf = (struct stack_frame *) sp;
+		ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+		reliable = false;
+		regs = NULL;
+	} else {
+		sf = (struct stack_frame *) state->sp;
+		sp = READ_ONCE_TASK_STACK(state->task, sf->back_chain);
+		if (likely(sp)) {
+			/* Non-zero back-chain points to the previous frame */
+			if (unlikely(outside_of_stack(state, sp))) {
+				if (!update_stack_info(state, sp))
+					goto out_err;
+			}
+			sf = (struct stack_frame *) sp;
+			ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+			reliable = true;
+		} else {
+			/* No back-chain, look for a pt_regs structure */
+			sp = state->sp + STACK_FRAME_OVERHEAD;
+			if (!on_stack(info, sp, sizeof(struct pt_regs)))
+				goto out_stop;
+			regs = (struct pt_regs *) sp;
+			if (user_mode(regs))
+				goto out_stop;
+			ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr);
+			reliable = true;
+		}
+	}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* Decode any ftrace redirection */
+	if (ip == (unsigned long) return_to_handler)
+		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+					   ip, (void *) sp);
+#endif
+
+	/* Update unwind state */
+	state->sp = sp;
+	state->ip = ip;
+	state->regs = regs;
+	state->reliable = reliable;
+	return true;
+
+out_err:
+	state->error = true;
+out_stop:
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
+	return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long sp)
+{
+	struct stack_info *info = &state->stack_info;
+	unsigned long *mask = &state->stack_mask;
+	struct stack_frame *sf;
+	unsigned long ip;
+	bool reliable;
+
+	memset(state, 0, sizeof(*state));
+	state->task = task;
+	state->regs = regs;
+
+	/* Don't even attempt to start from user mode regs: */
+	if (regs && user_mode(regs)) {
+		info->type = STACK_TYPE_UNKNOWN;
+		return;
+	}
+
+	/* Get current stack pointer and initialize stack info */
+	if (get_stack_info(sp, task, info, mask) != 0 ||
+	    !on_stack(info, sp, sizeof(struct stack_frame))) {
+		/* Something is wrong with the stack pointer */
+		info->type = STACK_TYPE_UNKNOWN;
+		state->error = true;
+		return;
+	}
+
+	/* Get the instruction pointer from pt_regs or the stack frame */
+	if (regs) {
+		ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr);
+		reliable = true;
+	} else {
+		sf = (struct stack_frame *) sp;
+		ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+		reliable = false;
+	}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* Decode any ftrace redirection */
+	if (ip == (unsigned long) return_to_handler)
+		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+					   ip, NULL);
+#endif
+
+	/* Update unwind state */
+	state->sp = sp;
+	state->ip = ip;
+	state->reliable = reliable;
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index e7920a68a12e..243d8b1185bf 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -29,7 +29,7 @@
 #include <asm/vdso.h>
 #include <asm/facility.h>
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 extern char vdso32_start, vdso32_end;
 static void *vdso32_kbase = &vdso32_start;
 static unsigned int vdso32_pages;
@@ -55,7 +55,7 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 
 	vdso_pagelist = vdso64_pagelist;
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	if (vma->vm_mm->context.compat_mm) {
 		vdso_pagelist = vdso32_pagelist;
 		vdso_pages = vdso32_pages;
@@ -76,7 +76,7 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	unsigned long vdso_pages;
 
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	if (vma->vm_mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
 #endif
@@ -223,7 +223,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return 0;
 
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	mm->context.compat_mm = is_compat_task();
 	if (mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
@@ -280,7 +280,7 @@ static int __init vdso_init(void)
 	int i;
 
 	vdso_init_data(vdso_data);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	/* Calculate the size of the 32 bit vDSO */
 	vdso32_pages = ((&vdso32_end - &vdso32_start
 			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index e76309fbbcb3..aee9ffbccb54 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -19,7 +19,7 @@ KBUILD_AFLAGS_31 += -m31 -s
 KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin
 KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
-			$(call cc-ldoption, -Wl$(comma)--hash-style=both)
+		    -Wl,--hash-style=both
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31)
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index f849ac61c5da..bec19e7e6e1c 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -19,7 +19,7 @@ KBUILD_AFLAGS_64 += -m64 -s
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
 KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
-			$(call cc-ldoption, -Wl$(comma)--hash-style=both)
+		    -Wl,--hash-style=both
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 8429ab079715..49d55327de0b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -72,6 +72,7 @@ SECTIONS
 	__end_ro_after_init = .;
 
 	RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
+	BOOT_DATA_PRESERVED
 
 	_edata = .;		/* End of data section */
 
@@ -143,6 +144,18 @@ SECTIONS
 	INIT_DATA_SECTION(0x100)
 
 	PERCPU_SECTION(0x100)
+
+	.dynsym ALIGN(8) : {
+		__dynsym_start = .;
+		*(.dynsym)
+		__dynsym_end = .;
+	}
+	.rela.dyn ALIGN(8) : {
+		__rela_dyn_start = .;
+		*(.rela*)
+		__rela_dyn_end = .;
+	}
+
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
@@ -161,6 +174,12 @@ SECTIONS
 		QUAD(__bss_stop - __bss_start)			/* bss_size */
 		QUAD(__boot_data_start)				/* bootdata_off */
 		QUAD(__boot_data_end - __boot_data_start)	/* bootdata_size */
+		QUAD(__boot_data_preserved_start)		/* bootdata_preserved_off */
+		QUAD(__boot_data_preserved_end -
+		     __boot_data_preserved_start)		/* bootdata_preserved_size */
+		QUAD(__dynsym_start)				/* dynsym_start */
+		QUAD(__rela_dyn_start)				/* rela_dyn_start */
+		QUAD(__rela_dyn_end)				/* rela_dyn_end */
 	} :NONE
 
 	/* Debugging sections.	*/
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 82162867f378..37503ae62486 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3194,7 +3194,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister);
 
-static void gib_alert_irq_handler(struct airq_struct *airq)
+static void gib_alert_irq_handler(struct airq_struct *airq, bool floating)
 {
 	inc_irq_stat(IRQIO_GAL);
 	process_gib_alert_list();
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 53008da05190..dc0874f2e203 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -178,6 +178,7 @@ ENTRY(__memset\bits)
 	BR_EX	%r14
 .L__memset_mvc\bits:
 	mvc	\bytes(1,%r1),0(%r1)
+ENDPROC(__memset\bits)
 .endm
 
 __MEMSET 16,2,sth
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index f5880bfd1b0c..3175413186b9 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -4,7 +4,7 @@
 #
 
 obj-y		:= init.o fault.o extmem.o mmap.o vmem.o maccess.o
-obj-y		+= page-states.o gup.o pageattr.o pgtable.o pgalloc.o
+obj-y		+= page-states.o pageattr.o pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 11613362c4e7..c220399ae196 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -247,12 +247,24 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 			current);
 }
 
+const struct exception_table_entry *s390_search_extables(unsigned long addr)
+{
+	const struct exception_table_entry *fixup;
+
+	fixup = search_extable(__start_dma_ex_table,
+			       __stop_dma_ex_table - __start_dma_ex_table,
+			       addr);
+	if (!fixup)
+		fixup = search_exception_tables(addr);
+	return fixup;
+}
+
 static noinline void do_no_context(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
 
 	/* Are we prepared to handle this kernel fault?  */
-	fixup = search_exception_tables(regs->psw.addr);
+	fixup = s390_search_extables(regs->psw.addr);
 	if (fixup) {
 		regs->psw.addr = extable_fixup(fixup);
 		return;
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
deleted file mode 100644
index 2809d11c7a28..000000000000
--- a/arch/s390/mm/gup.c
+++ /dev/null
@@ -1,300 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  Lockless get_user_pages_fast for s390
- *
- *  Copyright IBM Corp. 2010
- *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	pte_t *ptep, pte;
-
-	mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
-
-	ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
-	do {
-		pte = *ptep;
-		barrier();
-		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_protnone(pte))
-			return 0;
-		if ((pte_val(pte) & mask) != 0)
-			return 0;
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			return 0;
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(head);
-			return 0;
-		}
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 1;
-}
-
-static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
-	if ((pmd_val(pmd) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
-
-	refs = 0;
-	head = pmd_page(pmd);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-
-static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pmd_t *pmdp, pmd;
-
-	pmdp = (pmd_t *) pudp;
-	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		pmdp = (pmd_t *) pud_deref(pud);
-	pmdp += pmd_index(addr);
-	do {
-		pmd = *pmdp;
-		barrier();
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
-			return 0;
-		if (unlikely(pmd_large(pmd))) {
-			/*
-			 * NUMA hinting faults need to be handled in the GUP
-			 * slowpath for accounting purposes and so that they
-			 * can be serialised against THP migration.
-			 */
-			if (pmd_protnone(pmd))
-				return 0;
-			if (!gup_huge_pmd(pmdp, pmd, addr, next,
-					  write, pages, nr))
-				return 0;
-		} else if (!gup_pte_range(pmdp, pmd, addr, next,
-					  write, pages, nr))
-			return 0;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _REGION_ENTRY_PROTECT : 0) | _REGION_ENTRY_INVALID;
-	if ((pud_val(pud) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
-
-	refs = 0;
-	head = pud_page(pud);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pud_val(pud) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pud_t *pudp, pud;
-
-	pudp = (pud_t *) p4dp;
-	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
-		pudp = (pud_t *) p4d_deref(p4d);
-	pudp += pud_index(addr);
-	do {
-		pud = *pudp;
-		barrier();
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			return 0;
-		if (unlikely(pud_large(pud))) {
-			if (!gup_huge_pud(pudp, pud, addr, next, write, pages,
-					  nr))
-				return 0;
-		} else if (!gup_pmd_range(pudp, pud, addr, next, write, pages,
-					  nr))
-			return 0;
-	} while (pudp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	p4d_t *p4dp, p4d;
-
-	p4dp = (p4d_t *) pgdp;
-	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
-		p4dp = (p4d_t *) pgd_deref(pgd);
-	p4dp += p4d_index(addr);
-	do {
-		p4d = *p4dp;
-		barrier();
-		next = p4d_addr_end(addr, end);
-		if (p4d_none(p4d))
-			return 0;
-		if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr))
-			return 0;
-	} while (p4dp++, addr = next, addr != end);
-
-	return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, len, end;
-	unsigned long next, flags;
-	pgd_t *pgdp, pgd;
-	int nr = 0;
-
-	start &= PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-	if ((end <= start) || (end > mm->context.asce_limit))
-		return 0;
-	/*
-	 * local_irq_save() doesn't prevent pagetable teardown, but does
-	 * prevent the pagetables from being freed on s390.
-	 *
-	 * So long as we atomically load page table pointers versus teardown,
-	 * we can follow the address down to the the page and take a ref on it.
-	 */
-	local_irq_save(flags);
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd = *pgdp;
-		barrier();
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-	local_irq_restore(flags);
-
-	return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @write:	whether pages will be written to
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
-{
-	int nr, ret;
-
-	might_sleep();
-	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	if (nr == nr_pages)
-		return nr;
-
-	/* Try to get the remaining pages with get_user_pages */
-	start += nr << PAGE_SHIFT;
-	pages += nr;
-	ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
-				      write ? FOLL_WRITE : 0);
-	/* Have to be a bit careful with return values */
-	if (nr > 0)
-		ret = (ret < 0) ? nr : ret + nr;
-	return ret;
-}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 3e82f66d5c61..7cf48eefec8f 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,8 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
+bool initmem_freed;
+
 static void __init setup_zero_pages(void)
 {
 	unsigned int order;
@@ -148,6 +150,7 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
+	initmem_freed = true;
 	__set_memory((unsigned long)_sinittext,
 		     (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
 		     SET_MEMORY_RW | SET_MEMORY_NX);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 97b3ee53852b..818deeb1ebc3 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <asm/ctl_reg.h>
 #include <asm/io.h>
+#include <asm/stacktrace.h>
 
 static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t size)
 {
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index db6bb2f97a2c..99e06213a22b 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -290,7 +290,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
 	tlb_remove_table(tlb, table);
 }
 
-static void __tlb_remove_table(void *_table)
+void __tlb_remove_table(void *_table)
 {
 	unsigned int mask = (unsigned long) _table & 3;
 	void *table = (void *)((unsigned long) _table ^ mask);
@@ -316,67 +316,6 @@ static void __tlb_remove_table(void *_table)
 	}
 }
 
-static void tlb_remove_table_smp_sync(void *arg)
-{
-	/* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
-	/*
-	 * This isn't an RCU grace period and hence the page-tables cannot be
-	 * assumed to be actually RCU-freed.
-	 *
-	 * It is however sufficient for software page-table walkers that rely
-	 * on IRQ disabling. See the comment near struct mmu_table_batch.
-	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
-	struct mmu_table_batch *batch;
-	int i;
-
-	batch = container_of(head, struct mmu_table_batch, rcu);
-
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
-
-	free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	if (*batch) {
-		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
-		*batch = NULL;
-	}
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	tlb->mm->context.flush_mm = 1;
-	if (*batch == NULL) {
-		*batch = (struct mmu_table_batch *)
-			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		if (*batch == NULL) {
-			__tlb_flush_mm_lazy(tlb->mm);
-			tlb_remove_table_one(table);
-			return;
-		}
-		(*batch)->nr = 0;
-	}
-	(*batch)->tables[(*batch)->nr++] = table;
-	if ((*batch)->nr == MAX_TABLE_BATCH)
-		tlb_flush_mmu(tlb);
-}
-
 /*
  * Base infrastructure required to generate basic asces, region, segment,
  * and page tables that do not make use of enhanced features like EDAT1.
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 8485d6dc2754..9ebd01219812 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -410,6 +410,7 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 	return old;
 }
 
+#ifdef CONFIG_PGSTE
 static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
@@ -427,6 +428,7 @@ static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
 	pmd = pmd_alloc(mm, pud, addr);
 	return pmd;
 }
+#endif
 
 pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t new)
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 0472e27febdf..b403fa14847d 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -413,6 +413,8 @@ void __init vmem_map_init(void)
 	__set_memory((unsigned long)_sinittext,
 		     (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
 		     SET_MEMORY_RO | SET_MEMORY_X);
+	__set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
+		     SET_MEMORY_RO | SET_MEMORY_X);
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);
 }
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 51dd0267d014..5e7c63033159 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -455,7 +455,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
 	/* Restore registers */
 	save_restore_regs(jit, REGS_RESTORE, stack_depth);
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
 		jit->r14_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r14 thunk */
 		if (test_facility(35)) {
@@ -473,7 +473,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	/* br %r14 */
 	_EMIT2(0x07fe);
 
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable &&
 	    (jit->seen & SEEN_FUNC)) {
 		jit->r1_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r1 thunk */
@@ -999,7 +999,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		/* lg %w1,<d(imm)>(%l) */
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
 			      EMIT_CONST_U64(func));
-		if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+		if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
 			/* brasl %r14,__s390_indirect_jump_r1 */
 			EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
 		} else {
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 43d9525c36fc..7441857df51b 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -13,23 +13,17 @@
 #include <linux/oprofile.h>
 #include <linux/init.h>
 #include <asm/processor.h>
-
-static int __s390_backtrace(void *data, unsigned long address, int reliable)
-{
-	unsigned int *depth = data;
-
-	if (*depth == 0)
-		return 1;
-	(*depth)--;
-	oprofile_add_trace(address);
-	return 0;
-}
+#include <asm/unwind.h>
 
 static void s390_backtrace(struct pt_regs *regs, unsigned int depth)
 {
-	if (user_mode(regs))
-		return;
-	dump_trace(__s390_backtrace, &depth, NULL, regs->gprs[15]);
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, regs, 0) {
+		if (depth-- == 0)
+			break;
+		oprofile_add_trace(state.ip);
+	}
 }
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 22d0871291ee..748626a33028 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -3,5 +3,5 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_sysfs.o \
+obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index dc9bc82c072c..0ebb7c405a25 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -24,11 +24,9 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/delay.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
 #include <linux/seq_file.h>
+#include <linux/jump_label.h>
 #include <linux/pci.h>
-#include <linux/msi.h>
 
 #include <asm/isc.h>
 #include <asm/airq.h>
@@ -37,30 +35,13 @@
 #include <asm/pci_clp.h>
 #include <asm/pci_dma.h>
 
-#define DEBUG				/* enable pr_debug */
-
-#define	SIC_IRQ_MODE_ALL		0
-#define	SIC_IRQ_MODE_SINGLE		1
-
-#define ZPCI_NR_DMA_SPACES		1
-#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
-
 /* list of all detected zpci devices */
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
 
-static struct irq_chip zpci_irq_chip = {
-	.name = "zPCI",
-	.irq_unmask = pci_msi_unmask_irq,
-	.irq_mask = pci_msi_mask_irq,
-};
-
 static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
 static DEFINE_SPINLOCK(zpci_domain_lock);
 
-static struct airq_iv *zpci_aisb_iv;
-static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
-
 #define ZPCI_IOMAP_ENTRIES						\
 	min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2),	\
 	    ZPCI_IOMAP_MAX_ENTRIES)
@@ -70,6 +51,8 @@ static unsigned long *zpci_iomap_bitmap;
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
+DEFINE_STATIC_KEY_FALSE(have_mio);
+
 static struct kmem_cache *zdev_fmb_cache;
 
 struct zpci_dev *get_zdev_by_fid(u32 fid)
@@ -123,39 +106,6 @@ int pci_proc_domain(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pci_proc_domain);
 
-/* Modify PCI: Register adapter interruptions */
-static int zpci_set_airq(struct zpci_dev *zdev)
-{
-	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
-	struct zpci_fib fib = {0};
-	u8 status;
-
-	fib.isc = PCI_ISC;
-	fib.sum = 1;		/* enable summary notifications */
-	fib.noi = airq_iv_end(zdev->aibv);
-	fib.aibv = (unsigned long) zdev->aibv->vector;
-	fib.aibvo = 0;		/* each zdev has its own interrupt vector */
-	fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
-	fib.aisbo = zdev->aisb & 63;
-
-	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
-}
-
-/* Modify PCI: Unregister adapter interruptions */
-static int zpci_clear_airq(struct zpci_dev *zdev)
-{
-	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
-	struct zpci_fib fib = {0};
-	u8 cc, status;
-
-	cc = zpci_mod_fc(req, &fib, &status);
-	if (cc == 3 || (cc == 1 && status == 24))
-		/* Function already gone or IRQs already deregistered. */
-		cc = 0;
-
-	return cc ? -EIO : 0;
-}
-
 /* Modify PCI: Register I/O address translation parameters */
 int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
 		       u64 base, u64 limit, u64 iota)
@@ -241,7 +191,7 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
 	u64 data;
 	int rc;
 
-	rc = zpci_load(&data, req, offset);
+	rc = __zpci_load(&data, req, offset);
 	if (!rc) {
 		data = le64_to_cpu((__force __le64) data);
 		data >>= (8 - len) * 8;
@@ -259,7 +209,7 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 
 	data <<= (8 - len) * 8;
 	data = (__force u64) cpu_to_le64(data);
-	rc = zpci_store(data, req, offset);
+	rc = __zpci_store(data, req, offset);
 	return rc;
 }
 
@@ -276,18 +226,48 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
        zpci_memcpy_toio(to, from, count);
 }
 
+void __iomem *ioremap(unsigned long ioaddr, unsigned long size)
+{
+	struct vm_struct *area;
+	unsigned long offset;
+
+	if (!size)
+		return NULL;
+
+	if (!static_branch_unlikely(&have_mio))
+		return (void __iomem *) ioaddr;
+
+	offset = ioaddr & ~PAGE_MASK;
+	ioaddr &= PAGE_MASK;
+	size = PAGE_ALIGN(size + offset);
+	area = get_vm_area(size, VM_IOREMAP);
+	if (!area)
+		return NULL;
+
+	if (ioremap_page_range((unsigned long) area->addr,
+			       (unsigned long) area->addr + size,
+			       ioaddr, PAGE_KERNEL)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+	return (void __iomem *) ((unsigned long) area->addr + offset);
+}
+EXPORT_SYMBOL(ioremap);
+
+void iounmap(volatile void __iomem *addr)
+{
+	if (static_branch_likely(&have_mio))
+		vunmap((__force void *) ((unsigned long) addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);
+
 /* Create a virtual mapping cookie for a PCI BAR */
-void __iomem *pci_iomap_range(struct pci_dev *pdev,
-			      int bar,
-			      unsigned long offset,
-			      unsigned long max)
+static void __iomem *pci_iomap_range_fh(struct pci_dev *pdev, int bar,
+					unsigned long offset, unsigned long max)
 {
 	struct zpci_dev *zdev =	to_zpci(pdev);
 	int idx;
 
-	if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
-		return NULL;
-
 	idx = zdev->bars[bar].map_idx;
 	spin_lock(&zpci_iomap_lock);
 	/* Detect overrun */
@@ -298,6 +278,30 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev,
 
 	return (void __iomem *) ZPCI_ADDR(idx) + offset;
 }
+
+static void __iomem *pci_iomap_range_mio(struct pci_dev *pdev, int bar,
+					 unsigned long offset,
+					 unsigned long max)
+{
+	unsigned long barsize = pci_resource_len(pdev, bar);
+	struct zpci_dev *zdev = to_zpci(pdev);
+	void __iomem *iova;
+
+	iova = ioremap((unsigned long) zdev->bars[bar].mio_wt, barsize);
+	return iova ? iova + offset : iova;
+}
+
+void __iomem *pci_iomap_range(struct pci_dev *pdev, int bar,
+			      unsigned long offset, unsigned long max)
+{
+	if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
+		return NULL;
+
+	if (static_branch_likely(&have_mio))
+		return pci_iomap_range_mio(pdev, bar, offset, max);
+	else
+		return pci_iomap_range_fh(pdev, bar, offset, max);
+}
 EXPORT_SYMBOL(pci_iomap_range);
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
@@ -306,7 +310,37 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 }
 EXPORT_SYMBOL(pci_iomap);
 
-void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+static void __iomem *pci_iomap_wc_range_mio(struct pci_dev *pdev, int bar,
+					    unsigned long offset, unsigned long max)
+{
+	unsigned long barsize = pci_resource_len(pdev, bar);
+	struct zpci_dev *zdev = to_zpci(pdev);
+	void __iomem *iova;
+
+	iova = ioremap((unsigned long) zdev->bars[bar].mio_wb, barsize);
+	return iova ? iova + offset : iova;
+}
+
+void __iomem *pci_iomap_wc_range(struct pci_dev *pdev, int bar,
+				 unsigned long offset, unsigned long max)
+{
+	if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
+		return NULL;
+
+	if (static_branch_likely(&have_mio))
+		return pci_iomap_wc_range_mio(pdev, bar, offset, max);
+	else
+		return pci_iomap_range_fh(pdev, bar, offset, max);
+}
+EXPORT_SYMBOL(pci_iomap_wc_range);
+
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL(pci_iomap_wc);
+
+static void pci_iounmap_fh(struct pci_dev *pdev, void __iomem *addr)
 {
 	unsigned int idx = ZPCI_IDX(addr);
 
@@ -319,6 +353,19 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 	}
 	spin_unlock(&zpci_iomap_lock);
 }
+
+static void pci_iounmap_mio(struct pci_dev *pdev, void __iomem *addr)
+{
+	iounmap(addr);
+}
+
+void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+	if (static_branch_likely(&have_mio))
+		pci_iounmap_mio(pdev, addr);
+	else
+		pci_iounmap_fh(pdev, addr);
+}
 EXPORT_SYMBOL(pci_iounmap);
 
 static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
@@ -354,136 +401,6 @@ static struct pci_ops pci_root_ops = {
 	.write = pci_write,
 };
 
-static void zpci_irq_handler(struct airq_struct *airq)
-{
-	unsigned long si, ai;
-	struct airq_iv *aibv;
-	int irqs_on = 0;
-
-	inc_irq_stat(IRQIO_PCI);
-	for (si = 0;;) {
-		/* Scan adapter summary indicator bit vector */
-		si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv));
-		if (si == -1UL) {
-			if (irqs_on++)
-				/* End of second scan with interrupts on. */
-				break;
-			/* First scan complete, reenable interrupts. */
-			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC))
-				break;
-			si = 0;
-			continue;
-		}
-
-		/* Scan the adapter interrupt vector for this device. */
-		aibv = zpci_aibv[si];
-		for (ai = 0;;) {
-			ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
-			if (ai == -1UL)
-				break;
-			inc_irq_stat(IRQIO_MSI);
-			airq_iv_lock(aibv, ai);
-			generic_handle_irq(airq_iv_get_data(aibv, ai));
-			airq_iv_unlock(aibv, ai);
-		}
-	}
-}
-
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
-{
-	struct zpci_dev *zdev = to_zpci(pdev);
-	unsigned int hwirq, msi_vecs;
-	unsigned long aisb;
-	struct msi_desc *msi;
-	struct msi_msg msg;
-	int rc, irq;
-
-	zdev->aisb = -1UL;
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
-
-	/* Allocate adapter summary indicator bit */
-	aisb = airq_iv_alloc_bit(zpci_aisb_iv);
-	if (aisb == -1UL)
-		return -EIO;
-	zdev->aisb = aisb;
-
-	/* Create adapter interrupt vector */
-	zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
-	if (!zdev->aibv)
-		return -ENOMEM;
-
-	/* Wire up shortcut pointer */
-	zpci_aibv[aisb] = zdev->aibv;
-
-	/* Request MSI interrupts */
-	hwirq = 0;
-	for_each_pci_msi_entry(msi, pdev) {
-		if (hwirq >= msi_vecs)
-			break;
-		irq = irq_alloc_desc(0);	/* Alloc irq on node 0 */
-		if (irq < 0)
-			return -ENOMEM;
-		rc = irq_set_msi_desc(irq, msi);
-		if (rc)
-			return rc;
-		irq_set_chip_and_handler(irq, &zpci_irq_chip,
-					 handle_simple_irq);
-		msg.data = hwirq;
-		msg.address_lo = zdev->msi_addr & 0xffffffff;
-		msg.address_hi = zdev->msi_addr >> 32;
-		pci_write_msi_msg(irq, &msg);
-		airq_iv_set_data(zdev->aibv, hwirq, irq);
-		hwirq++;
-	}
-
-	/* Enable adapter interrupts */
-	rc = zpci_set_airq(zdev);
-	if (rc)
-		return rc;
-
-	return (msi_vecs == nvec) ? 0 : msi_vecs;
-}
-
-void arch_teardown_msi_irqs(struct pci_dev *pdev)
-{
-	struct zpci_dev *zdev = to_zpci(pdev);
-	struct msi_desc *msi;
-	int rc;
-
-	/* Disable adapter interrupts */
-	rc = zpci_clear_airq(zdev);
-	if (rc)
-		return;
-
-	/* Release MSI interrupts */
-	for_each_pci_msi_entry(msi, pdev) {
-		if (!msi->irq)
-			continue;
-		if (msi->msi_attrib.is_msix)
-			__pci_msix_desc_mask_irq(msi, 1);
-		else
-			__pci_msi_desc_mask_irq(msi, 1, 1);
-		irq_set_msi_desc(msi->irq, NULL);
-		irq_free_desc(msi->irq);
-		msi->msg.address_lo = 0;
-		msi->msg.address_hi = 0;
-		msi->msg.data = 0;
-		msi->irq = 0;
-	}
-
-	if (zdev->aisb != -1UL) {
-		zpci_aibv[zdev->aisb] = NULL;
-		airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
-		zdev->aisb = -1UL;
-	}
-	if (zdev->aibv) {
-		airq_iv_release(zdev->aibv);
-		zdev->aibv = NULL;
-	}
-}
-
 #ifdef CONFIG_PCI_IOV
 static struct resource iov_res = {
 	.name	= "PCI IOV res",
@@ -495,6 +412,7 @@ static struct resource iov_res = {
 
 static void zpci_map_resources(struct pci_dev *pdev)
 {
+	struct zpci_dev *zdev = to_zpci(pdev);
 	resource_size_t len;
 	int i;
 
@@ -502,8 +420,13 @@ static void zpci_map_resources(struct pci_dev *pdev)
 		len = pci_resource_len(pdev, i);
 		if (!len)
 			continue;
-		pdev->resource[i].start =
-			(resource_size_t __force) pci_iomap(pdev, i, 0);
+
+		if (static_branch_likely(&have_mio))
+			pdev->resource[i].start =
+				(resource_size_t __force) zdev->bars[i].mio_wb;
+		else
+			pdev->resource[i].start =
+				(resource_size_t __force) pci_iomap(pdev, i, 0);
 		pdev->resource[i].end = pdev->resource[i].start + len - 1;
 	}
 
@@ -524,6 +447,9 @@ static void zpci_unmap_resources(struct pci_dev *pdev)
 	resource_size_t len;
 	int i;
 
+	if (static_branch_likely(&have_mio))
+		return;
+
 	for (i = 0; i < PCI_BAR_COUNT; i++) {
 		len = pci_resource_len(pdev, i);
 		if (!len)
@@ -533,41 +459,6 @@ static void zpci_unmap_resources(struct pci_dev *pdev)
 	}
 }
 
-static struct airq_struct zpci_airq = {
-	.handler = zpci_irq_handler,
-	.isc = PCI_ISC,
-};
-
-static int __init zpci_irq_init(void)
-{
-	int rc;
-
-	rc = register_adapter_interrupt(&zpci_airq);
-	if (rc)
-		goto out;
-	/* Set summary to 1 to be called every time for the ISC. */
-	*zpci_airq.lsi_ptr = 1;
-
-	rc = -ENOMEM;
-	zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
-	if (!zpci_aisb_iv)
-		goto out_airq;
-
-	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
-	return 0;
-
-out_airq:
-	unregister_adapter_interrupt(&zpci_airq);
-out:
-	return rc;
-}
-
-static void zpci_irq_exit(void)
-{
-	airq_iv_release(zpci_aisb_iv);
-	unregister_adapter_interrupt(&zpci_airq);
-}
-
 static int zpci_alloc_iomap(struct zpci_dev *zdev)
 {
 	unsigned long entry;
@@ -958,7 +849,9 @@ static void zpci_mem_exit(void)
 	kmem_cache_destroy(zdev_fmb_cache);
 }
 
-static unsigned int s390_pci_probe = 1;
+static unsigned int s390_pci_probe __initdata = 1;
+static unsigned int s390_pci_no_mio __initdata;
+unsigned int s390_pci_force_floating __initdata;
 static unsigned int s390_pci_initialized;
 
 char * __init pcibios_setup(char *str)
@@ -967,6 +860,14 @@ char * __init pcibios_setup(char *str)
 		s390_pci_probe = 0;
 		return NULL;
 	}
+	if (!strcmp(str, "nomio")) {
+		s390_pci_no_mio = 1;
+		return NULL;
+	}
+	if (!strcmp(str, "force_floating")) {
+		s390_pci_force_floating = 1;
+		return NULL;
+	}
 	return str;
 }
 
@@ -985,6 +886,9 @@ static int __init pci_base_init(void)
 	if (!test_facility(69) || !test_facility(71))
 		return 0;
 
+	if (test_facility(153) && !s390_pci_no_mio)
+		static_branch_enable(&have_mio);
+
 	rc = zpci_debug_init();
 	if (rc)
 		goto out;
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index eeb7450db18c..3a36b07a5571 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -163,7 +163,14 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev,
 		memcpy(zdev->util_str, response->util_str,
 		       sizeof(zdev->util_str));
 	}
+	zdev->mio_capable = response->mio_addr_avail;
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		if (!(response->mio_valid & (1 << (PCI_BAR_COUNT - i - 1))))
+			continue;
 
+		zdev->bars[i].mio_wb = (void __iomem *) response->addr[i].wb;
+		zdev->bars[i].mio_wt = (void __iomem *) response->addr[i].wt;
+	}
 	return 0;
 }
 
@@ -279,11 +286,18 @@ int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
 	int rc;
 
 	rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
-	if (!rc)
-		/* Success -> store enabled handle in zdev */
-		zdev->fh = fh;
+	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+	if (rc)
+		goto out;
 
-	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
+	zdev->fh = fh;
+	if (zdev->mio_capable) {
+		rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_MIO);
+		zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+		if (rc)
+			clp_disable_fh(zdev);
+	}
+out:
 	return rc;
 }
 
@@ -296,11 +310,10 @@ int clp_disable_fh(struct zpci_dev *zdev)
 		return 0;
 
 	rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
+	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
 	if (!rc)
-		/* Success -> store disabled handle in zdev */
 		zdev->fh = fh;
 
-	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
 	return rc;
 }
 
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index f069929e8211..02f9505c99a8 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -8,9 +8,11 @@
 #include <linux/export.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
+#include <linux/jump_label.h>
 #include <asm/facility.h>
 #include <asm/pci_insn.h>
 #include <asm/pci_debug.h>
+#include <asm/pci_io.h>
 #include <asm/processor.h>
 
 #define ZPCI_INSN_BUSY_DELAY	1	/* 1 microsecond */
@@ -96,13 +98,15 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 }
 
 /* Set Interruption Controls */
-int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
 {
 	if (!test_facility(72))
 		return -EIO;
-	asm volatile (
-		"	.insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
-		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+
+	asm volatile(
+		".insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[iib]\n"
+		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [iib] "Q" (*iib));
+
 	return 0;
 }
 
@@ -140,7 +144,7 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int zpci_load(u64 *data, u64 req, u64 offset)
+int __zpci_load(u64 *data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -156,6 +160,52 @@ int zpci_load(u64 *data, u64 req, u64 offset)
 
 	return (cc > 0) ? -EIO : cc;
 }
+EXPORT_SYMBOL_GPL(__zpci_load);
+
+static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr,
+			       unsigned long len)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+
+	return __zpci_load(data, req, ZPCI_OFFSET(addr));
+}
+
+static inline int __pcilg_mio(u64 *data, u64 ioaddr, u64 len, u8 *status)
+{
+	register u64 addr asm("2") = ioaddr;
+	register u64 r3 asm("3") = len;
+	int cc = -ENXIO;
+	u64 __data;
+
+	asm volatile (
+		"       .insn   rre,0xb9d60000,%[data],%[ioaddr]\n"
+		"0:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [data] "=d" (__data), "+d" (r3)
+		: [ioaddr] "d" (addr)
+		: "cc");
+	*status = r3 >> 24 & 0xff;
+	*data = __data;
+	return cc;
+}
+
+int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len)
+{
+	u8 status;
+	int cc;
+
+	if (!static_branch_unlikely(&have_mio))
+		return zpci_load_fh(data, addr, len);
+
+	cc = __pcilg_mio(data, (__force u64) addr, len, &status);
+	if (cc)
+		zpci_err_insn(cc, status, 0, (__force u64) addr);
+
+	return (cc > 0) ? -EIO : cc;
+}
 EXPORT_SYMBOL_GPL(zpci_load);
 
 /* PCI Store */
@@ -178,7 +228,7 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int zpci_store(u64 data, u64 req, u64 offset)
+int __zpci_store(u64 data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -194,6 +244,50 @@ int zpci_store(u64 data, u64 req, u64 offset)
 
 	return (cc > 0) ? -EIO : cc;
 }
+EXPORT_SYMBOL_GPL(__zpci_store);
+
+static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data,
+				unsigned long len)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+
+	return __zpci_store(data, req, ZPCI_OFFSET(addr));
+}
+
+static inline int __pcistg_mio(u64 data, u64 ioaddr, u64 len, u8 *status)
+{
+	register u64 addr asm("2") = ioaddr;
+	register u64 r3 asm("3") = len;
+	int cc = -ENXIO;
+
+	asm volatile (
+		"       .insn   rre,0xb9d40000,%[data],%[ioaddr]\n"
+		"0:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), "+d" (r3)
+		: [data] "d" (data), [ioaddr] "d" (addr)
+		: "cc");
+	*status = r3 >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len)
+{
+	u8 status;
+	int cc;
+
+	if (!static_branch_unlikely(&have_mio))
+		return zpci_store_fh(addr, data, len);
+
+	cc = __pcistg_mio(data, (__force u64) addr, len, &status);
+	if (cc)
+		zpci_err_insn(cc, status, 0, (__force u64) addr);
+
+	return (cc > 0) ? -EIO : cc;
+}
 EXPORT_SYMBOL_GPL(zpci_store);
 
 /* PCI Store Block */
@@ -214,7 +308,7 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int zpci_store_block(const u64 *data, u64 req, u64 offset)
+int __zpci_store_block(const u64 *data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -230,4 +324,63 @@ int zpci_store_block(const u64 *data, u64 req, u64 offset)
 
 	return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(zpci_store_block);
+EXPORT_SYMBOL_GPL(__zpci_store_block);
+
+static inline int zpci_write_block_fh(volatile void __iomem *dst,
+				      const void *src, unsigned long len)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+	u64 offset = ZPCI_OFFSET(dst);
+
+	return __zpci_store_block(src, req, offset);
+}
+
+static inline int __pcistb_mio(const u64 *data, u64 ioaddr, u64 len, u8 *status)
+{
+	int cc = -ENXIO;
+
+	asm volatile (
+		"       .insn   rsy,0xeb00000000d4,%[len],%[ioaddr],%[data]\n"
+		"0:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [len] "+d" (len)
+		: [ioaddr] "d" (ioaddr), [data] "Q" (*data)
+		: "cc");
+	*status = len >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_write_block(volatile void __iomem *dst,
+		     const void *src, unsigned long len)
+{
+	u8 status;
+	int cc;
+
+	if (!static_branch_unlikely(&have_mio))
+		return zpci_write_block_fh(dst, src, len);
+
+	cc = __pcistb_mio(src, (__force u64) dst, len, &status);
+	if (cc)
+		zpci_err_insn(cc, status, 0, (__force u64) dst);
+
+	return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(zpci_write_block);
+
+static inline void __pciwb_mio(void)
+{
+	unsigned long unused = 0;
+
+	asm volatile (".insn    rre,0xb9d50000,%[op],%[op]\n"
+		      : [op] "+d" (unused));
+}
+
+void zpci_barrier(void)
+{
+	if (static_branch_likely(&have_mio))
+		__pciwb_mio();
+}
+EXPORT_SYMBOL_GPL(zpci_barrier);
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
new file mode 100644
index 000000000000..d80616ae8dd8
--- /dev/null
+++ b/arch/s390/pci/pci_irq.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/kernel_stat.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/smp.h>
+
+#include <asm/isc.h>
+#include <asm/airq.h>
+
+static enum {FLOATING, DIRECTED} irq_delivery;
+
+#define	SIC_IRQ_MODE_ALL		0
+#define	SIC_IRQ_MODE_SINGLE		1
+#define	SIC_IRQ_MODE_DIRECT		4
+#define	SIC_IRQ_MODE_D_ALL		16
+#define	SIC_IRQ_MODE_D_SINGLE		17
+#define	SIC_IRQ_MODE_SET_CPU		18
+
+/*
+ * summary bit vector
+ * FLOATING - summary bit per function
+ * DIRECTED - summary bit per cpu (only used in fallback path)
+ */
+static struct airq_iv *zpci_sbv;
+
+/*
+ * interrupt bit vectors
+ * FLOATING - interrupt bit vector per function
+ * DIRECTED - interrupt bit vector per cpu
+ */
+static struct airq_iv **zpci_ibv;
+
+/* Modify PCI: Register adapter interruptions */
+static int zpci_set_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+	struct zpci_fib fib = {0};
+	u8 status;
+
+	fib.fmt0.isc = PCI_ISC;
+	fib.fmt0.sum = 1;	/* enable summary notifications */
+	fib.fmt0.noi = airq_iv_end(zdev->aibv);
+	fib.fmt0.aibv = (unsigned long) zdev->aibv->vector;
+	fib.fmt0.aibvo = 0;	/* each zdev has its own interrupt vector */
+	fib.fmt0.aisb = (unsigned long) zpci_sbv->vector + (zdev->aisb/64)*8;
+	fib.fmt0.aisbo = zdev->aisb & 63;
+
+	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister adapter interruptions */
+static int zpci_clear_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
+	struct zpci_fib fib = {0};
+	u8 cc, status;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc == 3 || (cc == 1 && status == 24))
+		/* Function already gone or IRQs already deregistered. */
+		cc = 0;
+
+	return cc ? -EIO : 0;
+}
+
+/* Modify PCI: Register CPU directed interruptions */
+static int zpci_set_directed_irq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT_D);
+	struct zpci_fib fib = {0};
+	u8 status;
+
+	fib.fmt = 1;
+	fib.fmt1.noi = zdev->msi_nr_irqs;
+	fib.fmt1.dibvo = zdev->msi_first_bit;
+
+	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister CPU directed interruptions */
+static int zpci_clear_directed_irq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT_D);
+	struct zpci_fib fib = {0};
+	u8 cc, status;
+
+	fib.fmt = 1;
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc == 3 || (cc == 1 && status == 24))
+		/* Function already gone or IRQs already deregistered. */
+		cc = 0;
+
+	return cc ? -EIO : 0;
+}
+
+static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *dest,
+				 bool force)
+{
+	struct msi_desc *entry = irq_get_msi_desc(data->irq);
+	struct msi_msg msg = entry->msg;
+
+	msg.address_lo &= 0xff0000ff;
+	msg.address_lo |= (cpumask_first(dest) << 8);
+	pci_write_msi_msg(data->irq, &msg);
+
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip zpci_irq_chip = {
+	.name = "PCI-MSI",
+	.irq_unmask = pci_msi_unmask_irq,
+	.irq_mask = pci_msi_mask_irq,
+	.irq_set_affinity = zpci_set_irq_affinity,
+};
+
+static void zpci_handle_cpu_local_irq(bool rescan)
+{
+	struct airq_iv *dibv = zpci_ibv[smp_processor_id()];
+	unsigned long bit;
+	int irqs_on = 0;
+
+	for (bit = 0;;) {
+		/* Scan the directed IRQ bit vector */
+		bit = airq_iv_scan(dibv, bit, airq_iv_end(dibv));
+		if (bit == -1UL) {
+			if (!rescan || irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC))
+				break;
+			bit = 0;
+			continue;
+		}
+		inc_irq_stat(IRQIO_MSI);
+		generic_handle_irq(airq_iv_get_data(dibv, bit));
+	}
+}
+
+struct cpu_irq_data {
+	call_single_data_t csd;
+	atomic_t scheduled;
+};
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_irq_data, irq_data);
+
+static void zpci_handle_remote_irq(void *data)
+{
+	atomic_t *scheduled = data;
+
+	do {
+		zpci_handle_cpu_local_irq(false);
+	} while (atomic_dec_return(scheduled));
+}
+
+static void zpci_handle_fallback_irq(void)
+{
+	struct cpu_irq_data *cpu_data;
+	unsigned long cpu;
+	int irqs_on = 0;
+
+	for (cpu = 0;;) {
+		cpu = airq_iv_scan(zpci_sbv, cpu, airq_iv_end(zpci_sbv));
+		if (cpu == -1UL) {
+			if (irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+				break;
+			cpu = 0;
+			continue;
+		}
+		cpu_data = &per_cpu(irq_data, cpu);
+		if (atomic_inc_return(&cpu_data->scheduled) > 1)
+			continue;
+
+		cpu_data->csd.func = zpci_handle_remote_irq;
+		cpu_data->csd.info = &cpu_data->scheduled;
+		cpu_data->csd.flags = 0;
+		smp_call_function_single_async(cpu, &cpu_data->csd);
+	}
+}
+
+static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
+{
+	if (floating) {
+		inc_irq_stat(IRQIO_PCF);
+		zpci_handle_fallback_irq();
+	} else {
+		inc_irq_stat(IRQIO_PCD);
+		zpci_handle_cpu_local_irq(true);
+	}
+}
+
+static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
+{
+	unsigned long si, ai;
+	struct airq_iv *aibv;
+	int irqs_on = 0;
+
+	inc_irq_stat(IRQIO_PCF);
+	for (si = 0;;) {
+		/* Scan adapter summary indicator bit vector */
+		si = airq_iv_scan(zpci_sbv, si, airq_iv_end(zpci_sbv));
+		if (si == -1UL) {
+			if (irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+				break;
+			si = 0;
+			continue;
+		}
+
+		/* Scan the adapter interrupt vector for this device. */
+		aibv = zpci_ibv[si];
+		for (ai = 0;;) {
+			ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
+			if (ai == -1UL)
+				break;
+			inc_irq_stat(IRQIO_MSI);
+			airq_iv_lock(aibv, ai);
+			generic_handle_irq(airq_iv_get_data(aibv, ai));
+			airq_iv_unlock(aibv, ai);
+		}
+	}
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	unsigned int hwirq, msi_vecs, cpu;
+	unsigned long bit;
+	struct msi_desc *msi;
+	struct msi_msg msg;
+	int rc, irq;
+
+	zdev->aisb = -1UL;
+	zdev->msi_first_bit = -1U;
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+
+	if (irq_delivery == DIRECTED) {
+		/* Allocate cpu vector bits */
+		bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
+		if (bit == -1UL)
+			return -EIO;
+	} else {
+		/* Allocate adapter summary indicator bit */
+		bit = airq_iv_alloc_bit(zpci_sbv);
+		if (bit == -1UL)
+			return -EIO;
+		zdev->aisb = bit;
+
+		/* Create adapter interrupt vector */
+		zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+		if (!zdev->aibv)
+			return -ENOMEM;
+
+		/* Wire up shortcut pointer */
+		zpci_ibv[bit] = zdev->aibv;
+		/* Each function has its own interrupt vector */
+		bit = 0;
+	}
+
+	/* Request MSI interrupts */
+	hwirq = bit;
+	for_each_pci_msi_entry(msi, pdev) {
+		rc = -EIO;
+		if (hwirq - bit >= msi_vecs)
+			break;
+		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, msi->affinity);
+		if (irq < 0)
+			return -ENOMEM;
+		rc = irq_set_msi_desc(irq, msi);
+		if (rc)
+			return rc;
+		irq_set_chip_and_handler(irq, &zpci_irq_chip,
+					 handle_percpu_irq);
+		msg.data = hwirq;
+		if (irq_delivery == DIRECTED) {
+			msg.address_lo = zdev->msi_addr & 0xff0000ff;
+			msg.address_lo |= msi->affinity ?
+				(cpumask_first(&msi->affinity->mask) << 8) : 0;
+			for_each_possible_cpu(cpu) {
+				airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
+			}
+		} else {
+			msg.address_lo = zdev->msi_addr & 0xffffffff;
+			airq_iv_set_data(zdev->aibv, hwirq, irq);
+		}
+		msg.address_hi = zdev->msi_addr >> 32;
+		pci_write_msi_msg(irq, &msg);
+		hwirq++;
+	}
+
+	zdev->msi_first_bit = bit;
+	zdev->msi_nr_irqs = msi_vecs;
+
+	if (irq_delivery == DIRECTED)
+		rc = zpci_set_directed_irq(zdev);
+	else
+		rc = zpci_set_airq(zdev);
+	if (rc)
+		return rc;
+
+	return (msi_vecs == nvec) ? 0 : msi_vecs;
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	struct msi_desc *msi;
+	int rc;
+
+	/* Disable interrupts */
+	if (irq_delivery == DIRECTED)
+		rc = zpci_clear_directed_irq(zdev);
+	else
+		rc = zpci_clear_airq(zdev);
+	if (rc)
+		return;
+
+	/* Release MSI interrupts */
+	for_each_pci_msi_entry(msi, pdev) {
+		if (!msi->irq)
+			continue;
+		if (msi->msi_attrib.is_msix)
+			__pci_msix_desc_mask_irq(msi, 1);
+		else
+			__pci_msi_desc_mask_irq(msi, 1, 1);
+		irq_set_msi_desc(msi->irq, NULL);
+		irq_free_desc(msi->irq);
+		msi->msg.address_lo = 0;
+		msi->msg.address_hi = 0;
+		msi->msg.data = 0;
+		msi->irq = 0;
+	}
+
+	if (zdev->aisb != -1UL) {
+		zpci_ibv[zdev->aisb] = NULL;
+		airq_iv_free_bit(zpci_sbv, zdev->aisb);
+		zdev->aisb = -1UL;
+	}
+	if (zdev->aibv) {
+		airq_iv_release(zdev->aibv);
+		zdev->aibv = NULL;
+	}
+
+	if ((irq_delivery == DIRECTED) && zdev->msi_first_bit != -1U)
+		airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs);
+}
+
+static struct airq_struct zpci_airq = {
+	.handler = zpci_floating_irq_handler,
+	.isc = PCI_ISC,
+};
+
+static void __init cpu_enable_directed_irq(void *unused)
+{
+	union zpci_sic_iib iib = {{0}};
+
+	iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
+
+	__zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC);
+}
+
+static int __init zpci_directed_irq_init(void)
+{
+	union zpci_sic_iib iib = {{0}};
+	unsigned int cpu;
+
+	zpci_sbv = airq_iv_create(num_possible_cpus(), 0);
+	if (!zpci_sbv)
+		return -ENOMEM;
+
+	iib.diib.isc = PCI_ISC;
+	iib.diib.nr_cpus = num_possible_cpus();
+	iib.diib.disb_addr = (u64) zpci_sbv->vector;
+	__zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
+
+	zpci_ibv = kcalloc(num_possible_cpus(), sizeof(*zpci_ibv),
+			   GFP_KERNEL);
+	if (!zpci_ibv)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * Per CPU IRQ vectors look the same but bit-allocation
+		 * is only done on the first vector.
+		 */
+		zpci_ibv[cpu] = airq_iv_create(cache_line_size() * BITS_PER_BYTE,
+					       AIRQ_IV_DATA |
+					       AIRQ_IV_CACHELINE |
+					       (!cpu ? AIRQ_IV_ALLOC : 0));
+		if (!zpci_ibv[cpu])
+			return -ENOMEM;
+	}
+	on_each_cpu(cpu_enable_directed_irq, NULL, 1);
+
+	zpci_irq_chip.irq_set_affinity = zpci_set_irq_affinity;
+
+	return 0;
+}
+
+static int __init zpci_floating_irq_init(void)
+{
+	zpci_ibv = kcalloc(ZPCI_NR_DEVICES, sizeof(*zpci_ibv), GFP_KERNEL);
+	if (!zpci_ibv)
+		return -ENOMEM;
+
+	zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+	if (!zpci_sbv)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	kfree(zpci_ibv);
+	return -ENOMEM;
+}
+
+int __init zpci_irq_init(void)
+{
+	int rc;
+
+	irq_delivery = sclp.has_dirq ? DIRECTED : FLOATING;
+	if (s390_pci_force_floating)
+		irq_delivery = FLOATING;
+
+	if (irq_delivery == DIRECTED)
+		zpci_airq.handler = zpci_directed_irq_handler;
+
+	rc = register_adapter_interrupt(&zpci_airq);
+	if (rc)
+		goto out;
+	/* Set summary to 1 to be called every time for the ISC. */
+	*zpci_airq.lsi_ptr = 1;
+
+	switch (irq_delivery) {
+	case FLOATING:
+		rc = zpci_floating_irq_init();
+		break;
+	case DIRECTED:
+		rc = zpci_directed_irq_init();
+		break;
+	}
+
+	if (rc)
+		goto out_airq;
+
+	/*
+	 * Enable floating IRQs (with suppression after one IRQ). When using
+	 * directed IRQs this enables the fallback path.
+	 */
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC);
+
+	return 0;
+out_airq:
+	unregister_adapter_interrupt(&zpci_airq);
+out:
+	return rc;
+}
+
+void __init zpci_irq_exit(void)
+{
+	unsigned int cpu;
+
+	if (irq_delivery == DIRECTED) {
+		for_each_possible_cpu(cpu) {
+			airq_iv_release(zpci_ibv[cpu]);
+		}
+	}
+	kfree(zpci_ibv);
+	if (zpci_sbv)
+		airq_iv_release(zpci_sbv);
+	unregister_adapter_interrupt(&zpci_airq);
+}
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index ce6a3f75065b..dc1ae4ff79d7 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -4,7 +4,7 @@ OBJECT_FILES_NON_STANDARD := y
 
 purgatory-y := head.o purgatory.o string.o sha256.o mem.o
 
-targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
+targets += $(purgatory-y) purgatory.lds purgatory purgatory.ro
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
 $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
@@ -16,22 +16,26 @@ $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 $(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
-LDFLAGS_purgatory.ro += -z nodefaultlib
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
+KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 
-$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+LDFLAGS_purgatory := -r --no-undefined -nostdlib -z nodefaultlib -T
+$(obj)/purgatory: $(obj)/purgatory.lds $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
 
-quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
+OBJCOPYFLAGS_purgatory.ro := -O elf64-s390
+OBJCOPYFLAGS_purgatory.ro += --remove-section='*debug*'
+OBJCOPYFLAGS_purgatory.ro += --remove-section='.comment'
+OBJCOPYFLAGS_purgatory.ro += --remove-section='.note.*'
+$(obj)/purgatory.ro: $(obj)/purgatory FORCE
+		$(call if_changed,objcopy)
 
-$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
-	$(call if_changed,bin2c)
+$(obj)/kexec-purgatory.o: $(obj)/kexec-purgatory.S $(obj)/purgatory.ro FORCE
+	$(call if_changed_rule,as_o_S)
 
 obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += kexec-purgatory.o
diff --git a/arch/s390/purgatory/kexec-purgatory.S b/arch/s390/purgatory/kexec-purgatory.S
new file mode 100644
index 000000000000..8293753100ae
--- /dev/null
+++ b/arch/s390/purgatory/kexec-purgatory.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+	.section .rodata, "a"
+
+	.align	8
+kexec_purgatory:
+	.globl	kexec_purgatory
+	.incbin	"arch/s390/purgatory/purgatory.ro"
+.Lkexec_purgatroy_end:
+
+	.align	8
+kexec_purgatory_size:
+	.globl	kexec_purgatory_size
+	.quad	.Lkexec_purgatroy_end - kexec_purgatory
diff --git a/arch/s390/purgatory/purgatory.lds.S b/arch/s390/purgatory/purgatory.lds.S
new file mode 100644
index 000000000000..482eb4fbcef1
--- /dev/null
+++ b/arch/s390/purgatory/purgatory.lds.S
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm-generic/vmlinux.lds.h>
+
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+
+ENTRY(purgatory_start)
+
+SECTIONS
+{
+	. = 0;
+	.head.text : {
+		_head = . ;
+		HEAD_TEXT
+		_ehead = . ;
+	}
+	.text :	{
+		_text = .;	/* Text */
+		*(.text)
+		*(.text.*)
+		_etext = . ;
+	}
+	.rodata : {
+		_rodata = . ;
+		*(.rodata)	 /* read-only data */
+		*(.rodata.*)
+		_erodata = . ;
+	}
+	.data :	{
+		_data = . ;
+		*(.data)
+		*(.data.*)
+		_edata = . ;
+	}
+
+	. = ALIGN(256);
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		. = ALIGN(8);	/* For convenience during zeroing */
+		_ebss = .;
+	}
+	_end = .;
+
+	/* Sections to be discarded */
+	/DISCARD/ : {
+		*(.eh_frame)
+		*(*__ksymtab*)
+		*(___kcrctab*)
+	}
+}
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index cd7e8f4419f5..884a9caff5fb 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -11,7 +11,8 @@ chkbss: $(addprefix $(obj)/, $(chkbss-files))
 
 quiet_cmd_chkbss = CHKBSS  $<
       cmd_chkbss = \
-	if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
+	if $(OBJDUMP) -h $< | grep -q "\.bss" && \
+	   ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
 		echo "error: $< .bss section is not empty" >&2; exit 1; \
 	fi; \
 	touch $@;
diff --git a/arch/s390/tools/opcodes.txt b/arch/s390/tools/opcodes.txt
index 1cbed82cd17b..64638b764d1c 100644
--- a/arch/s390/tools/opcodes.txt
+++ b/arch/s390/tools/opcodes.txt
@@ -1,3 +1,5 @@
+0000	illegal	E
+0002	brkpt	E
 0101	pr	E
 0102	upt	E
 0104	ptff	E
@@ -257,6 +259,7 @@ b258	bsg	RRE_RR
 b25a	bsa	RRE_RR
 b25d	clst	RRE_RR
 b25e	srst	RRE_RR
+b25f	chsc	RRE_R0
 b263	cmpsc	RRE_RR
 b274	siga	S_RD
 b276	xsch	S_00
@@ -277,6 +280,9 @@ b29d	lfpc	S_RD
 b2a5	tre	RRE_RR
 b2a6	cu21	RRF_U0RR
 b2a7	cu12	RRF_U0RR
+b2ad	nqap	RRE_RR
+b2ae	dqap	RRE_RR
+b2af	pqap	RRE_RR
 b2b0	stfle	S_RD
 b2b1	stfl	S_RD
 b2b2	lpswe	S_RD
@@ -290,6 +296,7 @@ b2e5	epctr	RRE_RR
 b2e8	ppa	RRF_U0RR
 b2ec	etnd	RRE_R0
 b2ed	ecpga	RRE_RR
+b2f0	iucv	RRE_RR
 b2f8	tend	S_00
 b2fa	niai	IE_UU
 b2fc	tabort	S_RD
@@ -559,12 +566,15 @@ b998	alcr	RRE_RR
 b999	slbr	RRE_RR
 b99a	epair	RRE_R0
 b99b	esair	RRE_R0
+b99c	eqbs	RRF_U0RR
 b99d	esea	RRE_R0
 b99e	pti	RRE_RR
 b99f	ssair	RRE_R0
+b9a0	clp	RRF_U0RR
 b9a1	tpei	RRE_RR
 b9a2	ptf	RRE_R0
 b9aa	lptea	RRF_RURR2
+b9ab	essa	RRF_U0RR
 b9ac	irbm	RRE_RR
 b9ae	rrbm	RRE_RR
 b9af	pfmf	RRE_RR
@@ -1039,6 +1049,7 @@ eb7a	agsi	SIY_IRD
 eb7e	algsi	SIY_IRD
 eb80	icmh	RSY_RURD
 eb81	icmy	RSY_RURD
+eb8a	sqbs	RSY_RDRU
 eb8e	mvclu	RSY_RRRD
 eb8f	clclu	RSY_RRRD
 eb90	stmy	RSY_RRRD
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index b1c91ea9a958..0be08d586d40 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -90,12 +90,6 @@ config ARCH_DEFCONFIG
 	default "arch/sh/configs/shx3_defconfig" if SUPERH32
 	default "arch/sh/configs/cayman_defconfig" if SUPERH64
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config GENERIC_BUG
 	def_bool y
 	depends on BUG && SUPERH32
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 7bf2cb680d32..73fff39a0122 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -17,7 +17,6 @@ generic-y += mm-arch-hooks.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += serial.h
 generic-y += sizes.h
 generic-y += trace_clock.h
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 4f7f235f15f8..c28e37a344ad 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -229,9 +229,6 @@ __BUILD_IOPORT_STRING(q, u64)
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-/* synco on SH-4A, otherwise a nop */
-#define mmiowb()		wmb()
-
 /* We really want to try and get these to memcpy etc */
 void memcpy_fromio(void *, const volatile void __iomem *, unsigned long);
 void memcpy_toio(volatile void __iomem *, const void *, unsigned long);
diff --git a/arch/sh/include/asm/mmiowb.h b/arch/sh/include/asm/mmiowb.h
new file mode 100644
index 000000000000..535d59735f1d
--- /dev/null
+++ b/arch/sh/include/asm/mmiowb.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_SH_MMIOWB_H
+#define __ASM_SH_MMIOWB_H
+
+#include <asm/barrier.h>
+
+/* synco on SH-4A, otherwise a nop */
+#define mmiowb()			wmb()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* __ASM_SH_MMIOWB_H */
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 8ad73cb31121..b56f908b1395 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -70,6 +70,15 @@ do {							\
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
+#if CONFIG_PGTABLE_LEVELS > 2
+#define __pmd_free_tlb(tlb, pmdp, addr)			\
+do {							\
+	struct page *page = virt_to_page(pmdp);		\
+	pgtable_pmd_page_dtor(page);			\
+	tlb_remove_page((tlb), page);			\
+} while (0);
+#endif
+
 static inline void check_pgt_cache(void)
 {
 	quicklist_trim(QUICK_PT, NULL, 25, 16);
diff --git a/arch/sh/include/asm/spinlock-llsc.h b/arch/sh/include/asm/spinlock-llsc.h
index 786ee0fde3b0..7fd929cd2e7a 100644
--- a/arch/sh/include/asm/spinlock-llsc.h
+++ b/arch/sh/include/asm/spinlock-llsc.h
@@ -47,6 +47,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
 	__asm__ __volatile__ (
 		"mov		#1, %0 ! arch_spin_unlock	\n\t"
 		"mov.l		%0, @%1				\n\t"
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 77abe192fb43..bc77f3dd4261 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -11,133 +11,8 @@
 
 #ifdef CONFIG_MMU
 #include <linux/swap.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
 
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		fullmm;
-	unsigned long		start, end;
-};
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-
-	init_tlb_gather(tlb);
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (tlb->fullmm || force)
-		flush_tlb_mm(tlb->mm);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-}
-
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-}
-
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm && tlb->end) {
-		flush_tlb_range(vma, tlb->start, tlb->end);
-		init_tlb_gather(tlb);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-}
-
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	__tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
-#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
+#include <asm-generic/tlb.h>
 
 #if defined(CONFIG_CPU_SH4) || defined(CONFIG_SUPERH64)
 extern void tlb_wire_entry(struct vm_area_struct *, unsigned long, pte_t);
@@ -157,11 +32,6 @@ static inline void tlb_unwire_entry(void)
 
 #else /* CONFIG_MMU */
 
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, address)	do { } while (0)
-#define tlb_flush(tlb)					do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif /* CONFIG_MMU */
diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c
index f3cb2cccb262..2950b19ad077 100644
--- a/arch/sh/kernel/stacktrace.c
+++ b/arch/sh/kernel/stacktrace.c
@@ -49,8 +49,6 @@ void save_stack_trace(struct stack_trace *trace)
 	unsigned long *sp = (unsigned long *)current_stack_pointer;
 
 	unwind_stack(current, NULL, sp,  &save_stack_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
@@ -84,7 +82,5 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	unsigned long *sp = (unsigned long *)tsk->thread.sp;
 
 	unwind_stack(current, NULL, sp,  &save_stack_ops_nosched, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 40f8f4f73fe8..f6421c9ce5d3 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -63,6 +63,7 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
@@ -191,14 +192,6 @@ config NR_CPUS
 
 source "kernel/Kconfig.hz"
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y if SPARC32
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y if SPARC64
-
 config GENERIC_HWEIGHT
 	bool
 	default y
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index a22cfd5c0ee8..95c44380b1d6 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -15,10 +15,10 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += msi.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += word-at-a-time.h
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index b162c23ae8c2..688911051b44 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -396,8 +396,6 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 	}
 }
 
-#define mmiowb()
-
 #ifdef __KERNEL__
 
 /* On sparc64 we have the whole physical IO address space accessible
diff --git a/arch/sparc/include/asm/tlb_32.h b/arch/sparc/include/asm/tlb_32.h
index 343cea19e573..5cd28a8793e3 100644
--- a/arch/sparc/include/asm/tlb_32.h
+++ b/arch/sparc/include/asm/tlb_32.h
@@ -2,24 +2,6 @@
 #ifndef _SPARC_TLB_H
 #define _SPARC_TLB_H
 
-#define tlb_start_vma(tlb, vma) \
-do {								\
-	flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define tlb_end_vma(tlb, vma) \
-do {								\
-	flush_tlb_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
-	do { } while (0)
-
-#define tlb_flush(tlb) \
-do {								\
-	flush_tlb_mm((tlb)->mm);				\
-} while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _SPARC_TLB_H */
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 00bcbe2326d9..b506ad06aefc 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index dce6db147f24..70ee60383900 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -2,162 +2,8 @@
 #ifndef __UM_TLB_H
 #define __UM_TLB_H
 
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/percpu.h>
-#include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		need_flush; /* Really unmapped some ptes? */
-	unsigned long		start;
-	unsigned long		end;
-	unsigned int		fullmm; /* non-zero means full mm flush */
-};
-
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->need_flush = 0;
-
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-
-	init_tlb_gather(tlb);
-}
-
-extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
-			       unsigned long end);
-
-static inline void
-tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
-}
-
-static inline void
-tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	init_tlb_gather(tlb);
-}
-
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	if (!tlb->need_flush)
-		return;
-
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* arch_tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->start = start;
-		tlb->end = end;
-		tlb->need_flush = 1;
-	}
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-}
-
-/* tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
- *	while handling the additional races in SMP caused by other CPUs
- *	caching valid mappings in their TLBs.
- */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	__tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-/**
- * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
- *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate.   This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
- */
-#define tlb_remove_tlb_entry(tlb, ptep, address)		\
-	do {							\
-		tlb->need_flush = 1;				\
-		__tlb_remove_tlb_entry(tlb, ptep, address);	\
-	} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
-
-#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr)
-
-#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
-
-#define tlb_migrate_finish(mm) do {} while (0)
+#include <asm-generic/cacheflush.h>
+#include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c
index ebe7bcf62684..bd95e020d509 100644
--- a/arch/um/kernel/stacktrace.c
+++ b/arch/um/kernel/stacktrace.c
@@ -63,8 +63,6 @@ static const struct stacktrace_ops dump_ops = {
 static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace)
 {
 	dump_trace(tsk, &dump_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace(struct stack_trace *trace)
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 817d82608712..2445dfcf6444 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -20,6 +20,7 @@ config UNICORE32
 	select GENERIC_IOMAP
 	select MODULES_USE_ELF_REL
 	select NEED_DMA_MAP_STATE
+	select MMU_GATHER_NO_RANGE if MMU
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
@@ -38,12 +39,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	bool
 
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index d77d953c04c1..b301a0b3c0b2 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += parport.h
 generic-y += percpu.h
diff --git a/arch/unicore32/include/asm/tlb.h b/arch/unicore32/include/asm/tlb.h
index 9cca15cdae94..00a8477333f6 100644
--- a/arch/unicore32/include/asm/tlb.h
+++ b/arch/unicore32/include/asm/tlb.h
@@ -12,10 +12,9 @@
 #ifndef __UNICORE_TLB_H__
 #define __UNICORE_TLB_H__
 
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+/*
+ * unicore32 lacks an efficient flush_tlb_range(), use flush_tlb_mm().
+ */
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 	do {							\
diff --git a/arch/unicore32/kernel/stacktrace.c b/arch/unicore32/kernel/stacktrace.c
index 9976e767d51c..e37da8c6837b 100644
--- a/arch/unicore32/kernel/stacktrace.c
+++ b/arch/unicore32/kernel/stacktrace.c
@@ -120,8 +120,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace(struct stack_trace *trace)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 62fc3fda1a05..0a3cc347143f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -14,6 +14,7 @@ config X86_32
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select CLKSRC_I8253
 	select CLONE_BACKWARDS
+	select HAVE_DEBUG_STACKOVERFLOW
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
 
@@ -28,7 +29,6 @@ config X86_64
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE
 	select SWIOTLB
-	select X86_DEV_DMA_OPS
 	select ARCH_HAS_SYSCALL_WRAPPER
 
 #
@@ -65,6 +65,7 @@ config X86
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
@@ -74,6 +75,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
@@ -138,7 +140,6 @@ config X86
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
@@ -183,7 +184,6 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if PARAVIRT
-	select HAVE_RCU_TABLE_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
@@ -268,9 +268,6 @@ config ARCH_MAY_HAVE_PC_FDC
 	def_bool y
 	depends on ISA_DMA_API
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
@@ -703,8 +700,6 @@ config STA2X11
 	bool "STA2X11 Companion Chip Support"
 	depends on X86_32_NON_STANDARD && PCI
 	select ARCH_HAS_PHYS_TO_DMA
-	select X86_DEV_DMA_OPS
-	select X86_DMA_REMAP
 	select SWIOTLB
 	select MFD_STA2X11
 	select GPIOLIB
@@ -783,14 +778,6 @@ config PARAVIRT_SPINLOCKS
 
 	  If you are unsure how to answer this question, answer Y.
 
-config QUEUED_LOCK_STAT
-	bool "Paravirt queued spinlock statistics"
-	depends on PARAVIRT_SPINLOCKS && DEBUG_FS
-	---help---
-	  Enable the collection of statistical data on the slowpath
-	  behavior of paravirtualized queued spinlocks and report
-	  them on debugfs.
-
 source "arch/x86/xen/Kconfig"
 
 config KVM_GUEST
@@ -1330,8 +1317,16 @@ config MICROCODE_AMD
 	  processors will be enabled.
 
 config MICROCODE_OLD_INTERFACE
-	def_bool y
+	bool "Ancient loading interface (DEPRECATED)"
+	default n
 	depends on MICROCODE
+	---help---
+	  DO NOT USE THIS! This is the ancient /dev/cpu/microcode interface
+	  which was used by userspace tools like iucode_tool and microcode.ctl.
+	  It is inadequate because it runs too late to be able to properly
+	  load microcode on a machine and it needs special tools. Instead, you
+	  should've switched to the early loading method with the initrd or
+	  builtin microcode by now: Documentation/x86/microcode.txt
 
 config X86_MSR
 	tristate "/dev/cpu/*/msr - Model-specific register support"
@@ -1606,12 +1601,9 @@ config ARCH_FLATMEM_ENABLE
 	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
-	depends on NUMA && X86_32
-
-config ARCH_DISCONTIGMEM_DEFAULT
-	def_bool y
+	def_bool n
 	depends on NUMA && X86_32
+	depends on BROKEN
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
@@ -1620,8 +1612,7 @@ config ARCH_SPARSEMEM_ENABLE
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
 config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
+	def_bool X86_64 || (NUMA && X86_32)
 
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
@@ -2878,11 +2869,6 @@ config HAVE_ATOMIC_IOMAP
 
 config X86_DEV_DMA_OPS
 	bool
-	depends on X86_64 || STA2X11
-
-config X86_DMA_REMAP
-	bool
-	depends on STA2X11
 
 config HAVE_GENERIC_GUP
 	def_bool y
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a587805c6687..56e748a7679f 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -47,7 +47,7 @@ export REALMODE_CFLAGS
 export BITS
 
 ifdef CONFIG_X86_NEED_RELOCS
-        LDFLAGS_vmlinux := --emit-relocs
+        LDFLAGS_vmlinux := --emit-relocs --discard-none
 endif
 
 #
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 0ef4ad55b29b..ad84239e595e 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -276,7 +276,7 @@ static unsigned long get_acpi_srat_table(void)
 		if (acpi_table) {
 			header = (struct acpi_table_header *)acpi_table;
 
-			if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_SRAT))
+			if (ACPI_COMPARE_NAMESEG(header->signature, ACPI_SIG_SRAT))
 				return acpi_table;
 		}
 		entry += size;
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 9f908112bbb9..2b2481acc661 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -25,18 +25,6 @@ CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_SMP=y
 CONFIG_X86_GENERIC=y
 CONFIG_HPET_TIMER=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 1d3badfda09e..e8829abf063a 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -24,18 +24,6 @@ CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_SMP=y
 CONFIG_CALGARY_IOMMU=y
 CONFIG_NR_CPUS=64
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d309f30cf7af..7b23431be5cb 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -650,6 +650,7 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	pushfl
 
 	/* switch stack */
 	movl	%esp, TASK_threadsp(%eax)
@@ -672,6 +673,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfl
 	popl	%esi
 	popl	%edi
 	popl	%ebx
@@ -766,13 +768,12 @@ END(ret_from_exception)
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
-.Lneed_resched:
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	restore_all_kernel
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz	restore_all_kernel
 	call	preempt_schedule_irq
-	jmp	.Lneed_resched
+	jmp	restore_all_kernel
 END(resume_kernel)
 #endif
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1f0efdb7b629..20e45d9b4e15 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -298,7 +298,7 @@ ENTRY(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset
 #endif
 
 #ifdef CONFIG_RETPOLINE
@@ -430,8 +430,8 @@ END(irq_entries_start)
 	 * it before we actually move ourselves to the IRQ stack.
 	 */
 
-	movq	\old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8)
-	movq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	movq	\old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8)
+	movq	PER_CPU_VAR(hardirq_stack_ptr), %rsp
 
 #ifdef CONFIG_DEBUG_ENTRY
 	/*
@@ -645,10 +645,9 @@ retint_kernel:
 	/* Check if we need preemption */
 	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
-0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
+	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
 	call	preempt_schedule_irq
-	jmp	0b
 1:
 #endif
 	/*
@@ -841,7 +840,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8)
 
 /**
  * idtentry - Generate an IDT entry stub
@@ -879,7 +878,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
@@ -925,13 +924,13 @@ ENTRY(\sym)
 	.endif
 
 	.if \shift_ist != -1
-	subq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	call	\do_sym
 
 	.if \shift_ist != -1
-	addq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	/* these procedures expect "no swapgs" flag in ebx */
@@ -1129,7 +1128,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \
 	hv_stimer0_callback_vector hv_stimer0_vector_handler
 #endif /* CONFIG_HYPERV */
 
-idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET
 idtentry int3			do_int3			has_error_code=0
 idtentry stack_segment		do_stack_segment	has_error_code=1
 
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 5bfe2243a08f..42fe42e82baf 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -116,7 +116,7 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE
 targets += vdsox32.lds $(vobjx32s-y)
 
 $(obj)/%.so: OBJCOPYFLAGS := -S
-$(obj)/%.so: $(obj)/%.so.dbg
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 007b3fe9d727..98c7d12b945c 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -29,12 +29,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
 extern time_t __vdso_time(time_t *t);
 
 #ifdef CONFIG_PARAVIRT_CLOCK
-extern u8 pvclock_page
+extern u8 pvclock_page[PAGE_SIZE]
 	__attribute__((visibility("hidden")));
 #endif
 
 #ifdef CONFIG_HYPERV_TSCPAGE
-extern u8 hvclock_page
+extern u8 hvclock_page[PAGE_SIZE]
 	__attribute__((visibility("hidden")));
 #endif
 
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index fa847a620f40..a20b134de2a8 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -7,7 +7,7 @@
 
 static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 			 void *stripped_addr, size_t stripped_len,
-			 FILE *outfile, const char *name)
+			 FILE *outfile, const char *image_name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */
@@ -93,11 +93,12 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		int k;
 		ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
 			GET_LE(&symtab_hdr->sh_entsize) * i;
-		const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
-			GET_LE(&sym->st_name);
+		const char *sym_name = raw_addr +
+				       GET_LE(&strtab_hdr->sh_offset) +
+				       GET_LE(&sym->st_name);
 
 		for (k = 0; k < NSYMS; k++) {
-			if (!strcmp(name, required_syms[k].name)) {
+			if (!strcmp(sym_name, required_syms[k].name)) {
 				if (syms[k]) {
 					fail("duplicate symbol %s\n",
 					     required_syms[k].name);
@@ -134,7 +135,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	if (syms[sym_vvar_start] % 4096)
 		fail("vvar_begin must be a multiple of 4096\n");
 
-	if (!name) {
+	if (!image_name) {
 		fwrite(stripped_addr, stripped_len, 1, outfile);
 		return;
 	}
@@ -157,7 +158,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "const struct vdso_image %s = {\n", name);
+	fprintf(outfile, "const struct vdso_image %s = {\n", image_name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
 	if (alt_sec) {
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index d45f3fbd232e..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -116,6 +116,110 @@ static __initconst const u64 amd_hw_cache_event_ids
  },
 };
 
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+		[C(RESULT_MISS)]   = 0xc860, /* L2$ access from DC Miss */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches  */
+		[C(RESULT_MISS)]   = 0x0081, /* Instruction cache misses   */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+		[C(RESULT_MISS)]   = 0xf045, /* L2 DTLB misses (PT walks) */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+		[C(RESULT_MISS)]   = 0xff85, /* L1 ITLB misses, L2 misses */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr.      */
+		[C(RESULT_MISS)]   = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+};
+
 /*
  * AMD Performance Monitor K7 and later, up to and including Family 16h:
  */
@@ -865,9 +969,10 @@ __init int amd_pmu_init(void)
 		x86_pmu.amd_nb_constraints = 0;
 	}
 
-	/* Events are common for all AMDs */
-	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
-	       sizeof(hw_cache_event_ids));
+	if (boot_cpu_data.x86 >= 0x17)
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+	else
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 
 	return 0;
 }
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 81911e11a15d..f315425d8468 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event)
 			return -EINVAL;
 	}
 
+	/* sample_regs_user never support XMM registers */
+	if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+		return -EINVAL;
+	/*
+	 * Besides the general purpose registers, XMM registers may
+	 * be collected in PEBS on some platforms, e.g. Icelake
+	 */
+	if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
+		if (x86_pmu.pebs_no_xmm_regs)
+			return -EINVAL;
+
+		if (!event->attr.precise_ip)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
@@ -661,6 +676,10 @@ static inline int is_x86_event(struct perf_event *event)
 	return event->pmu == &pmu;
 }
 
+struct pmu *x86_get_pmu(void)
+{
+	return &pmu;
+}
 /*
  * Event scheduler state:
  *
@@ -849,18 +868,43 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	struct event_constraint *c;
 	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	struct perf_event *e;
-	int i, wmin, wmax, unsched = 0;
+	int n0, i, wmin, wmax, unsched = 0;
 	struct hw_perf_event *hwc;
 
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 
+	/*
+	 * Compute the number of events already present; see x86_pmu_add(),
+	 * validate_group() and x86_pmu_commit_txn(). For the former two
+	 * cpuc->n_events hasn't been updated yet, while for the latter
+	 * cpuc->n_txn contains the number of events added in the current
+	 * transaction.
+	 */
+	n0 = cpuc->n_events;
+	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
+		n0 -= cpuc->n_txn;
+
 	if (x86_pmu.start_scheduling)
 		x86_pmu.start_scheduling(cpuc);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		cpuc->event_constraint[i] = NULL;
-		c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
-		cpuc->event_constraint[i] = c;
+		c = cpuc->event_constraint[i];
+
+		/*
+		 * Previously scheduled events should have a cached constraint,
+		 * while new events should not have one.
+		 */
+		WARN_ON_ONCE((c && i >= n0) || (!c && i < n0));
+
+		/*
+		 * Request constraints for new events; or for those events that
+		 * have a dynamic constraint -- for those the constraint can
+		 * change due to external factors (sibling state, allow_tfa).
+		 */
+		if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) {
+			c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
+			cpuc->event_constraint[i] = c;
+		}
 
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
@@ -925,25 +969,20 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	if (!unsched && assign) {
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
-			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
 			if (x86_pmu.commit_scheduling)
 				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
 	} else {
-		for (i = 0; i < n; i++) {
+		for (i = n0; i < n; i++) {
 			e = cpuc->event_list[i];
-			/*
-			 * do not put_constraint() on comitted events,
-			 * because they are good to go
-			 */
-			if ((e->hw.flags & PERF_X86_EVENT_COMMITTED))
-				continue;
 
 			/*
 			 * release events that failed scheduling
 			 */
 			if (x86_pmu.put_event_constraints)
 				x86_pmu.put_event_constraints(cpuc, e);
+
+			cpuc->event_constraint[i] = NULL;
 		}
 	}
 
@@ -1373,11 +1412,6 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	int i;
 
 	/*
-	 * event is descheduled
-	 */
-	event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
-
-	/*
 	 * If we're called during a txn, we only need to undo x86_pmu.add.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
@@ -1413,6 +1447,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 		cpuc->event_list[i-1] = cpuc->event_list[i];
 		cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
 	}
+	cpuc->event_constraint[i-1] = NULL;
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
@@ -2024,7 +2059,7 @@ static int validate_event(struct perf_event *event)
 	if (IS_ERR(fake_cpuc))
 		return PTR_ERR(fake_cpuc);
 
-	c = x86_pmu.get_event_constraints(fake_cpuc, -1, event);
+	c = x86_pmu.get_event_constraints(fake_cpuc, 0, event);
 
 	if (!c || !c->weight)
 		ret = -EINVAL;
@@ -2072,8 +2107,7 @@ static int validate_group(struct perf_event *event)
 	if (n < 0)
 		goto out;
 
-	fake_cpuc->n_events = n;
-
+	fake_cpuc->n_events = 0;
 	ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
 
 out:
@@ -2348,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event,
 	cyc2ns_read_end();
 }
 
+/*
+ * Determine whether the regs were taken from an irq/exception handler rather
+ * than from perf_arch_fetch_caller_regs().
+ */
+static bool perf_hw_regs(struct pt_regs *regs)
+{
+	return regs->flags & X86_EFLAGS_FIXED;
+}
+
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
@@ -2359,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_callchain_store(entry, regs->ip))
-		return;
+	if (perf_hw_regs(regs)) {
+		if (perf_callchain_store(entry, regs->ip))
+			return;
+		unwind_start(&state, current, regs, NULL);
+	} else {
+		unwind_start(&state, current, NULL, (void *)regs->sp);
+	}
 
-	for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
-	     unwind_next_frame(&state)) {
+	for (; !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
 		if (!addr || perf_callchain_store(entry, addr))
 			return;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f9451566cd9b..ef763f535e3a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct event_constraint intel_icl_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	INTEL_UEVENT_CONSTRAINT(0x1c0, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+	INTEL_EVENT_CONSTRAINT(0x32, 0xf),	/* SW_PREFETCH_ACCESS.* */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff),  /* CYCLE_ACTIVITY.STALLS_TOTAL */
+	INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff),  /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0xf),      /* CYCLE_ACTIVITY.* */
+	INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+	EVENT_EXTRA_END
+};
+
 EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
@@ -1827,6 +1856,45 @@ static __initconst const u64 glp_hw_cache_extra_regs
 	},
 };
 
+#define TNT_LOCAL_DRAM			BIT_ULL(26)
+#define TNT_DEMAND_READ			GLM_DEMAND_DATA_RD
+#define TNT_DEMAND_WRITE		GLM_DEMAND_RFO
+#define TNT_LLC_ACCESS			GLM_ANY_RESPONSE
+#define TNT_SNP_ANY			(SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \
+					 SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM)
+#define TNT_LLC_MISS			(TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM)
+
+static __initconst const u64 tnt_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= TNT_DEMAND_READ|
+						  TNT_LLC_ACCESS,
+			[C(RESULT_MISS)]	= TNT_DEMAND_READ|
+						  TNT_LLC_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= TNT_DEMAND_WRITE|
+						  TNT_LLC_ACCESS,
+			[C(RESULT_MISS)]	= TNT_DEMAND_WRITE|
+						  TNT_LLC_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+};
+
+static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -2015,7 +2083,7 @@ static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int
 	/*
 	 * We're going to use PMC3, make sure TFA is set before we touch it.
 	 */
-	if (cntr == 3 && !cpuc->is_fake)
+	if (cntr == 3)
 		intel_set_tfa(cpuc, true);
 }
 
@@ -2091,15 +2159,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
+
+	/*
+	 * Needs to be called after x86_pmu_disable_event,
+	 * so we don't trigger the event without PEBS bit set.
+	 */
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2145,6 +2217,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	bits <<= (idx * 4);
 	mask = 0xfULL << (idx * 4);
 
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+		bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+		mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+	}
+
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
 	ctrl_val |= bits;
@@ -2688,7 +2765,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if ((event->hw.config & c->cmask) == c->code) {
+			if (constraint_match(c, event->hw.config)) {
 				event->hw.flags |= c->flags;
 				return c;
 			}
@@ -2838,7 +2915,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
 	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int is_excl, i;
+	int is_excl, i, w;
 
 	/*
 	 * validating a group does not require
@@ -2894,36 +2971,40 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
+	w = c->weight;
 	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) {
 			__clear_bit(i, c->idxmsk);
+			w--;
+			continue;
+		}
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) {
 			__clear_bit(i, c->idxmsk);
+			w--;
+			continue;
+		}
 	}
 
 	/*
-	 * recompute actual bit weight for scheduling algorithm
-	 */
-	c->weight = hweight64(c->idxmsk64);
-
-	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (c->weight == 0)
+	if (!w)
 		c = &emptyconstraint;
 
+	c->weight = w;
+
 	return c;
 }
 
@@ -2931,11 +3012,9 @@ static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = NULL;
-	struct event_constraint *c2;
+	struct event_constraint *c1, *c2;
 
-	if (idx >= 0) /* fake does < 0 */
-		c1 = cpuc->event_constraint[idx];
+	c1 = cpuc->event_constraint[idx];
 
 	/*
 	 * first time only
@@ -2943,7 +3022,8 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	 * - dynamic constraint: handled by intel_get_excl_constraints()
 	 */
 	c2 = __intel_get_event_constraints(cpuc, idx, event);
-	if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) {
+	if (c1) {
+	        WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC));
 		bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX);
 		c1->weight = c2->weight;
 		c2 = c1;
@@ -3366,6 +3446,12 @@ static struct event_constraint counter0_constraint =
 static struct event_constraint counter2_constraint =
 			EVENT_CONSTRAINT(0, 0x4, 0);
 
+static struct event_constraint fixed0_constraint =
+			FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
+static struct event_constraint fixed0_counter0_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL);
+
 static struct event_constraint *
 hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -3385,6 +3471,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 }
 
 static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	/*
+	 * Fixed counter 0 has less skid.
+	 * Force instruction:ppp in Fixed counter 0
+	 */
+	if ((event->attr.precise_ip == 3) &&
+	    constraint_match(&fixed0_constraint, event->hw.config))
+		return &fixed0_constraint;
+
+	return hsw_get_event_constraints(cpuc, idx, event);
+}
+
+static struct event_constraint *
 glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
 {
@@ -3399,6 +3500,29 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return c;
 }
 
+static struct event_constraint *
+tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	/*
+	 * :ppp means to do reduced skid PEBS,
+	 * which is available on PMC0 and fixed counter 0.
+	 */
+	if (event->attr.precise_ip == 3) {
+		/* Force instruction:ppp on PMC0 and Fixed counter 0 */
+		if (constraint_match(&fixed0_constraint, event->hw.config))
+			return &fixed0_counter0_constraint;
+
+		return &counter0_constraint;
+	}
+
+	c = intel_get_event_constraints(cpuc, idx, event);
+
+	return c;
+}
+
 static bool allow_tsx_force_abort = true;
 
 static struct event_constraint *
@@ -3410,7 +3534,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	/*
 	 * Without TFA we must not use PMC3.
 	 */
-	if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) {
+	if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
 		c = dyn_constraint(cpuc, c, idx);
 		c->idxmsk64 &= ~(1ULL << 3);
 		c->weight--;
@@ -3507,6 +3631,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 
 int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 {
+	cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
@@ -4114,6 +4240,42 @@ static struct attribute *hsw_tsx_events_attrs[] = {
 	NULL
 };
 
+EVENT_ATTR_STR(tx-capacity-read,  tx_capacity_read,  "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read,  el_capacity_read,  "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_hsw),
+	NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+	EVENT_PTR(tx_start),
+	EVENT_PTR(tx_abort),
+	EVENT_PTR(tx_commit),
+	EVENT_PTR(tx_capacity_read),
+	EVENT_PTR(tx_capacity_write),
+	EVENT_PTR(tx_conflict),
+	EVENT_PTR(el_start),
+	EVENT_PTR(el_abort),
+	EVENT_PTR(el_commit),
+	EVENT_PTR(el_capacity_read),
+	EVENT_PTR(el_capacity_write),
+	EVENT_PTR(el_conflict),
+	EVENT_PTR(cycles_t),
+	EVENT_PTR(cycles_ct),
+	NULL,
+};
+
+static __init struct attribute **get_icl_events_attrs(void)
+{
+	return boot_cpu_has(X86_FEATURE_RTM) ?
+		merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
+		icl_events_attrs;
+}
+
 static ssize_t freeze_on_smi_show(struct device *cdev,
 				  struct device_attribute *attr,
 				  char *buf)
@@ -4153,6 +4315,50 @@ done:
 	return count;
 }
 
+static void update_tfa_sched(void *ignored)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/*
+	 * check if PMC3 is used
+	 * and if so force schedule out for all event types all contexts
+	 */
+	if (test_bit(3, cpuc->active_mask))
+		perf_pmu_resched(x86_get_pmu());
+}
+
+static ssize_t show_sysctl_tfa(struct device *cdev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	return snprintf(buf, 40, "%d\n", allow_tsx_force_abort);
+}
+
+static ssize_t set_sysctl_tfa(struct device *cdev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	bool val;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	/* no change */
+	if (val == allow_tsx_force_abort)
+		return count;
+
+	allow_tsx_force_abort = val;
+
+	get_online_cpus();
+	on_each_cpu(update_tfa_sched, NULL, 1);
+	put_online_cpus();
+
+	return count;
+}
+
+
 static DEVICE_ATTR_RW(freeze_on_smi);
 
 static ssize_t branches_show(struct device *cdev,
@@ -4185,7 +4391,9 @@ static struct attribute *intel_pmu_caps_attrs[] = {
        NULL
 };
 
-static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort);
+static DEVICE_ATTR(allow_tsx_force_abort, 0644,
+		   show_sysctl_tfa,
+		   set_sysctl_tfa);
 
 static struct attribute *intel_pmu_attrs[] = {
 	&dev_attr_freeze_on_smi.attr,
@@ -4446,6 +4654,32 @@ __init int intel_pmu_init(void)
 		name = "goldmont_plus";
 		break;
 
+	case INTEL_FAM6_ATOM_TREMONT_X:
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.extra_regs = intel_tnt_extra_regs;
+		/*
+		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+		 * for precise cycles.
+		 */
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.get_event_constraints = tnt_get_event_constraints;
+		extra_attr = slm_format_attr;
+		pr_cont("Tremont events, ");
+		name = "Tremont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
@@ -4694,13 +4928,41 @@ __init int intel_pmu_init(void)
 			x86_pmu.get_event_constraints = tfa_get_event_constraints;
 			x86_pmu.enable_all = intel_tfa_pmu_enable_all;
 			x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
-			intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr;
+			intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
 		}
 
 		pr_cont("Skylake events, ");
 		name = "skylake";
 		break;
 
+	case INTEL_FAM6_ICELAKE_MOBILE:
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_icl_event_constraints;
+		x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_icl_extra_regs;
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = icl_get_event_constraints;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			hsw_format_attr : nhm_format_attr;
+		extra_attr = merge_attr(extra_attr, skl_format_attr);
+		x86_pmu.cpu_events = get_icl_events_attrs();
+		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
+		x86_pmu.lbr_pt_coexist = true;
+		intel_pmu_pebs_data_source_skl(false);
+		pr_cont("Icelake events, ");
+		name = "icelake";
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index d41de9af7a39..6072f92cb8ea 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 10c99ce1fead..7a9f5dac5abe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL),	/* SLOTS */
+
+	INTEL_PLD_CONSTRAINT(0x1cd, 0xff),			/* MEM_TRANS_RETIRED.LOAD_LATENCY */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),	/* MEM_INST_RETIRED.LOAD */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),	/* MEM_INST_RETIRED.STORE */
+
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),		/* MEM_INST_RETIRED.* */
+
+	/*
+	 * Everything else is handled by PMU_FL_PEBS_ALL, because we
+	 * need the full constraints from the main table.
+	 */
+
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -858,7 +878,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 	if (x86_pmu.pebs_constraints) {
 		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
-			if ((event->hw.config & c->cmask) == c->code) {
+			if (constraint_match(c, event->hw.config)) {
 				event->hw.flags |= c->flags;
 				return c;
 			}
@@ -906,17 +926,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			reserved * x86_pmu.pebs_record_size;
+			reserved * cpuc->pebs_record_size;
 	} else {
-		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+		threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
 	}
 
 	ds->pebs_interrupt_threshold = threshold;
 }
 
+static void adaptive_pebs_record_size_update(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+	int sz = sizeof(struct pebs_basic);
+
+	if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+		sz += sizeof(struct pebs_meminfo);
+	if (pebs_data_cfg & PEBS_DATACFG_GP)
+		sz += sizeof(struct pebs_gprs);
+	if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+		sz += sizeof(struct pebs_xmm);
+	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+		sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+	cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
+				PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+				PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u64 sample_type = attr->sample_type;
+	u64 pebs_data_cfg = 0;
+	bool gprs, tsx_weight;
+
+	if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+	    attr->precise_ip > 1)
+		return pebs_data_cfg;
+
+	if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+		pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+	/*
+	 * We need GPRs when:
+	 * + user requested them
+	 * + precise_ip < 2 for the non event IP
+	 * + For RTM TSX weight we need GPRs for the abort code.
+	 */
+	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+	       (attr->sample_regs_intr & PEBS_GP_REGS);
+
+	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+		      x86_pmu.rtm_abort_event);
+
+	if (gprs || (attr->precise_ip < 2) || tsx_weight)
+		pebs_data_cfg |= PEBS_DATACFG_GP;
+
+	if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+	    (attr->sample_regs_intr & PEBS_XMM_REGS))
+		pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		/*
+		 * For now always log all LBRs. Could configure this
+		 * later.
+		 */
+		pebs_data_cfg |= PEBS_DATACFG_LBRS |
+			((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+	}
+
+	return pebs_data_cfg;
+}
+
 static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+		  struct perf_event *event, bool add)
 {
+	struct pmu *pmu = event->ctx->pmu;
 	/*
 	 * Make sure we get updated with the first PEBS
 	 * event. It will trigger also during removal, but
@@ -933,6 +1023,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
 		update = true;
 	}
 
+	/*
+	 * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+	 * iterating all remaining PEBS events to reconstruct the config.
+	 */
+	if (x86_pmu.intel_cap.pebs_baseline && add) {
+		u64 pebs_data_cfg;
+
+		/* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+		if (cpuc->n_pebs == 1) {
+			cpuc->pebs_data_cfg = 0;
+			cpuc->pebs_record_size = sizeof(struct pebs_basic);
+		}
+
+		pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+		/* Update pebs_record_size if new event requires more data. */
+		if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+			cpuc->pebs_data_cfg |= pebs_data_cfg;
+			adaptive_pebs_record_size_update();
+			update = true;
+		}
+	}
+
 	if (update)
 		pebs_update_threshold(cpuc);
 }
@@ -947,7 +1060,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
 
-	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+	pebs_update_state(needed_cb, cpuc, event, true);
 }
 
 void intel_pmu_pebs_enable(struct perf_event *event)
@@ -960,11 +1073,19 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
-	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
 
+	if (x86_pmu.intel_cap.pebs_baseline) {
+		hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+		if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+			wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+			cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+		}
+	}
+
 	/*
 	 * Use auto-reload if possible to save a MSR write in the PMI.
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -991,7 +1112,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
 
-	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+	pebs_update_state(needed_cb, cpuc, event, false);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -1004,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
-	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+	    (x86_pmu.version < 5))
 		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
@@ -1125,34 +1247,57 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	return 0;
 }
 
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
 {
-	if (pebs->tsx_tuning) {
-		union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+	if (tsx_tuning) {
+		union hsw_tsx_tuning tsx = { .value = tsx_tuning };
 		return tsx.cycles_last_block;
 	}
 	return 0;
 }
 
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
 {
-	u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+	u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
 
 	/* For RTM XABORTs also log the abort code from AX */
-	if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
-		txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+	if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+		txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
 	return txn;
 }
 
-static void setup_pebs_sample_data(struct perf_event *event,
-				   struct pt_regs *iregs, void *__pebs,
-				   struct perf_sample_data *data,
-				   struct pt_regs *regs)
+static inline u64 get_pebs_status(void *n)
 {
+	if (x86_pmu.intel_cap.pebs_format < 4)
+		return ((struct pebs_record_nhm *)n)->status;
+	return ((struct pebs_basic *)n)->applicable_counters;
+}
+
 #define PERF_X86_EVENT_PEBS_HSW_PREC \
 		(PERF_X86_EVENT_PEBS_ST_HSW | \
 		 PERF_X86_EVENT_PEBS_LD_HSW | \
 		 PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+	u64 val = PERF_MEM_NA;
+	int fl = event->hw.flags;
+	bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+	if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+		val = load_latency_data(aux);
+	else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+		val = precise_datala_hsw(event, aux);
+	else if (fst)
+		val = precise_store_data(aux);
+	return val;
+}
+
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
 	/*
 	 * We cast to the biggest pebs_record but are careful not to
 	 * unconditionally access the 'extra' entries.
@@ -1160,17 +1305,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_skl *pebs = __pebs;
 	u64 sample_type;
-	int fll, fst, dsrc;
-	int fl = event->hw.flags;
+	int fll;
 
 	if (pebs == NULL)
 		return;
 
 	sample_type = event->attr.sample_type;
-	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
-	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
-	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
 
 	perf_sample_data_init(data, 0, event->hw.last_period);
 
@@ -1185,16 +1326,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	/*
 	 * data.data_src encodes the data source
 	 */
-	if (dsrc) {
-		u64 val = PERF_MEM_NA;
-		if (fll)
-			val = load_latency_data(pebs->dse);
-		else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
-			val = precise_datala_hsw(event, pebs->dse);
-		else if (fst)
-			val = precise_store_data(pebs->dse);
-		data->data_src.val = val;
-	}
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		data->data_src.val = get_data_src(event, pebs->dse);
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the
@@ -1281,10 +1414,11 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
 		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data->weight = intel_hsw_weight(pebs);
+			data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-			data->txn = intel_hsw_transaction(pebs);
+			data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+							      pebs->ax);
 	}
 
 	/*
@@ -1301,6 +1435,140 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		data->br_stack = &cpuc->lbr_stack;
 }
 
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+				    struct pebs_gprs *gprs)
+{
+	regs->ax = gprs->ax;
+	regs->bx = gprs->bx;
+	regs->cx = gprs->cx;
+	regs->dx = gprs->dx;
+	regs->si = gprs->si;
+	regs->di = gprs->di;
+	regs->bp = gprs->bp;
+	regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+	regs->r8 = gprs->r8;
+	regs->r9 = gprs->r9;
+	regs->r10 = gprs->r10;
+	regs->r11 = gprs->r11;
+	regs->r12 = gprs->r12;
+	regs->r13 = gprs->r13;
+	regs->r14 = gprs->r14;
+	regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+					    struct pt_regs *iregs, void *__pebs,
+					    struct perf_sample_data *data,
+					    struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct pebs_basic *basic = __pebs;
+	void *next_record = basic + 1;
+	u64 sample_type;
+	u64 format_size;
+	struct pebs_meminfo *meminfo = NULL;
+	struct pebs_gprs *gprs = NULL;
+	struct x86_perf_regs *perf_regs;
+
+	if (basic == NULL)
+		return;
+
+	perf_regs = container_of(regs, struct x86_perf_regs, regs);
+	perf_regs->xmm_regs = NULL;
+
+	sample_type = event->attr.sample_type;
+	format_size = basic->format_size;
+	perf_sample_data_init(data, 0, event->hw.last_period);
+	data->period = event->hw.last_period;
+
+	if (event->attr.use_clockid == 0)
+		data->time = native_sched_clock_from_tsc(basic->tsc);
+
+	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happened between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
+	*regs = *iregs;
+	/* The ip in basic is EventingIP */
+	set_linear_ip(regs, basic->ip);
+	regs->flags = PERF_EFLAGS_EXACT;
+
+	/*
+	 * The record for MEMINFO is in front of GP
+	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+	 * Save the pointer here but process later.
+	 */
+	if (format_size & PEBS_DATACFG_MEMINFO) {
+		meminfo = next_record;
+		next_record = meminfo + 1;
+	}
+
+	if (format_size & PEBS_DATACFG_GP) {
+		gprs = next_record;
+		next_record = gprs + 1;
+
+		if (event->attr.precise_ip < 2) {
+			set_linear_ip(regs, gprs->ip);
+			regs->flags &= ~PERF_EFLAGS_EXACT;
+		}
+
+		if (sample_type & PERF_SAMPLE_REGS_INTR)
+			adaptive_pebs_save_regs(regs, gprs);
+	}
+
+	if (format_size & PEBS_DATACFG_MEMINFO) {
+		if (sample_type & PERF_SAMPLE_WEIGHT)
+			data->weight = meminfo->latency ?:
+				intel_get_tsx_weight(meminfo->tsx_tuning);
+
+		if (sample_type & PERF_SAMPLE_DATA_SRC)
+			data->data_src.val = get_data_src(event, meminfo->aux);
+
+		if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+			data->addr = meminfo->address;
+
+		if (sample_type & PERF_SAMPLE_TRANSACTION)
+			data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+							  gprs ? gprs->ax : 0);
+	}
+
+	if (format_size & PEBS_DATACFG_XMMS) {
+		struct pebs_xmm *xmm = next_record;
+
+		next_record = xmm + 1;
+		perf_regs->xmm_regs = xmm->xmm;
+	}
+
+	if (format_size & PEBS_DATACFG_LBRS) {
+		struct pebs_lbr *lbr = next_record;
+		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+					& 0xff) + 1;
+		next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+		if (has_branch_stack(event)) {
+			intel_pmu_store_pebs_lbrs(lbr);
+			data->br_stack = &cpuc->lbr_stack;
+		}
+	}
+
+	WARN_ONCE(next_record != __pebs + (format_size >> 48),
+			"PEBS record size %llu, expected %llu, config %llx\n",
+			format_size >> 48,
+			(u64)(next_record - __pebs),
+			basic->format_size);
+}
+
 static inline void *
 get_next_pebs_record_by_bit(void *base, void *top, int bit)
 {
@@ -1318,19 +1586,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 	if (base == NULL)
 		return NULL;
 
-	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
-		struct pebs_record_nhm *p = at;
+	for (at = base; at < top; at += cpuc->pebs_record_size) {
+		unsigned long status = get_pebs_status(at);
 
-		if (test_bit(bit, (unsigned long *)&p->status)) {
+		if (test_bit(bit, (unsigned long *)&status)) {
 			/* PEBS v3 has accurate status bits */
 			if (x86_pmu.intel_cap.pebs_format >= 3)
 				return at;
 
-			if (p->status == (1 << bit))
+			if (status == (1 << bit))
 				return at;
 
 			/* clear non-PEBS bit and re-check */
-			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status = status & cpuc->pebs_enabled;
 			pebs_status &= PEBS_COUNTER_MASK;
 			if (pebs_status == (1 << bit))
 				return at;
@@ -1410,11 +1678,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 static void __intel_pmu_pebs_event(struct perf_event *event,
 				   struct pt_regs *iregs,
 				   void *base, void *top,
-				   int bit, int count)
+				   int bit, int count,
+				   void (*setup_sample)(struct perf_event *,
+						struct pt_regs *,
+						void *,
+						struct perf_sample_data *,
+						struct pt_regs *))
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_sample_data data;
-	struct pt_regs regs;
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1429,20 +1704,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		return;
 
 	while (count > 1) {
-		setup_pebs_sample_data(event, iregs, at, &data, &regs);
-		perf_event_output(event, &data, &regs);
-		at += x86_pmu.pebs_record_size;
+		setup_sample(event, iregs, at, &data, regs);
+		perf_event_output(event, &data, regs);
+		at += cpuc->pebs_record_size;
 		at = get_next_pebs_record_by_bit(at, top, bit);
 		count--;
 	}
 
-	setup_pebs_sample_data(event, iregs, at, &data, &regs);
+	setup_sample(event, iregs, at, &data, regs);
 
 	/*
 	 * All but the last records are processed.
 	 * The last one is left to be able to call the overflow handler.
 	 */
-	if (perf_event_overflow(event, &data, &regs)) {
+	if (perf_event_overflow(event, &data, regs)) {
 		x86_pmu_stop(event, 0);
 		return;
 	}
@@ -1483,7 +1758,27 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+	__intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+			       setup_pebs_fixed_sample_data);
+}
+
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+{
+	struct perf_event *event;
+	int bit;
+
+	/*
+	 * The drain_pebs() could be called twice in a short period
+	 * for auto-reload event in pmu::read(). There are no
+	 * overflows have happened in between.
+	 * It needs to call intel_pmu_save_and_restart_reload() to
+	 * update the event->count for this case.
+	 */
+	for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+		event = cpuc->events[bit];
+		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+			intel_pmu_save_and_restart_reload(event, 0);
+	}
 }
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
@@ -1513,19 +1808,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	}
 
 	if (unlikely(base >= top)) {
-		/*
-		 * The drain_pebs() could be called twice in a short period
-		 * for auto-reload event in pmu::read(). There are no
-		 * overflows have happened in between.
-		 * It needs to call intel_pmu_save_and_restart_reload() to
-		 * update the event->count for this case.
-		 */
-		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 size) {
-			event = cpuc->events[bit];
-			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
-				intel_pmu_save_and_restart_reload(event, 0);
-		}
+		intel_pmu_pebs_event_update_no_drain(cpuc, size);
 		return;
 	}
 
@@ -1538,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
-			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 size)
+			for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
 				counts[bit]++;
 
 			continue;
@@ -1578,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * If collision happened, the record will be dropped.
 		 */
 		if (p->status != (1ULL << bit)) {
-			for_each_set_bit(i, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+			for_each_set_bit(i, (unsigned long *)&pebs_status, size)
 				error[i]++;
 			continue;
 		}
@@ -1587,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < size; bit++) {
+	for_each_set_bit(bit, (unsigned long *)&mask, size) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 
@@ -1608,11 +1889,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 		if (counts[bit]) {
 			__intel_pmu_pebs_event(event, iregs, base,
-					       top, bit, counts[bit]);
+					       top, bit, counts[bit],
+					       setup_pebs_fixed_sample_data);
 		}
 	}
 }
 
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct perf_event *event;
+	void *base, *at, *top;
+	int bit, size;
+	u64 mask;
+
+	if (!x86_pmu.pebs_active)
+		return;
+
+	base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+	       (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+	size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+	if (unlikely(base >= top)) {
+		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		return;
+	}
+
+	for (at = base; at < top; at += cpuc->pebs_record_size) {
+		u64 pebs_status;
+
+		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+		pebs_status &= mask;
+
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+			counts[bit]++;
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&mask, size) {
+		if (counts[bit] == 0)
+			continue;
+
+		event = cpuc->events[bit];
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		if (WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
+
+		__intel_pmu_pebs_event(event, iregs, base,
+				       top, bit, counts[bit],
+				       setup_pebs_adaptive_sample_data);
+	}
+}
+
 /*
  * BTS, PEBS probe and setup
  */
@@ -1628,12 +1964,18 @@ void __init intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
-	if (x86_pmu.version <= 4)
+	if (x86_pmu.version <= 4) {
 		x86_pmu.pebs_no_isolation = 1;
+		x86_pmu.pebs_no_xmm_regs = 1;
+	}
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
+		char *pebs_qual = "";
 		int format = x86_pmu.intel_cap.pebs_format;
 
+		if (format < 4)
+			x86_pmu.intel_cap.pebs_baseline = 0;
+
 		switch (format) {
 		case 0:
 			pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -1669,6 +2011,29 @@ void __init intel_ds_init(void)
 			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
+		case 4:
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+			x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+			if (x86_pmu.intel_cap.pebs_baseline) {
+				x86_pmu.large_pebs_flags |=
+					PERF_SAMPLE_BRANCH_STACK |
+					PERF_SAMPLE_TIME;
+				x86_pmu.flags |= PMU_FL_PEBS_ALL;
+				pebs_qual = "-baseline";
+			} else {
+				/* Only basic record supported */
+				x86_pmu.pebs_no_xmm_regs = 1;
+				x86_pmu.large_pebs_flags &=
+					~(PERF_SAMPLE_ADDR |
+					  PERF_SAMPLE_TIME |
+					  PERF_SAMPLE_DATA_SRC |
+					  PERF_SAMPLE_TRANSACTION |
+					  PERF_SAMPLE_REGS_USER |
+					  PERF_SAMPLE_REGS_INTR);
+			}
+			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+			break;
+
 		default:
 			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 580c1b91c454..6f814a27416b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	 * be 'new'. Conversely, a new event can get installed through the
 	 * context switch path for the first time.
 	 */
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+		cpuc->lbr_pebs_users++;
 	perf_sched_cb_inc(event->ctx->pmu);
 	if (!cpuc->lbr_users++ && !event->total_time_running)
 		intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event)
 		task_ctx->lbr_callstack_users--;
 	}
 
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+		cpuc->lbr_pebs_users--;
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
+	WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
 	perf_sched_cb_dec(event->ctx->pmu);
 }
 
@@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (!cpuc->lbr_users)
+	/*
+	 * Don't read when all LBRs users are using adaptive PEBS.
+	 *
+	 * This could be smarter and actually check the event,
+	 * but this simple approach seems to work for now.
+	 */
+	if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
 		return;
 
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
@@ -1080,6 +1091,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	}
 }
 
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int i;
+
+	cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		u64 info = lbr->lbr[i].info;
+		struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+		e->from		= lbr->lbr[i].from;
+		e->to		= lbr->lbr[i].to;
+		e->mispred	= !!(info & LBR_INFO_MISPRED);
+		e->predicted	= !(info & LBR_INFO_MISPRED);
+		e->in_tx	= !!(info & LBR_INFO_IN_TX);
+		e->abort	= !!(info & LBR_INFO_ABORT);
+		e->cycles	= info & LBR_INFO_CYCLES;
+		e->reserved	= 0;
+	}
+	intel_pmu_lbr_filter(cpuc);
+}
+
 /*
  * Map interface branch filters onto LBR filters
  */
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fb3a2f13fc70..339d7628080c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1525,8 +1525,7 @@ static __init int pt_init(void)
 	}
 
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
-		pt_pmu.pmu.capabilities =
-			PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
 
 	pt_pmu.pmu.capabilities	|= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
 	pt_pmu.pmu.attr_groups		 = pt_attr_groups;
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 94dc564146ca..37ebf6fc5415 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE,  skl_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9fe64c01a2e5..fc40a1473058 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
 	.pci_init = skx_uncore_pci_init,
 };
 
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+	.cpu_init = icl_uncore_cpu_init,
+	.pci_init = skl_uncore_pci_init,
+};
+
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
@@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,      skx_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 853a49a8ccf6..79eb2e21e4f0 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -512,6 +512,7 @@ int skl_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
 /* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 13493f43b247..f8431819b3e1 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -34,6 +34,8 @@
 #define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC	0x3e33
 #define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC	0x3eca
 #define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC	0x3e32
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC		0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC		0x8a12
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -93,6 +95,12 @@
 #define SKL_UNC_PERF_GLOBAL_CTL			0xe01
 #define SKL_UNC_GLOBAL_CTL_CORE_ALL		((1 << 5) - 1)
 
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG			0x396
+#define ICL_UNC_NUM_CBO_MASK			0xf
+#define ICL_UNC_CBO_0_PER_CTR0			0x702
+#define ICL_UNC_CBO_MSR_OFFSET			0x8
+
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void)
 	snb_uncore_arb.ops = &skl_uncore_msr_ops;
 }
 
+static struct intel_uncore_type icl_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 4,
+	.perf_ctr_bits	= 44,
+	.perf_ctr	= ICL_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= ICL_UNC_CBO_MSR_OFFSET,
+	.ops		= &skl_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+	{ /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+	.name = "format",
+	.attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+	.name		= "clock",
+	.num_counters	= 1,
+	.num_boxes	= 1,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_CTL_EV_SEL_MASK,
+	.format_group	= &icl_uncore_clock_format_group,
+	.ops		= &skl_uncore_msr_ops,
+	.event_descs	= icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+	&icl_uncore_cbox,
+	&snb_uncore_arb,
+	&icl_uncore_clockbox,
+	NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+	u64 num_boxes;
+
+	rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+	return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = icl_msr_uncores;
+	icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+	snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
 enum {
 	SNB_PCI_UNCORE_IMC,
 };
@@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 	{ /* end: all zeroes */ },
 };
 
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
 static struct pci_driver snb_uncore_pci_driver = {
 	.name		= "snb_uncore",
 	.id_table	= snb_uncore_pci_ids,
@@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = {
 	.id_table	= skl_uncore_pci_ids,
 };
 
+static struct pci_driver icl_uncore_pci_driver = {
+	.name		= "icl_uncore",
+	.id_table	= icl_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Server */
 	IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Server */
 	IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Server */
+	IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
+	IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
 	{  /* end marker */ }
 };
 
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index a878e6286e4a..f3f4c2263501 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,6 +89,7 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
+	case INTEL_FAM6_ICELAKE_MOBILE:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 1e98a42b560a..07fc84bb85c1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,28 +49,33 @@ struct event_constraint {
 		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 		u64		idxmsk64;
 	};
-	u64	code;
-	u64	cmask;
-	int	weight;
-	int	overlap;
-	int	flags;
+	u64		code;
+	u64		cmask;
+	int		weight;
+	int		overlap;
+	int		flags;
+	unsigned int	size;
 };
+
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+	return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
+
 /*
  * struct hw_perf_event.flags flags
  */
 #define PERF_X86_EVENT_PEBS_LDLAT	0x0001 /* ld+ldlat data address sampling */
 #define PERF_X86_EVENT_PEBS_ST		0x0002 /* st data address sampling */
 #define PERF_X86_EVENT_PEBS_ST_HSW	0x0004 /* haswell style datala, store */
-#define PERF_X86_EVENT_COMMITTED	0x0008 /* event passed commit_txn */
-#define PERF_X86_EVENT_PEBS_LD_HSW	0x0010 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW	0x0020 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL		0x0040 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
-#define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
-#define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
-#define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
-
+#define PERF_X86_EVENT_PEBS_LD_HSW	0x0008 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW	0x0010 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_EXCL		0x0020 /* HT exclusivity on counter */
+#define PERF_X86_EVENT_DYNAMIC		0x0040 /* dynamic alloc'd constraint */
+#define PERF_X86_EVENT_RDPMC_ALLOWED	0x0080 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -116,6 +121,24 @@ struct amd_nb {
 	 (1ULL << PERF_REG_X86_R14)   | \
 	 (1ULL << PERF_REG_X86_R15))
 
+#define PEBS_XMM_REGS                   \
+	((1ULL << PERF_REG_X86_XMM0)  | \
+	 (1ULL << PERF_REG_X86_XMM1)  | \
+	 (1ULL << PERF_REG_X86_XMM2)  | \
+	 (1ULL << PERF_REG_X86_XMM3)  | \
+	 (1ULL << PERF_REG_X86_XMM4)  | \
+	 (1ULL << PERF_REG_X86_XMM5)  | \
+	 (1ULL << PERF_REG_X86_XMM6)  | \
+	 (1ULL << PERF_REG_X86_XMM7)  | \
+	 (1ULL << PERF_REG_X86_XMM8)  | \
+	 (1ULL << PERF_REG_X86_XMM9)  | \
+	 (1ULL << PERF_REG_X86_XMM10) | \
+	 (1ULL << PERF_REG_X86_XMM11) | \
+	 (1ULL << PERF_REG_X86_XMM12) | \
+	 (1ULL << PERF_REG_X86_XMM13) | \
+	 (1ULL << PERF_REG_X86_XMM14) | \
+	 (1ULL << PERF_REG_X86_XMM15))
+
 /*
  * Per register state.
  */
@@ -207,10 +230,16 @@ struct cpu_hw_events {
 	int			n_pebs;
 	int			n_large_pebs;
 
+	/* Current super set of events hardware configuration */
+	u64			pebs_data_cfg;
+	u64			active_pebs_data_cfg;
+	int			pebs_record_size;
+
 	/*
 	 * Intel LBR bits
 	 */
 	int				lbr_users;
+	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
@@ -257,18 +286,29 @@ struct cpu_hw_events {
 	void				*kfree_on_online[X86_PERF_KFREE_MAX];
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) {	\
 	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
+	.size = (e) - (c),		\
 	.cmask = (m),			\
 	.weight = (w),			\
 	.overlap = (o),			\
 	.flags = f,			\
 }
 
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+	__EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
 #define EVENT_CONSTRAINT(c, n, m)	\
 	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
+/*
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+	__EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
 #define INTEL_EXCLEVT_CONSTRAINT(c, n)	\
 	__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
 			   0, PERF_X86_EVENT_EXCL)
@@ -304,6 +344,12 @@ struct cpu_hw_events {
 	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
 
 /*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n)			\
+	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
+/*
  * Constraint on the Event code + UMask + fixed-mask
  *
  * filter mask to validate fixed counter events.
@@ -350,6 +396,9 @@ struct cpu_hw_events {
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
 
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n)			\
+	EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
 /* Check only flags, but allow all event/umask */
 #define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\
 	EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -366,6 +415,11 @@ struct cpu_hw_events {
 			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
 
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+	__EVENT_CONSTRAINT_RANGE(code, end, n,				\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
 #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
 	__EVENT_CONSTRAINT(code, n,			\
 			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
@@ -473,6 +527,7 @@ union perf_capabilities {
 		 * values > 32bit.
 		 */
 		u64	full_width_write:1;
+		u64     pebs_baseline:1;
 	};
 	u64	capabilities;
 };
@@ -613,14 +668,16 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1;
+			pebs_no_isolation	:1,
+			pebs_no_xmm_regs	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
+	int		max_pebs_events;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
-	int 		max_pebs_events;
 	unsigned long	large_pebs_flags;
+	u64		rtm_abort_event;
 
 	/*
 	 * Intel LBR
@@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = {		\
 	.event_str_ht	= ht,						\
 }
 
+struct pmu *x86_get_pmu(void);
 extern struct x86_pmu x86_pmu __read_mostly;
 
 static inline bool x86_pmu_has_lbr_callstack(void)
@@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[];
 
 extern struct event_constraint intel_skl_pebs_event_constraints[];
 
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_add(struct perf_event *event);
@@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
 
 void intel_pmu_auto_reload_read(struct perf_event *event);
 
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 8eb6fbee8e13..5c056b8aebef 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -86,6 +86,11 @@ static void hv_apic_write(u32 reg, u32 val)
 
 static void hv_apic_eoi_write(u32 reg, u32 val)
 {
+	struct hv_vp_assist_page *hvp = hv_vp_assist_page[smp_processor_id()];
+
+	if (hvp && (xchg(&hvp->apic_assist, 0) & 0x1))
+		return;
+
 	wrmsr(HV_X64_MSR_EOI, val, 0);
 }
 
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index a861b0456b1a..07f21a06392f 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -56,7 +56,7 @@ static void hv_qlock_wait(u8 *byte, u8 val)
 /*
  * Hyper-V does not support this so far.
  */
-bool hv_vcpu_is_preempted(int vcpu)
+__visible bool hv_vcpu_is_preempted(int vcpu)
 {
 	return false;
 }
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 321fe5f5d0e9..4d5fcd47ab75 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -61,9 +61,8 @@
 } while (0)
 
 #define RELOAD_SEG(seg)		{		\
-	unsigned int pre = GET_SEG(seg);	\
+	unsigned int pre = (seg) | 3;		\
 	unsigned int cur = get_user_seg(seg);	\
-	pre |= 3;				\
 	if (pre != cur)				\
 		set_user_seg(seg, pre);		\
 }
@@ -72,6 +71,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 				   struct sigcontext_32 __user *sc)
 {
 	unsigned int tmpflags, err = 0;
+	u16 gs, fs, es, ds;
 	void __user *buf;
 	u32 tmp;
 
@@ -79,16 +79,10 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
-		/*
-		 * Reload fs and gs if they have changed in the signal
-		 * handler.  This does not handle long fs/gs base changes in
-		 * the handler, but does not clobber them at least in the
-		 * normal case.
-		 */
-		RELOAD_SEG(gs);
-		RELOAD_SEG(fs);
-		RELOAD_SEG(ds);
-		RELOAD_SEG(es);
+		gs = GET_SEG(gs);
+		fs = GET_SEG(fs);
+		ds = GET_SEG(ds);
+		es = GET_SEG(es);
 
 		COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 		COPY(dx); COPY(cx); COPY(ip); COPY(ax);
@@ -106,6 +100,17 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 		buf = compat_ptr(tmp);
 	} get_user_catch(err);
 
+	/*
+	 * Reload fs and gs if they have changed in the signal
+	 * handler.  This does not handle long fs/gs base changes in
+	 * the handler, but does not clobber them at least in the
+	 * normal case.
+	 */
+	RELOAD_SEG(gs);
+	RELOAD_SEG(fs);
+	RELOAD_SEG(ds);
+	RELOAD_SEG(es);
+
 	err |= fpu__restore_sig(buf, 1);
 
 	force_iret();
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index a0ab9ab61c75..eebd05942e6c 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -11,3 +11,4 @@ generic-y += early_ioremap.h
 generic-y += export.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..464034db299f 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -20,6 +20,17 @@
 #endif
 
 /*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.ignore_alts
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
  * Issue one struct alt_instr descriptor entry (need to put it into
  * the section .altinstructions, see below). This entry contains
  * enough information for the alternatives patching code to patch an
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4c74073a19cc..094fbc9c0b1c 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -45,6 +45,16 @@
 #define LOCK_PREFIX ""
 #endif
 
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+#define ANNOTATE_IGNORE_ALTERNATIVE				\
+	"999:\n\t"						\
+	".pushsection .discard.ignore_alts\n\t"			\
+	".long 999b - .\n\t"					\
+	".popsection\n\t"
+
 struct alt_instr {
 	s32 instr_offset;	/* original instruction */
 	s32 repl_offset;	/* offset to replacement instruction */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 6467757bb39f..3ff577c0b102 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -148,30 +148,6 @@
 	_ASM_PTR (entry);					\
 	.popsection
 
-.macro ALIGN_DESTINATION
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE_UA(100b, 103b)
-	_ASM_EXTABLE_UA(101b, 103b)
-	.endm
-
 #else
 # define _EXPAND_EXTABLE_HANDLE(x) #x
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 29c706415443..cff3f3f3bfe0 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -7,6 +7,64 @@
 #include <asm/processor.h>
 #include <asm/intel_ds.h>
 
+#ifdef CONFIG_X86_64
+
+/* Macro to enforce the same ordering and stack sizes */
+#define ESTACKS_MEMBERS(guardsize, db2_holesize)\
+	char	DF_stack_guard[guardsize];	\
+	char	DF_stack[EXCEPTION_STKSZ];	\
+	char	NMI_stack_guard[guardsize];	\
+	char	NMI_stack[EXCEPTION_STKSZ];	\
+	char	DB2_stack_guard[guardsize];	\
+	char	DB2_stack[db2_holesize];	\
+	char	DB1_stack_guard[guardsize];	\
+	char	DB1_stack[EXCEPTION_STKSZ];	\
+	char	DB_stack_guard[guardsize];	\
+	char	DB_stack[EXCEPTION_STKSZ];	\
+	char	MCE_stack_guard[guardsize];	\
+	char	MCE_stack[EXCEPTION_STKSZ];	\
+	char	IST_top_guard[guardsize];	\
+
+/* The exception stacks' physical storage. No guard pages required */
+struct exception_stacks {
+	ESTACKS_MEMBERS(0, 0)
+};
+
+/* The effective cpu entry area mapping with guard pages. */
+struct cea_exception_stacks {
+	ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
+};
+
+/*
+ * The exception stack ordering in [cea_]exception_stacks
+ */
+enum exception_stack_ordering {
+	ESTACK_DF,
+	ESTACK_NMI,
+	ESTACK_DB2,
+	ESTACK_DB1,
+	ESTACK_DB,
+	ESTACK_MCE,
+	N_EXCEPTION_STACKS
+};
+
+#define CEA_ESTACK_SIZE(st)					\
+	sizeof(((struct cea_exception_stacks *)0)->st## _stack)
+
+#define CEA_ESTACK_BOT(ceastp, st)				\
+	((unsigned long)&(ceastp)->st## _stack)
+
+#define CEA_ESTACK_TOP(ceastp, st)				\
+	(CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st))
+
+#define CEA_ESTACK_OFFS(st)					\
+	offsetof(struct cea_exception_stacks, st## _stack)
+
+#define CEA_ESTACK_PAGES					\
+	(sizeof(struct cea_exception_stacks) / PAGE_SIZE)
+
+#endif
+
 /*
  * cpu_entry_area is a percpu region that contains things needed by the CPU
  * and early entry/exit code.  Real types aren't used for all fields here
@@ -32,12 +90,9 @@ struct cpu_entry_area {
 
 #ifdef CONFIG_X86_64
 	/*
-	 * Exception stacks used for IST entries.
-	 *
-	 * In the future, this should have a separate slot for each stack
-	 * with guard pages between them.
+	 * Exception stacks used for IST entries with guard pages.
 	 */
-	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+	struct cea_exception_stacks estacks;
 #endif
 #ifdef CONFIG_CPU_SUP_INTEL
 	/*
@@ -57,6 +112,7 @@ struct cpu_entry_area {
 #define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
@@ -76,4 +132,7 @@ static inline struct entry_stack *cpu_entry_stack(int cpu)
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
 
+#define __this_cpu_ist_top_va(name)					\
+	CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name)
+
 #endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0e56ff7e4848..1d337c51f7e6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -156,11 +156,14 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 #else
 
 /*
- * Static testing of CPU features.  Used the same as boot_cpu_has().
- * These will statically patch the target code for additional
- * performance.
+ * Static testing of CPU features. Used the same as boot_cpu_has(). It
+ * statically patches the target code for additional performance. Use
+ * static_cpu_has() only in fast paths, where every cycle counts. Which
+ * means that the boot_cpu_has() variant is already fast enough for the
+ * majority of cases and you should stick to using it as it is generally
+ * only two instructions: a RIP-relative MOV and a TEST.
  */
-static __always_inline __pure bool _static_cpu_has(u16 bit)
+static __always_inline bool _static_cpu_has(u16 bit)
 {
 	asm_volatile_goto("1: jmp 6f\n"
 		 "2:\n"
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 9e5ca30738e5..1a8609a15856 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -104,11 +104,9 @@ static inline void debug_stack_usage_dec(void)
 {
 	__this_cpu_dec(debug_stack_usage);
 }
-int is_debug_stack(unsigned long addr);
 void debug_stack_set_zero(void);
 void debug_stack_reset(void);
 #else /* !X86_64 */
-static inline int is_debug_stack(unsigned long addr) { return 0; }
 static inline void debug_stack_set_zero(void) { }
 static inline void debug_stack_reset(void) { }
 static inline void debug_stack_usage_inc(void) { }
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 50ba74a34a37..9da8cccdf3fb 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -103,8 +103,6 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
 	FIX_PARAVIRT_BOOTMAP,
 #endif
-	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
-	FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index fb04a3ded7dd..745a19d34f23 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -253,7 +253,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
@@ -275,7 +275,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
@@ -497,8 +497,7 @@ static inline void fpregs_activate(struct fpu *fpu)
  *  - switch_fpu_finish() restores the new state as
  *    necessary.
  */
-static inline void
-switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
 	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index ae26df1c2789..8380c3ddd4b2 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,7 +8,7 @@
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
-#define MAX_FIXED_PEBS_EVENTS	3
+#define MAX_FIXED_PEBS_EVENTS	4
 
 /*
  * A debug store configuration.
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 686247db3106..a06a9f8294ea 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -90,8 +90,6 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define __raw_writew __writew
 #define __raw_writel __writel
 
-#define mmiowb() barrier()
-
 #ifdef CONFIG_X86_64
 
 build_mmio_read(readq, "q", u64, "=r", :"memory")
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index fbb16e6b6c18..8f95686ec27e 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -16,11 +16,7 @@ static inline int irq_canonicalize(int irq)
 	return ((irq == 2) ? 9 : irq);
 }
 
-#ifdef CONFIG_X86_32
-extern void irq_ctx_init(int cpu);
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-#endif
+extern int irq_init_percpu_irqstack(unsigned int cpu);
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 548d90bbf919..889f8b1b5b7f 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -18,8 +18,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
- *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
+ *  Vectors 129 ... LOCAL_TIMER_VECTOR-1
+ *  Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
  *
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a9d03af34030..c79abe7ca093 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -295,6 +295,7 @@ union kvm_mmu_extended_role {
 		unsigned int valid:1;
 		unsigned int execonly:1;
 		unsigned int cr0_pg:1;
+		unsigned int cr4_pae:1;
 		unsigned int cr4_pse:1;
 		unsigned int cr4_pke:1;
 		unsigned int cr4_smap:1;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 19d18fae6ec6..93dff1963337 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -13,6 +13,7 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+#include <asm/debugreg.h>
 
 extern atomic64_t last_mm_ctx_id;
 
@@ -356,4 +357,59 @@ static inline unsigned long __get_current_cr3_fast(void)
 	return cr3;
 }
 
+typedef struct {
+	struct mm_struct *mm;
+} temp_mm_state_t;
+
+/*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down.
+ *
+ * Context: The temporary mm needs to be used exclusively by a single core. To
+ *          harden security IRQs must be disabled while the temporary mm is
+ *          loaded, thereby preventing interrupt handler bugs from overriding
+ *          the kernel memory protection.
+ */
+static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
+{
+	temp_mm_state_t temp_state;
+
+	lockdep_assert_irqs_disabled();
+	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	switch_mm_irqs_off(NULL, mm, current);
+
+	/*
+	 * If breakpoints are enabled, disable them while the temporary mm is
+	 * used. Userspace might set up watchpoints on addresses that are used
+	 * in the temporary mm, which would lead to wrong signals being sent or
+	 * crashes.
+	 *
+	 * Note that breakpoints are not disabled selectively, which also causes
+	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
+	 * undesirable, but still seems reasonable as the code that runs in the
+	 * temporary mm should be short.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_disable();
+
+	return temp_state;
+}
+
+static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
+{
+	lockdep_assert_irqs_disabled();
+	switch_mm_irqs_off(NULL, prev_state.mm, current);
+
+	/*
+	 * Restore the breakpoints if they were disabled before the temporary mm
+	 * was loaded.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ca5bc0eacb95..1378518cf63f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -116,6 +116,7 @@
 #define LBR_INFO_CYCLES			0xffff
 
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
+#define MSR_PEBS_DATA_CFG		0x000003f2
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index dad12b767ba0..daf25b60c9e3 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -11,6 +11,15 @@
 #include <asm/msr-index.h>
 
 /*
+ * This should be used immediately before a retpoline alternative. It tells
+ * objtool where the retpolines are so that it can make sense of the control
+ * flow by just reading the original instruction(s) and ignoring the
+ * alternatives.
+ */
+#define ANNOTATE_NOSPEC_ALTERNATIVE \
+	ANNOTATE_IGNORE_ALTERNATIVE
+
+/*
  * Fill the CPU return stack buffer.
  *
  * Each entry in the RSB, if used for a speculative 'ret', contains an
@@ -57,19 +66,6 @@
 #ifdef __ASSEMBLY__
 
 /*
- * This should be used immediately before a retpoline alternative.  It tells
- * objtool where the retpolines are so that it can make sense of the control
- * flow by just reading the original instruction(s) and ignoring the
- * alternatives.
- */
-.macro ANNOTATE_NOSPEC_ALTERNATIVE
-	.Lannotate_\@:
-	.pushsection .discard.nospec
-	.long .Lannotate_\@ - .
-	.popsection
-.endm
-
-/*
  * This should be used immediately before an indirect jump/call. It tells
  * objtool the subsequent indirect jump/call is vouched safe for retpoline
  * builds.
@@ -152,12 +148,6 @@
 
 #else /* __ASSEMBLY__ */
 
-#define ANNOTATE_NOSPEC_ALTERNATIVE				\
-	"999:\n\t"						\
-	".pushsection .discard.nospec\n\t"			\
-	".long 999b - .\n\t"					\
-	".popsection\n\t"
-
 #define ANNOTATE_RETPOLINE_SAFE					\
 	"999:\n\t"						\
 	".pushsection .discard.retpoline_safe\n\t"		\
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 0d5c739eebd7..565ad755c785 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -22,11 +22,9 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define DOUBLEFAULT_STACK 1
-#define NMI_STACK 0
-#define DEBUG_STACK 0
-#define MCE_STACK 0
-#define N_EXCEPTION_STACKS 1
+#define IRQ_STACK_SIZE		THREAD_SIZE
+
+#define N_EXCEPTION_STACKS	1
 
 #ifdef CONFIG_X86_PAE
 /*
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8f657286d599..793c14c372cb 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,22 +14,20 @@
 
 #define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
 #define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define CURRENT_MASK (~(THREAD_SIZE - 1))
 
 #define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)
 #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
 
-#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
-#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-
 #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define DOUBLEFAULT_STACK 1
-#define NMI_STACK 2
-#define DEBUG_STACK 3
-#define MCE_STACK 4
-#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
+/*
+ * The index for the tss.ist[] array. The hardware limit is 7 entries.
+ */
+#define	IST_INDEX_DF		0
+#define	IST_INDEX_NMI		1
+#define	IST_INDEX_DB		2
+#define	IST_INDEX_MCE		3
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8bdf74902293..1392d5e6e8d6 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
  */
 
 #define INTEL_PMC_MAX_GENERIC				       32
-#define INTEL_PMC_MAX_FIXED					3
+#define INTEL_PMC_MAX_FIXED					4
 #define INTEL_PMC_IDX_FIXED				       32
 
 #define X86_PMC_IDX_MAX					       64
@@ -32,6 +32,8 @@
 
 #define HSW_IN_TX					(1ULL << 32)
 #define HSW_IN_TX_CHECKPOINTED				(1ULL << 33)
+#define ICL_EVENTSEL_ADAPTIVE				(1ULL << 34)
+#define ICL_FIXED_0_ADAPTIVE				(1ULL << 32)
 
 #define AMD64_EVENTSEL_INT_CORE_ENABLE			(1ULL << 36)
 #define AMD64_EVENTSEL_GUESTONLY			(1ULL << 40)
@@ -87,6 +89,12 @@
 #define ARCH_PERFMON_BRANCH_MISSES_RETIRED		6
 #define ARCH_PERFMON_EVENTS_COUNT			7
 
+#define PEBS_DATACFG_MEMINFO	BIT_ULL(0)
+#define PEBS_DATACFG_GP	BIT_ULL(1)
+#define PEBS_DATACFG_XMMS	BIT_ULL(2)
+#define PEBS_DATACFG_LBRS	BIT_ULL(3)
+#define PEBS_DATACFG_LBR_SHIFT	24
+
 /*
  * Intel "Architectural Performance Monitoring" CPUID
  * detection/enumeration details:
@@ -177,6 +185,41 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
+ * Adaptive PEBS v4
+ */
+
+struct pebs_basic {
+	u64 format_size;
+	u64 ip;
+	u64 applicable_counters;
+	u64 tsc;
+};
+
+struct pebs_meminfo {
+	u64 address;
+	u64 aux;
+	u64 latency;
+	u64 tsx_tuning;
+};
+
+struct pebs_gprs {
+	u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+	u64 r8, r9, r10, r11, r12, r13, r14, r15;
+};
+
+struct pebs_xmm {
+	u64 xmm[16*2];	/* two entries for each register */
+};
+
+struct pebs_lbr_entry {
+	u64 from, to, info;
+};
+
+struct pebs_lbr {
+	struct pebs_lbr_entry lbr[0]; /* Variable length */
+};
+
+/*
  * IBS cpuid feature detection
  */
 
@@ -248,6 +291,11 @@ extern void perf_events_lapic_init(void);
 #define PERF_EFLAGS_VM		(1UL << 5)
 
 struct pt_regs;
+struct x86_perf_regs {
+	struct pt_regs	regs;
+	u64		*xmm_regs;
+};
+
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
@@ -260,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
  */
 #define perf_arch_fetch_caller_regs(regs, __ip)		{	\
 	(regs)->ip = (__ip);					\
-	(regs)->bp = caller_frame_pointer();			\
+	(regs)->sp = (unsigned long)__builtin_frame_address(0);	\
 	(regs)->cs = __KERNEL_CS;				\
 	regs->flags = 0;					\
-	asm volatile(						\
-		_ASM_MOV "%%"_ASM_SP ", %0\n"			\
-		: "=m" ((regs)->sp)				\
-		:: "memory"					\
-	);							\
 }
 
 struct perf_guest_switch_msr {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 2779ace16d23..3a221942f805 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -46,7 +46,7 @@ void ptdump_walk_user_pgd_level_checkwx(void);
  */
 extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 	__visible;
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page))
 
 extern spinlock_t pgd_lock;
 extern struct list_head pgd_list;
@@ -1021,6 +1021,9 @@ static inline void __meminit init_trampoline_default(void)
 	/* Default trampoline pgd value */
 	trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 }
+
+void __init poking_init(void);
+
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
 # else
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2bb3a648fc12..7e99ef67bff0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -367,6 +367,13 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 #define __KERNEL_TSS_LIMIT	\
 	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
 
+/* Per CPU interrupt stacks */
+struct irq_stack {
+	char		stack[IRQ_STACK_SIZE];
+} __aligned(IRQ_STACK_SIZE);
+
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #else
@@ -374,38 +381,25 @@ DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
-/*
- * Save the original ist values for checking stack pointers during debugging
- */
-struct orig_ist {
-	unsigned long		ist[7];
-};
-
 #ifdef CONFIG_X86_64
-DECLARE_PER_CPU(struct orig_ist, orig_ist);
-
-union irq_stack_union {
-	char irq_stack[IRQ_STACK_SIZE];
+struct fixed_percpu_data {
 	/*
 	 * GCC hardcodes the stack canary as %gs:40.  Since the
 	 * irq_stack is the object at %gs:0, we reserve the bottom
 	 * 48 bytes of the irq stack for the canary.
 	 */
-	struct {
-		char gs_base[40];
-		unsigned long stack_canary;
-	};
+	char		gs_base[40];
+	unsigned long	stack_canary;
 };
 
-DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_union);
+DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
+DECLARE_INIT_PER_CPU(fixed_percpu_data);
 
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu);
+	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
 }
 
-DECLARE_PER_CPU(char *, irq_stack_ptr);
 DECLARE_PER_CPU(unsigned int, irq_count);
 extern asmlinkage void ignore_sysret(void);
 
@@ -427,15 +421,8 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
-/*
- * per-CPU IRQ handling stacks
- */
-struct irq_stack {
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __aligned(THREAD_SIZE);
-
-DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
-DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
+/* Per CPU softirq stack pointer */
+DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
 #endif	/* X86_64 */
 
 extern unsigned int fpu_kernel_xstate_size;
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
deleted file mode 100644
index 4c25cf6caefa..000000000000
--- a/arch/x86/include/asm/rwsem.h
+++ /dev/null
@@ -1,237 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
- *
- * Written by David Howells (dhowells@redhat.com).
- *
- * Derived from asm-x86/semaphore.h
- *
- *
- * The MSW of the count is the negated number of active writers and waiting
- * lockers, and the LSW is the total number of active locks
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
- * uncontended lock. This can be determined because XADD returns the old value.
- * Readers increment by 1 and see a positive value when uncontended, negative
- * if there are writers (and maybe) readers waiting (in which case it goes to
- * sleep).
- *
- * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
- * be extended to 65534 by manually checking the whole MSW rather than relying
- * on the S flag.
- *
- * The value of ACTIVE_BIAS supports up to 65535 active processes.
- *
- * This should be totally fair - if anything is waiting, a process that wants a
- * lock will go to the back of the queue. When the currently active lock is
- * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consecutive readers at the
- * front, then they'll all be woken up, but no other readers will be.
- */
-
-#ifndef _ASM_X86_RWSEM_H
-#define _ASM_X86_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-#include <asm/asm.h>
-
-/*
- * The bias values and the counter type limits the number of
- * potential readers/writers to 32767 for 32 bits and 2147483647
- * for 64 bits.
- */
-
-#ifdef CONFIG_X86_64
-# define RWSEM_ACTIVE_MASK		0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK		0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-#define ____down_read(sem, slow_path)					\
-({									\
-	struct rw_semaphore* ret;					\
-	asm volatile("# beginning down_read\n\t"			\
-		     LOCK_PREFIX _ASM_INC "(%[sem])\n\t"		\
-		     /* adds 0x00000001 */				\
-		     "  jns        1f\n"				\
-		     "  call " slow_path "\n"				\
-		     "1:\n\t"						\
-		     "# ending down_read\n\t"				\
-		     : "+m" (sem->count), "=a" (ret),			\
-			ASM_CALL_CONSTRAINT				\
-		     : [sem] "a" (sem)					\
-		     : "memory", "cc");					\
-	ret;								\
-})
-
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	____down_read(sem, "call_rwsem_down_read_failed");
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable")))
-		return -EINTR;
-	return 0;
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline bool __down_read_trylock(struct rw_semaphore *sem)
-{
-	long result, tmp;
-	asm volatile("# beginning __down_read_trylock\n\t"
-		     "  mov          %[count],%[result]\n\t"
-		     "1:\n\t"
-		     "  mov          %[result],%[tmp]\n\t"
-		     "  add          %[inc],%[tmp]\n\t"
-		     "  jle	     2f\n\t"
-		     LOCK_PREFIX "  cmpxchg  %[tmp],%[count]\n\t"
-		     "  jnz	     1b\n\t"
-		     "2:\n\t"
-		     "# ending __down_read_trylock\n\t"
-		     : [count] "+m" (sem->count), [result] "=&a" (result),
-		       [tmp] "=&r" (tmp)
-		     : [inc] "i" (RWSEM_ACTIVE_READ_BIAS)
-		     : "memory", "cc");
-	return result >= 0;
-}
-
-/*
- * lock for writing
- */
-#define ____down_write(sem, slow_path)			\
-({							\
-	long tmp;					\
-	struct rw_semaphore* ret;			\
-							\
-	asm volatile("# beginning down_write\n\t"	\
-		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"	\
-		     /* adds 0xffff0001, returns the old value */ \
-		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
-		     /* was the active mask 0 before? */\
-		     "  jz        1f\n"			\
-		     "  call " slow_path "\n"		\
-		     "1:\n"				\
-		     "# ending down_write"		\
-		     : "+m" (sem->count), [tmp] "=d" (tmp),	\
-		       "=a" (ret), ASM_CALL_CONSTRAINT	\
-		     : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \
-		     : "memory", "cc");			\
-	ret;						\
-})
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	____down_write(sem, "call_rwsem_down_write_failed");
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable")))
-		return -EINTR;
-
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline bool __down_write_trylock(struct rw_semaphore *sem)
-{
-	bool result;
-	long tmp0, tmp1;
-	asm volatile("# beginning __down_write_trylock\n\t"
-		     "  mov          %[count],%[tmp0]\n\t"
-		     "1:\n\t"
-		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
-		     /* was the active mask 0 before? */
-		     "  jnz          2f\n\t"
-		     "  mov          %[tmp0],%[tmp1]\n\t"
-		     "  add          %[inc],%[tmp1]\n\t"
-		     LOCK_PREFIX "  cmpxchg  %[tmp1],%[count]\n\t"
-		     "  jnz	     1b\n\t"
-		     "2:\n\t"
-		     CC_SET(e)
-		     "# ending __down_write_trylock\n\t"
-		     : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0),
-		       [tmp1] "=&r" (tmp1), CC_OUT(e) (result)
-		     : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory");
-	return result;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-	asm volatile("# beginning __up_read\n\t"
-		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
-		     /* subtracts 1, returns the old value */
-		     "  jns        1f\n\t"
-		     "  call call_rwsem_wake\n" /* expects old value in %edx */
-		     "1:\n"
-		     "# ending __up_read\n"
-		     : "+m" (sem->count), [tmp] "=d" (tmp)
-		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS)
-		     : "memory", "cc");
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	long tmp;
-	asm volatile("# beginning __up_write\n\t"
-		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
-		     /* subtracts 0xffff0001, returns the old value */
-		     "  jns        1f\n\t"
-		     "  call call_rwsem_wake\n" /* expects old value in %edx */
-		     "1:\n\t"
-		     "# ending __up_write\n"
-		     : "+m" (sem->count), [tmp] "=d" (tmp)
-		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory", "cc");
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	asm volatile("# beginning __downgrade_write\n\t"
-		     LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t"
-		     /*
-		      * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
-		      *     0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
-		      */
-		     "  jns       1f\n\t"
-		     "  call call_rwsem_downgrade_wake\n"
-		     "1:\n\t"
-		     "# ending __downgrade_write\n"
-		     : "+m" (sem->count)
-		     : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS)
-		     : "memory", "cc");
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 07a25753e85c..ae7b909dc242 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -85,6 +85,9 @@ int set_pages_nx(struct page *page, int numpages);
 int set_pages_ro(struct page *page, int numpages);
 int set_pages_rw(struct page *page, int numpages);
 
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
 extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index db333300bd4b..f94a7d0ddd49 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -13,13 +13,12 @@
 #ifndef _ASM_X86_SMAP_H
 #define _ASM_X86_SMAP_H
 
-#include <linux/stringify.h>
 #include <asm/nops.h>
 #include <asm/cpufeatures.h>
 
 /* "Raw" instruction opcodes */
-#define __ASM_CLAC	.byte 0x0f,0x01,0xca
-#define __ASM_STAC	.byte 0x0f,0x01,0xcb
+#define __ASM_CLAC	".byte 0x0f,0x01,0xca"
+#define __ASM_STAC	".byte 0x0f,0x01,0xcb"
 
 #ifdef __ASSEMBLY__
 
@@ -28,10 +27,10 @@
 #ifdef CONFIG_X86_SMAP
 
 #define ASM_CLAC \
-	ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP
+	ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP
 
 #define ASM_STAC \
-	ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP
+	ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP
 
 #else /* CONFIG_X86_SMAP */
 
@@ -49,26 +48,46 @@
 static __always_inline void clac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP);
+	alternative("", __ASM_CLAC, X86_FEATURE_SMAP);
 }
 
 static __always_inline void stac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP);
+	alternative("", __ASM_STAC, X86_FEATURE_SMAP);
+}
+
+static __always_inline unsigned long smap_save(void)
+{
+	unsigned long flags;
+
+	asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
+				  X86_FEATURE_SMAP)
+		      : "=rm" (flags) : : "memory", "cc");
+
+	return flags;
+}
+
+static __always_inline void smap_restore(unsigned long flags)
+{
+	asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+		      : : "g" (flags) : "memory", "cc");
 }
 
 /* These macros can be used in asm() statements */
 #define ASM_CLAC \
-	ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP)
+	ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP)
 #define ASM_STAC \
-	ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP)
+	ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP)
 
 #else /* CONFIG_X86_SMAP */
 
 static inline void clac(void) { }
 static inline void stac(void) { }
 
+static inline unsigned long smap_save(void) { return 0; }
+static inline void smap_restore(unsigned long flags) { }
+
 #define ASM_CLAC
 #define ASM_STAC
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 2e95b6c1bca3..da545df207b2 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -131,7 +131,7 @@ void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
-void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
+int common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_disable(void);
 int common_cpu_die(unsigned int cpu);
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 8ec97a62c245..91e29b6a86a5 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -13,7 +13,7 @@
  * On x86_64, %gs is shared by percpu area and stack canary.  All
  * percpu symbols are zero based and %gs points to the base of percpu
  * area.  The first occupant of the percpu area is always
- * irq_stack_union which contains stack_canary at offset 40.  Userland
+ * fixed_percpu_data which contains stack_canary at offset 40.  Userland
  * %gs is always saved and restored on kernel entry and exit using
  * swapgs, so stack protector doesn't add any complexity there.
  *
@@ -64,7 +64,7 @@ static __always_inline void boot_init_stack_canary(void)
 	u64 tsc;
 
 #ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
 #endif
 	/*
 	 * We both use the random pool and the current TSC as a source
@@ -79,7 +79,7 @@ static __always_inline void boot_init_stack_canary(void)
 
 	current->stack_canary = canary;
 #ifdef CONFIG_X86_64
-	this_cpu_write(irq_stack_union.stack_canary, canary);
+	this_cpu_write(fixed_percpu_data.stack_canary, canary);
 #else
 	this_cpu_write(stack_canary.canary, canary);
 #endif
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f335aad404a4..a8d0cdf48616 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -9,6 +9,8 @@
 
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
+
+#include <asm/cpu_entry_area.h>
 #include <asm/switch_to.h>
 
 enum stack_type {
@@ -98,19 +100,6 @@ struct stack_frame_ia32 {
     u32 return_address;
 };
 
-static inline unsigned long caller_frame_pointer(void)
-{
-	struct stack_frame *frame;
-
-	frame = __builtin_frame_address(0);
-
-#ifdef CONFIG_FRAME_POINTER
-	frame = frame->next_frame;
-#endif
-
-	return (unsigned long)frame;
-}
-
 void show_opcodes(struct pt_regs *regs, const char *loglvl);
 void show_ip(struct pt_regs *regs, const char *loglvl);
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 7cf1a270d891..18a4b6890fa8 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -46,6 +46,7 @@ struct inactive_task_frame {
 	unsigned long r13;
 	unsigned long r12;
 #else
+	unsigned long flags;
 	unsigned long si;
 	unsigned long di;
 #endif
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 2fe745356fb1..6d8d6bc183b7 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -14,6 +14,8 @@
  * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
  */
 
+#include <asm/rmwcc.h>
+
 #define ADDR (*(volatile long *)addr)
 
 /**
@@ -29,7 +31,7 @@
  */
 static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; bts %1,%0"
+	asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -47,7 +49,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btr %1,%0"
+	asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -64,7 +66,7 @@ static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btc %1,%0"
+	asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -78,14 +80,9 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
+static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; bts %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
 /**
@@ -98,12 +95,7 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; btr %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
 /**
@@ -116,12 +108,7 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; btc %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
 #define sync_test_bit(nr, addr) test_bit(nr, addr)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index e85ff65c43c3..c90678fd391a 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -18,7 +18,7 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
@@ -35,8 +35,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
+extern __ro_after_init struct mm_struct *poking_mm;
+extern __ro_after_init unsigned long poking_addr;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 404b8b1d44f5..f23e7aaff4cd 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,7 @@
 #define tlb_end_vma(tlb, vma) do { } while (0)
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
+#define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index f4204bf377fc..dee375831962 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -167,7 +167,7 @@ struct tlb_state {
 	 */
 	struct mm_struct *loaded_mm;
 
-#define LOADED_MM_SWITCHING ((struct mm_struct *)1)
+#define LOADED_MM_SWITCHING ((struct mm_struct *)1UL)
 
 	/* Last user mm for optimizing IBPB */
 	union {
@@ -274,6 +274,8 @@ static inline bool nmi_uaccess_okay(void)
 	return true;
 }
 
+#define nmi_uaccess_okay nmi_uaccess_okay
+
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1954dd5552a2..c82abd6e4ca3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -427,10 +427,11 @@ do {									\
 ({								\
 	__label__ __pu_label;					\
 	int __pu_err = -EFAULT;					\
-	__typeof__(*(ptr)) __pu_val;				\
-	__pu_val = x;						\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(ptr) __pu_ptr = (ptr);			\
+	__typeof__(size) __pu_size = (size);			\
 	__uaccess_begin();					\
-	__put_user_size(__pu_val, (ptr), (size), __pu_label);	\
+	__put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label);	\
 	__pu_err = 0;						\
 __pu_label:							\
 	__uaccess_end();					\
@@ -585,7 +586,6 @@ extern void __cmpxchg_wrong_size(void)
 #define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size)	\
 ({									\
 	int __ret = 0;							\
-	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
 	__uaccess_begin_nospec();					\
@@ -661,7 +661,7 @@ extern void __cmpxchg_wrong_size(void)
 		__cmpxchg_wrong_size();					\
 	}								\
 	__uaccess_end();						\
-	*__uval = __old;						\
+	*(uval) = __old;						\
 	__ret;								\
 })
 
@@ -705,7 +705,7 @@ extern struct movsl_mask {
  * checking before using them, but you have to surround them with the
  * user_access_begin/end() pair.
  */
-static __must_check inline bool user_access_begin(const void __user *ptr, size_t len)
+static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
 {
 	if (unlikely(!access_ok(ptr,len)))
 		return 0;
@@ -715,6 +715,9 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t
 #define user_access_begin(a,b)	user_access_begin(a,b)
 #define user_access_end()	__uaccess_end()
 
+#define user_access_save()	smap_save()
+#define user_access_restore(x)	smap_restore(x)
+
 #define unsafe_put_user(x, ptr, label)	\
 	__put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label)
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index a9d637bc301d..5cd1caa8bc65 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,9 +208,6 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 }
 
 unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len);
-
-unsigned long
 mcsafe_handle_tail(char *to, char *from, unsigned len);
 
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 2863c2026655..d50c7b747d8b 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -217,6 +217,22 @@ xen_single_call(unsigned int call,
 	return (long)__res;
 }
 
+static __always_inline void __xen_stac(void)
+{
+	/*
+	 * Suppress objtool seeing the STAC/CLAC and getting confused about it
+	 * calling random code with AC=1.
+	 */
+	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+		     ASM_STAC ::: "memory", "flags");
+}
+
+static __always_inline void __xen_clac(void)
+{
+	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+		     ASM_CLAC ::: "memory", "flags");
+}
+
 static inline long
 privcmd_call(unsigned int call,
 	     unsigned long a1, unsigned long a2,
@@ -225,9 +241,9 @@ privcmd_call(unsigned int call,
 {
 	long res;
 
-	stac();
+	__xen_stac();
 	res = xen_single_call(call, a1, a2, a3, a4, a5);
-	clac();
+	__xen_clac();
 
 	return res;
 }
@@ -424,9 +440,9 @@ HYPERVISOR_dm_op(
 	domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs)
 {
 	int ret;
-	stac();
+	__xen_stac();
 	ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs);
-	clac();
+	__xen_clac();
 	return ret;
 }
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index dabfcf7c3941..7a0e64ccd6ff 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -381,6 +381,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP	(1 << 3)
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,8 +27,29 @@ enum perf_event_x86_regs {
 	PERF_REG_X86_R13,
 	PERF_REG_X86_R14,
 	PERF_REG_X86_R15,
-
+	/* These are the limits for the GPRs. */
 	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
 	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+	/* These all need two bits set because they are 128bit */
+	PERF_REG_X86_XMM0  = 32,
+	PERF_REG_X86_XMM1  = 34,
+	PERF_REG_X86_XMM2  = 36,
+	PERF_REG_X86_XMM3  = 38,
+	PERF_REG_X86_XMM4  = 40,
+	PERF_REG_X86_XMM5  = 42,
+	PERF_REG_X86_XMM6  = 44,
+	PERF_REG_X86_XMM7  = 46,
+	PERF_REG_X86_XMM8  = 48,
+	PERF_REG_X86_XMM9  = 50,
+	PERF_REG_X86_XMM10 = 52,
+	PERF_REG_X86_XMM11 = 54,
+	PERF_REG_X86_XMM12 = 56,
+	PERF_REG_X86_XMM13 = 58,
+	PERF_REG_X86_XMM14 = 60,
+	PERF_REG_X86_XMM15 = 62,
+
+	/* These include both GPRs and XMMX registers */
+	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 158ad1483c43..cb6e076a6d39 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -51,6 +51,18 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 	if (c->x86_vendor == X86_VENDOR_INTEL &&
 	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
 			flags->bm_control = 0;
+	/*
+	 * For all recent Centaur CPUs, the ucode will make sure that each
+	 * core can keep cache coherence with each other while entering C3
+	 * type state. So, set bm_check to 1 to indicate that the kernel
+	 * doesn't need to execute a cache flush operation (WBINVD) when
+	 * entering C3 type state.
+	 */
+	if (c->x86_vendor == X86_VENDOR_CENTAUR) {
+		if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
+		    c->x86_stepping >= 0x0e))
+			flags->bm_check = 1;
+	}
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9a79c7808f9c..7b9b49dfc05a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/mmu_context.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -264,7 +265,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-void *text_poke_early(void *addr, const void *opcode, size_t len);
+void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Are we looking at a near JMP with a 1 or 4-byte displacement.
@@ -666,16 +667,136 @@ void __init alternative_instructions(void)
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-void *__init_or_module text_poke_early(void *addr, const void *opcode,
-					      size_t len)
+void __init_or_module text_poke_early(void *addr, const void *opcode,
+				      size_t len)
 {
 	unsigned long flags;
+
+	if (boot_cpu_has(X86_FEATURE_NX) &&
+	    is_module_text_address((unsigned long)addr)) {
+		/*
+		 * Modules text is marked initially as non-executable, so the
+		 * code cannot be running and speculative code-fetches are
+		 * prevented. Just change the code.
+		 */
+		memcpy(addr, opcode, len);
+	} else {
+		local_irq_save(flags);
+		memcpy(addr, opcode, len);
+		local_irq_restore(flags);
+		sync_core();
+
+		/*
+		 * Could also do a CLFLUSH here to speed up CPU recovery; but
+		 * that causes hangs on some VIA CPUs.
+		 */
+	}
+}
+
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
+static void *__text_poke(void *addr, const void *opcode, size_t len)
+{
+	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
+	struct page *pages[2] = {NULL};
+	temp_mm_state_t prev;
+	unsigned long flags;
+	pte_t pte, *ptep;
+	spinlock_t *ptl;
+	pgprot_t pgprot;
+
+	/*
+	 * While boot memory allocator is running we cannot use struct pages as
+	 * they are not yet initialized. There is no way to recover.
+	 */
+	BUG_ON(!after_bootmem);
+
+	if (!core_kernel_text((unsigned long)addr)) {
+		pages[0] = vmalloc_to_page(addr);
+		if (cross_page_boundary)
+			pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
+	} else {
+		pages[0] = virt_to_page(addr);
+		WARN_ON(!PageReserved(pages[0]));
+		if (cross_page_boundary)
+			pages[1] = virt_to_page(addr + PAGE_SIZE);
+	}
+	/*
+	 * If something went wrong, crash and burn since recovery paths are not
+	 * implemented.
+	 */
+	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));
+
 	local_irq_save(flags);
-	memcpy(addr, opcode, len);
+
+	/*
+	 * Map the page without the global bit, as TLB flushing is done with
+	 * flush_tlb_mm_range(), which is intended for non-global PTEs.
+	 */
+	pgprot = __pgprot(pgprot_val(PAGE_KERNEL) & ~_PAGE_GLOBAL);
+
+	/*
+	 * The lock is not really needed, but this allows to avoid open-coding.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+
+	/*
+	 * This must not fail; preallocated in poking_init().
+	 */
+	VM_BUG_ON(!ptep);
+
+	pte = mk_pte(pages[0], pgprot);
+	set_pte_at(poking_mm, poking_addr, ptep, pte);
+
+	if (cross_page_boundary) {
+		pte = mk_pte(pages[1], pgprot);
+		set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
+	}
+
+	/*
+	 * Loading the temporary mm behaves as a compiler barrier, which
+	 * guarantees that the PTE will be set at the time memcpy() is done.
+	 */
+	prev = use_temporary_mm(poking_mm);
+
+	kasan_disable_current();
+	memcpy((u8 *)poking_addr + offset_in_page(addr), opcode, len);
+	kasan_enable_current();
+
+	/*
+	 * Ensure that the PTE is only cleared after the instructions of memcpy
+	 * were issued by using a compiler barrier.
+	 */
+	barrier();
+
+	pte_clear(poking_mm, poking_addr, ptep);
+	if (cross_page_boundary)
+		pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);
+
+	/*
+	 * Loading the previous page-table hierarchy requires a serializing
+	 * instruction that already allows the core to see the updated version.
+	 * Xen-PV is assumed to serialize execution in a similar manner.
+	 */
+	unuse_temporary_mm(prev);
+
+	/*
+	 * Flushing the TLB might involve IPIs, which would require enabled
+	 * IRQs, but not if the mm is not used, as it is in this point.
+	 */
+	flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
+			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
+			   PAGE_SHIFT, false);
+
+	/*
+	 * If the text does not match what we just wrote then something is
+	 * fundamentally screwy; there's nothing we can really do about that.
+	 */
+	BUG_ON(memcmp(addr, opcode, len));
+
+	pte_unmap_unlock(ptep, ptl);
 	local_irq_restore(flags);
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
 	return addr;
 }
 
@@ -689,48 +810,36 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note that the caller must ensure that if the modified code is part of a
+ * module, the module would not be removed during poking. This can be achieved
+ * by registering a module notifier, and ordering module removal and patching
+ * trough a mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {
-	unsigned long flags;
-	char *vaddr;
-	struct page *pages[2];
-	int i;
-
-	/*
-	 * While boot memory allocator is runnig we cannot use struct
-	 * pages as they are not yet initialized.
-	 */
-	BUG_ON(!after_bootmem);
-
 	lockdep_assert_held(&text_mutex);
 
-	if (!core_kernel_text((unsigned long)addr)) {
-		pages[0] = vmalloc_to_page(addr);
-		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
-	} else {
-		pages[0] = virt_to_page(addr);
-		WARN_ON(!PageReserved(pages[0]));
-		pages[1] = virt_to_page(addr + PAGE_SIZE);
-	}
-	BUG_ON(!pages[0]);
-	local_irq_save(flags);
-	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
-	if (pages[1])
-		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
-	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
-	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	clear_fixmap(FIX_TEXT_POKE0);
-	if (pages[1])
-		clear_fixmap(FIX_TEXT_POKE1);
-	local_flush_tlb();
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
-	for (i = 0; i < len; i++)
-		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
-	local_irq_restore(flags);
-	return addr;
+	return __text_poke(addr, opcode, len);
+}
+
+/**
+ * text_poke_kgdb - Update instructions on a live kernel by kgdb
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Only atomic text poke/set should be allowed when not doing early patching.
+ * It means the size must be writable atomically and the address must be aligned
+ * in a way that permits an atomic write. It also makes sure we fit on a single
+ * page.
+ *
+ * Context: should only be used by kgdb, which ensures no other core is running,
+ *	    despite the fact it does not hold the text_mutex.
+ */
+void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
+{
+	return __text_poke(addr, opcode, len);
 }
 
 static void do_sync_core(void *info)
@@ -788,7 +897,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  *	  replacing opcode
  *	- sync cores
  */
-void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
 	unsigned char int3 = 0xcc;
 
@@ -830,7 +939,5 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	 * the writing of the new instruction.
 	 */
 	bp_patching_in_progress = false;
-
-	return addr;
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b7bcdd781651..ab6af775f06c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -802,6 +802,24 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 	return 0;
 }
 
+static int __init lapic_init_clockevent(void)
+{
+	if (!lapic_timer_frequency)
+		return -1;
+
+	/* Calculate the scaled math multiplication factor */
+	lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+					TICK_NSEC, lapic_clockevent.shift);
+	lapic_clockevent.max_delta_ns =
+		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
+	lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
+	lapic_clockevent.min_delta_ns =
+		clockevent_delta2ns(0xF, &lapic_clockevent);
+	lapic_clockevent.min_delta_ticks = 0xF;
+
+	return 0;
+}
+
 static int __init calibrate_APIC_clock(void)
 {
 	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
@@ -810,25 +828,21 @@ static int __init calibrate_APIC_clock(void)
 	long delta, deltatsc;
 	int pm_referenced = 0;
 
-	/**
-	 * check if lapic timer has already been calibrated by platform
-	 * specific routine, such as tsc calibration code. if so, we just fill
+	if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return 0;
+
+	/*
+	 * Check if lapic timer has already been calibrated by platform
+	 * specific routine, such as tsc calibration code. If so just fill
 	 * in the clockevent structure and return.
 	 */
-
-	if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
-		return 0;
-	} else if (lapic_timer_frequency) {
+	if (!lapic_init_clockevent()) {
 		apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
-				lapic_timer_frequency);
-		lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
-					TICK_NSEC, lapic_clockevent.shift);
-		lapic_clockevent.max_delta_ns =
-			clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
-		lapic_clockevent.max_delta_ticks = 0x7FFFFF;
-		lapic_clockevent.min_delta_ns =
-			clockevent_delta2ns(0xF, &lapic_clockevent);
-		lapic_clockevent.min_delta_ticks = 0xF;
+			    lapic_timer_frequency);
+		/*
+		 * Direct calibration methods must have an always running
+		 * local APIC timer, no need for broadcast timer.
+		 */
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 		return 0;
 	}
@@ -869,17 +883,8 @@ static int __init calibrate_APIC_clock(void)
 	pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
 					&delta, &deltatsc);
 
-	/* Calculate the scaled math multiplication factor */
-	lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
-				       lapic_clockevent.shift);
-	lapic_clockevent.max_delta_ns =
-		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
-	lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
-	lapic_clockevent.min_delta_ns =
-		clockevent_delta2ns(0xF, &lapic_clockevent);
-	lapic_clockevent.min_delta_ticks = 0xF;
-
 	lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+	lapic_init_clockevent();
 
 	apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
 	apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 78778b54f904..a5464b8b6c46 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -175,7 +175,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 	this_cpu_write(cpu_llc_id, node);
 
 	/* Account for nodes per socket in multi-core-module processors */
-	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
+	if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index ddced33184b5..d3d075226c0a 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -68,10 +68,12 @@ int main(void)
 #undef ENTRY
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
+	DEFINE(DB_STACK_OFFSET, offsetof(struct cea_exception_stacks, DB_stack) -
+	       offsetof(struct cea_exception_stacks, DB1_stack));
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
-	DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary));
+	DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary));
 	BLANK();
 #endif
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 01004bfb1a1b..fb6a64bd765f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -82,11 +82,14 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  *	performance at the same time..
  */
 
+#ifdef CONFIG_X86_32
 extern __visible void vide(void);
-__asm__(".globl vide\n"
+__asm__(".text\n"
+	".globl vide\n"
 	".type vide, @function\n"
 	".align 4\n"
 	"vide: ret\n");
+#endif
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 804c49493938..64d5aec24203 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -83,7 +83,7 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!cpu_khz)
 		return 0;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
@@ -99,7 +99,7 @@ void arch_freq_prepare_all(void)
 	if (!cpu_khz)
 		return;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
 	for_each_online_cpu(cpu)
@@ -115,7 +115,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!cpu_khz)
 		return 0;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b91b3bfa5cfb..29630393f300 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -440,7 +440,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	char arg[20];
 	int ret, i;
 
-	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") ||
+	    cpu_mitigations_off())
 		return SPECTRE_V2_CMD_NONE;
 
 	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
@@ -672,7 +673,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
 	char arg[20];
 	int ret, i;
 
-	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") ||
+	    cpu_mitigations_off()) {
 		return SPEC_STORE_BYPASS_CMD_NONE;
 	} else {
 		ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
@@ -1008,6 +1010,11 @@ static void __init l1tf_select_mitigation(void)
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return;
 
+	if (cpu_mitigations_off())
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+	else if (cpu_mitigations_auto_nosmt())
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+
 	override_cache_bits(&boot_cpu_data);
 
 	switch (l1tf_mitigation) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5e37dfa4d9df..37640544e12f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -507,19 +507,6 @@ void load_percpu_segment(int cpu)
 DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 #endif
 
-#ifdef CONFIG_X86_64
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-#endif
-
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
 {
@@ -1511,9 +1498,9 @@ static __init int setup_clearcpuid(char *arg)
 __setup("clearcpuid=", setup_clearcpuid);
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(union irq_stack_union,
-		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
+DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
+		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
 /*
  * The following percpu variables are hot.  Align current_task to
@@ -1523,9 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(char *, irq_stack_ptr) =
-	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE;
-
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
 DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
@@ -1562,23 +1547,7 @@ void syscall_init(void)
 	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
-/*
- * Copies of the original ist values from the tss are only accessed during
- * debugging, no special alignment required.
- */
-DEFINE_PER_CPU(struct orig_ist, orig_ist);
-
-static DEFINE_PER_CPU(unsigned long, debug_stack_addr);
 DEFINE_PER_CPU(int, debug_stack_usage);
-
-int is_debug_stack(unsigned long addr)
-{
-	return __this_cpu_read(debug_stack_usage) ||
-		(addr <= __this_cpu_read(debug_stack_addr) &&
-		 addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
-}
-NOKPROBE_SYMBOL(is_debug_stack);
-
 DEFINE_PER_CPU(u32, debug_idt_ctr);
 
 void debug_stack_set_zero(void)
@@ -1668,7 +1637,7 @@ static void setup_getcpu(int cpu)
 	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
 	struct desc_struct d = { };
 
-	if (static_cpu_has(X86_FEATURE_RDTSCP))
+	if (boot_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux(cpudata);
 
 	/* Store CPU and node number in limit. */
@@ -1690,17 +1659,14 @@ static void setup_getcpu(int cpu)
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
  * 'CPU state barrier', nothing should get across.
- * A lot of state is already set up in PDA init for 64 bit
  */
 #ifdef CONFIG_X86_64
 
 void cpu_init(void)
 {
-	struct orig_ist *oist;
+	int cpu = raw_smp_processor_id();
 	struct task_struct *me;
 	struct tss_struct *t;
-	unsigned long v;
-	int cpu = raw_smp_processor_id();
 	int i;
 
 	wait_for_master_cpu(cpu);
@@ -1715,7 +1681,6 @@ void cpu_init(void)
 		load_ucode_ap();
 
 	t = &per_cpu(cpu_tss_rw, cpu);
-	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
 	if (this_cpu_read(numa_node) == 0 &&
@@ -1753,16 +1718,11 @@ void cpu_init(void)
 	/*
 	 * set up and load the per-CPU TSS
 	 */
-	if (!oist->ist[0]) {
-		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
-
-		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
-			estacks += exception_stack_sizes[v];
-			oist->ist[v] = t->x86_tss.ist[v] =
-					(unsigned long)estacks;
-			if (v == DEBUG_STACK-1)
-				per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks;
-		}
+	if (!t->x86_tss.ist[0]) {
+		t->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
+		t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
+		t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
+		t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
 	}
 
 	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index cf25405444ab..415621ddb8a2 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -19,6 +19,8 @@
 
 #include "cpu.h"
 
+#define APICID_SOCKET_ID_BIT 6
+
 /*
  * nodes_per_socket: Stores the number of nodes per socket.
  * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
@@ -87,6 +89,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
 		if (!err)
 			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
 
+		/* Socket ID is ApicId[6] for these processors. */
+		c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+
 		cacheinfo_hygon_init_llc_id(c, cpu, node_id);
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 8492ef7d9015..3da9a8823e47 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -528,7 +528,7 @@ static void do_inject(void)
 	 * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
 	 * Fam10h and later BKDGs.
 	 */
-	if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+	if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
 	    b == 4 &&
 	    boot_cpu_data.x86 < 0x17) {
 		toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 5260185cbf7b..8a4a7823451a 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -418,8 +418,9 @@ static int do_microcode_update(const void __user *buf, size_t size)
 		if (ustate == UCODE_ERROR) {
 			error = -1;
 			break;
-		} else if (ustate == UCODE_OK)
+		} else if (ustate == UCODE_NEW) {
 			apply_microcode_on_target(cpu);
+		}
 	}
 
 	return error;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 16936a24795c..a44bdbe7c55e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -31,6 +31,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/uio.h>
 #include <linux/mm.h>
 
 #include <asm/microcode_intel.h>
@@ -861,32 +862,33 @@ out:
 	return ret;
 }
 
-static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
-				int (*get_ucode_data)(void *, const void *, size_t))
+static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
-	int new_rev = uci->cpu_sig.rev;
-	unsigned int leftover = size;
 	unsigned int curr_mc_size = 0, new_mc_size = 0;
-	unsigned int csig, cpf;
 	enum ucode_state ret = UCODE_OK;
+	int new_rev = uci->cpu_sig.rev;
+	u8 *new_mc = NULL, *mc = NULL;
+	unsigned int csig, cpf;
 
-	while (leftover) {
+	while (iov_iter_count(iter)) {
 		struct microcode_header_intel mc_header;
-		unsigned int mc_size;
+		unsigned int mc_size, data_size;
+		u8 *data;
 
-		if (leftover < sizeof(mc_header)) {
-			pr_err("error! Truncated header in microcode data file\n");
+		if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) {
+			pr_err("error! Truncated or inaccessible header in microcode data file\n");
 			break;
 		}
 
-		if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
-			break;
-
 		mc_size = get_totalsize(&mc_header);
-		if (!mc_size || mc_size > leftover) {
-			pr_err("error! Bad data in microcode data file\n");
+		if (mc_size < sizeof(mc_header)) {
+			pr_err("error! Bad data in microcode data file (totalsize too small)\n");
+			break;
+		}
+		data_size = mc_size - sizeof(mc_header);
+		if (data_size > iov_iter_count(iter)) {
+			pr_err("error! Bad data in microcode data file (truncated file?)\n");
 			break;
 		}
 
@@ -899,7 +901,9 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			curr_mc_size = mc_size;
 		}
 
-		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
+		memcpy(mc, &mc_header, sizeof(mc_header));
+		data = mc + sizeof(mc_header);
+		if (!copy_from_iter_full(data, data_size, iter) ||
 		    microcode_sanity_check(mc, 1) < 0) {
 			break;
 		}
@@ -914,14 +918,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			mc = NULL;	/* trigger new vmalloc */
 			ret = UCODE_NEW;
 		}
-
-		ucode_ptr += mc_size;
-		leftover  -= mc_size;
 	}
 
 	vfree(mc);
 
-	if (leftover) {
+	if (iov_iter_count(iter)) {
 		vfree(new_mc);
 		return UCODE_ERROR;
 	}
@@ -945,12 +946,6 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	return ret;
 }
 
-static int get_ucode_fw(void *to, const void *from, size_t n)
-{
-	memcpy(to, from, n);
-	return 0;
-}
-
 static bool is_blacklisted(unsigned int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -977,10 +972,12 @@ static bool is_blacklisted(unsigned int cpu)
 static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 					     bool refresh_fw)
 {
-	char name[30];
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	const struct firmware *firmware;
+	struct iov_iter iter;
 	enum ucode_state ret;
+	struct kvec kvec;
+	char name[30];
 
 	if (is_blacklisted(cpu))
 		return UCODE_NFOUND;
@@ -993,26 +990,30 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 		return UCODE_NFOUND;
 	}
 
-	ret = generic_load_microcode(cpu, (void *)firmware->data,
-				     firmware->size, &get_ucode_fw);
+	kvec.iov_base = (void *)firmware->data;
+	kvec.iov_len = firmware->size;
+	iov_iter_kvec(&iter, WRITE, &kvec, 1, firmware->size);
+	ret = generic_load_microcode(cpu, &iter);
 
 	release_firmware(firmware);
 
 	return ret;
 }
 
-static int get_ucode_user(void *to, const void *from, size_t n)
-{
-	return copy_from_user(to, from, n);
-}
-
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
+	struct iov_iter iter;
+	struct iovec iov;
+
 	if (is_blacklisted(cpu))
 		return UCODE_NFOUND;
 
-	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
+	iov.iov_base = (void __user *)buf;
+	iov.iov_len = size;
+	iov_iter_init(&iter, WRITE, &iov, 1, size);
+
+	return generic_load_microcode(cpu, &iter);
 }
 
 static struct microcode_ops microcode_intel_ops = {
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 2c8522a39ed5..cb2e49810d68 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -35,11 +35,11 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
 		   "fpu_exception\t: %s\n"
 		   "cpuid level\t: %d\n"
 		   "wp\t\t: yes\n",
-		   static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
-		   static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
-		   static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
-		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
-		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
+		   boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+		   boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
 		   c->cpuid_level);
 }
 #else
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 2dbd990a2eb7..89320c0396b1 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -342,10 +342,10 @@ int update_domains(struct rdt_resource *r, int closid)
 	if (cpumask_empty(cpu_mask) || mba_sc)
 		goto done;
 	cpu = get_cpu();
-	/* Update CBM on this cpu if it's in cpu_mask. */
+	/* Update resource control msr on this CPU if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
 		rdt_ctrl_update(&msr_param);
-	/* Update CBM on other cpus. */
+	/* Update resource control msr on other CPUs. */
 	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	put_cpu();
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 85212a32b54d..333c177a2471 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2516,100 +2516,127 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
 	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
 }
 
-/**
- * rdtgroup_init_alloc - Initialize the new RDT group's allocations
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations. That is, all shareable and unused bits.
+/*
+ * Initialize cache resources per RDT domain
  *
- * All-zero CBM is invalid. If there are no more shareable bits available
- * on any domain then the entire allocation will fail.
+ * Set the RDT domain up to start off with all usable allocations. That is,
+ * all shareable and unused bits. All-zero CBM is invalid.
  */
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
+				 u32 closid)
 {
 	struct rdt_resource *r_cdp = NULL;
 	struct rdt_domain *d_cdp = NULL;
 	u32 used_b = 0, unused_b = 0;
-	u32 closid = rdtgrp->closid;
-	struct rdt_resource *r;
 	unsigned long tmp_cbm;
 	enum rdtgrp_mode mode;
-	struct rdt_domain *d;
 	u32 peer_ctl, *ctrl;
-	int i, ret;
+	int i;
 
-	for_each_alloc_enabled_rdt_resource(r) {
-		/*
-		 * Only initialize default allocations for CBM cache
-		 * resources
-		 */
-		if (r->rid == RDT_RESOURCE_MBA)
-			continue;
-		list_for_each_entry(d, &r->domains, list) {
-			rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
-			d->have_new_ctrl = false;
-			d->new_ctrl = r->cache.shareable_bits;
-			used_b = r->cache.shareable_bits;
-			ctrl = d->ctrl_val;
-			for (i = 0; i < closids_supported(); i++, ctrl++) {
-				if (closid_allocated(i) && i != closid) {
-					mode = rdtgroup_mode_by_closid(i);
-					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
-						break;
-					/*
-					 * If CDP is active include peer
-					 * domain's usage to ensure there
-					 * is no overlap with an exclusive
-					 * group.
-					 */
-					if (d_cdp)
-						peer_ctl = d_cdp->ctrl_val[i];
-					else
-						peer_ctl = 0;
-					used_b |= *ctrl | peer_ctl;
-					if (mode == RDT_MODE_SHAREABLE)
-						d->new_ctrl |= *ctrl | peer_ctl;
-				}
-			}
-			if (d->plr && d->plr->cbm > 0)
-				used_b |= d->plr->cbm;
-			unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
-			unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
-			d->new_ctrl |= unused_b;
-			/*
-			 * Force the initial CBM to be valid, user can
-			 * modify the CBM based on system availability.
-			 */
-			cbm_ensure_valid(&d->new_ctrl, r);
+	rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
+	d->have_new_ctrl = false;
+	d->new_ctrl = r->cache.shareable_bits;
+	used_b = r->cache.shareable_bits;
+	ctrl = d->ctrl_val;
+	for (i = 0; i < closids_supported(); i++, ctrl++) {
+		if (closid_allocated(i) && i != closid) {
+			mode = rdtgroup_mode_by_closid(i);
+			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+				break;
 			/*
-			 * Assign the u32 CBM to an unsigned long to ensure
-			 * that bitmap_weight() does not access out-of-bound
-			 * memory.
+			 * If CDP is active include peer domain's
+			 * usage to ensure there is no overlap
+			 * with an exclusive group.
 			 */
-			tmp_cbm = d->new_ctrl;
-			if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
-			    r->cache.min_cbm_bits) {
-				rdt_last_cmd_printf("No space on %s:%d\n",
-						    r->name, d->id);
-				return -ENOSPC;
-			}
-			d->have_new_ctrl = true;
+			if (d_cdp)
+				peer_ctl = d_cdp->ctrl_val[i];
+			else
+				peer_ctl = 0;
+			used_b |= *ctrl | peer_ctl;
+			if (mode == RDT_MODE_SHAREABLE)
+				d->new_ctrl |= *ctrl | peer_ctl;
 		}
 	}
+	if (d->plr && d->plr->cbm > 0)
+		used_b |= d->plr->cbm;
+	unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+	unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+	d->new_ctrl |= unused_b;
+	/*
+	 * Force the initial CBM to be valid, user can
+	 * modify the CBM based on system availability.
+	 */
+	cbm_ensure_valid(&d->new_ctrl, r);
+	/*
+	 * Assign the u32 CBM to an unsigned long to ensure that
+	 * bitmap_weight() does not access out-of-bound memory.
+	 */
+	tmp_cbm = d->new_ctrl;
+	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
+		rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id);
+		return -ENOSPC;
+	}
+	d->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
+ * Initialize cache resources with default values.
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations.
+ *
+ * If there are no more shareable bits available on any domain then
+ * the entire allocation will fail.
+ */
+static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
+{
+	struct rdt_domain *d;
+	int ret;
+
+	list_for_each_entry(d, &r->domains, list) {
+		ret = __init_one_rdt_domain(d, r, closid);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Initialize MBA resource with default values. */
+static void rdtgroup_init_mba(struct rdt_resource *r)
+{
+	struct rdt_domain *d;
+
+	list_for_each_entry(d, &r->domains, list) {
+		d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+		d->have_new_ctrl = true;
+	}
+}
+
+/* Initialize the RDT group's allocations. */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+	struct rdt_resource *r;
+	int ret;
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		/*
-		 * Only initialize default allocations for CBM cache
-		 * resources
-		 */
-		if (r->rid == RDT_RESOURCE_MBA)
-			continue;
+		if (r->rid == RDT_RESOURCE_MBA) {
+			rdtgroup_init_mba(r);
+		} else {
+			ret = rdtgroup_init_cat(r, rdtgrp->closid);
+			if (ret < 0)
+				return ret;
+		}
+
 		ret = update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("Failed to initialize allocations\n");
 			return ret;
 		}
+
 	}
 
 	rdtgrp->mode = RDT_MODE_SHAREABLE;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 17ffc869cab8..a96ca8584803 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -204,8 +204,7 @@ static struct crash_mem *fill_up_crash_elf_data(void)
 	 * another range split. So add extra two slots here.
 	 */
 	nr_ranges += 2;
-	cmem = vzalloc(sizeof(struct crash_mem) +
-			sizeof(struct crash_mem_range) * nr_ranges);
+	cmem = vzalloc(struct_size(cmem, ranges, nr_ranges));
 	if (!cmem)
 		return NULL;
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index cd53f3030e40..64a59d726639 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -34,14 +34,14 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
@@ -59,14 +59,14 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_SOFTIRQ;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5cdb9e84da57..753b8cfe8b8a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,23 +16,21 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 
-static char *exception_stack_names[N_EXCEPTION_STACKS] = {
-		[ DOUBLEFAULT_STACK-1	]	= "#DF",
-		[ NMI_STACK-1		]	= "NMI",
-		[ DEBUG_STACK-1		]	= "#DB",
-		[ MCE_STACK-1		]	= "#MC",
-};
-
-static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	[0 ... N_EXCEPTION_STACKS - 1]		= EXCEPTION_STKSZ,
-	[DEBUG_STACK - 1]			= DEBUG_STKSZ
+static const char * const exception_stack_names[] = {
+		[ ESTACK_DF	]	= "#DF",
+		[ ESTACK_NMI	]	= "NMI",
+		[ ESTACK_DB2	]	= "#DB2",
+		[ ESTACK_DB1	]	= "#DB1",
+		[ ESTACK_DB	]	= "#DB",
+		[ ESTACK_MCE	]	= "#MC",
 };
 
 const char *stack_type_name(enum stack_type type)
 {
-	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
@@ -52,43 +50,84 @@ const char *stack_type_name(enum stack_type type)
 	return NULL;
 }
 
+/**
+ * struct estack_pages - Page descriptor for exception stacks
+ * @offs:	Offset from the start of the exception stack area
+ * @size:	Size of the exception stack
+ * @type:	Type to store in the stack_info struct
+ */
+struct estack_pages {
+	u32	offs;
+	u16	size;
+	u16	type;
+};
+
+#define EPAGERANGE(st)							\
+	[PFN_DOWN(CEA_ESTACK_OFFS(st)) ...				\
+	 PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = {	\
+		.offs	= CEA_ESTACK_OFFS(st),				\
+		.size	= CEA_ESTACK_SIZE(st),				\
+		.type	= STACK_TYPE_EXCEPTION + ESTACK_ ##st, }
+
+/*
+ * Array of exception stack page descriptors. If the stack is larger than
+ * PAGE_SIZE, all pages covering a particular stack will have the same
+ * info. The guard pages including the not mapped DB2 stack are zeroed
+ * out.
+ */
+static const
+struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = {
+	EPAGERANGE(DF),
+	EPAGERANGE(NMI),
+	EPAGERANGE(DB1),
+	EPAGERANGE(DB),
+	EPAGERANGE(MCE),
+};
+
 static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin, *end;
+	unsigned long begin, end, stk = (unsigned long)stack;
+	const struct estack_pages *ep;
 	struct pt_regs *regs;
-	unsigned k;
+	unsigned int k;
 
-	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
-	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
-		end   = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
-		begin = end - (exception_stack_sizes[k] / sizeof(long));
-		regs  = (struct pt_regs *)end - 1;
-
-		if (stack <= begin || stack >= end)
-			continue;
+	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
+	end = begin + sizeof(struct cea_exception_stacks);
+	/* Bail if @stack is outside the exception stack area. */
+	if (stk < begin || stk >= end)
+		return false;
 
-		info->type	= STACK_TYPE_EXCEPTION + k;
-		info->begin	= begin;
-		info->end	= end;
-		info->next_sp	= (unsigned long *)regs->sp;
+	/* Calc page offset from start of exception stacks */
+	k = (stk - begin) >> PAGE_SHIFT;
+	/* Lookup the page descriptor */
+	ep = &estack_pages[k];
+	/* Guard page? */
+	if (!ep->size)
+		return false;
 
-		return true;
-	}
+	begin += (unsigned long)ep->offs;
+	end = begin + (unsigned long)ep->size;
+	regs = (struct pt_regs *)end - 1;
 
-	return false;
+	info->type	= ep->type;
+	info->begin	= (unsigned long *)begin;
+	info->end	= (unsigned long *)end;
+	info->next_sp	= (unsigned long *)regs->sp;
+	return true;
 }
 
 static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end   = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	unsigned long *end   = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack >= end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index ef49517f6bb2..0caf8122d680 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -678,12 +678,8 @@ static inline void *alloc_tramp(unsigned long size)
 {
 	return module_alloc(size);
 }
-static inline void tramp_free(void *tramp, int size)
+static inline void tramp_free(void *tramp)
 {
-	int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	set_memory_nx((unsigned long)tramp, npages);
-	set_memory_rw((unsigned long)tramp, npages);
 	module_memfree(tramp);
 }
 #else
@@ -692,7 +688,7 @@ static inline void *alloc_tramp(unsigned long size)
 {
 	return NULL;
 }
-static inline void tramp_free(void *tramp, int size) { }
+static inline void tramp_free(void *tramp) { }
 #endif
 
 /* Defined as markers to the end of the ftrace default trampolines */
@@ -730,6 +726,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long offset;
+	unsigned long npages;
 	unsigned long size;
 	unsigned long retq;
 	unsigned long *ptr;
@@ -762,6 +759,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		return 0;
 
 	*tramp_size = size + RET_SIZE + sizeof(void *);
+	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
@@ -806,9 +804,17 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
+	set_vm_flush_reset_perms(trampoline);
+
+	/*
+	 * Module allocation needs to be completed by making the page
+	 * executable. The page is still writable, which is a security hazard,
+	 * but anyhow ftrace breaks W^X completely.
+	 */
+	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
 fail:
-	tramp_free(trampoline, *tramp_size);
+	tramp_free(trampoline);
 	return 0;
 }
 
@@ -939,7 +945,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 	if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
 		return;
 
-	tramp_free((void *)ops->trampoline, ops->trampoline_size);
+	tramp_free((void *)ops->trampoline);
 	ops->trampoline = 0;
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d1dbe8e4eb82..bcd206c8ac90 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -265,7 +265,7 @@ ENDPROC(start_cpu0)
 	GLOBAL(initial_code)
 	.quad	x86_64_start_kernel
 	GLOBAL(initial_gs)
-	.quad	INIT_PER_CPU_VAR(irq_stack_union)
+	.quad	INIT_PER_CPU_VAR(fixed_percpu_data)
 	GLOBAL(initial_stack)
 	/*
 	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 01adea278a71..6d8917875f44 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -41,13 +41,12 @@ struct idt_data {
 #define SYSG(_vector, _addr)				\
 	G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS)
 
-/* Interrupt gate with interrupt stack */
+/*
+ * Interrupt gate with interrupt stack. The _ist index is the index in
+ * the tss.ist[] array, but for the descriptor it needs to start at 1.
+ */
 #define ISTG(_vector, _addr, _ist)			\
-	G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS)
-
-/* System interrupt gate with interrupt stack */
-#define SISTG(_vector, _addr, _ist)			\
-	G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS)
+	G(_vector, _addr, _ist + 1, GATE_INTERRUPT, DPL0, __KERNEL_CS)
 
 /* Task gate */
 #define TSKG(_vector, _gdt)				\
@@ -184,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
  * cpu_init() when the TSS has been initialized.
  */
 static const __initconst struct idt_data ist_idts[] = {
-	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
-	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
-	ISTG(X86_TRAP_DF,	double_fault,	DOUBLEFAULT_STACK),
+	ISTG(X86_TRAP_DB,	debug,		IST_INDEX_DB),
+	ISTG(X86_TRAP_NMI,	nmi,		IST_INDEX_NMI),
+	ISTG(X86_TRAP_DF,	double_fault,	IST_INDEX_DF),
 #ifdef CONFIG_X86_MCE
-	ISTG(X86_TRAP_MC,	&machine_check,	MCE_STACK),
+	ISTG(X86_TRAP_MC,	&machine_check,	IST_INDEX_MCE),
 #endif
 };
 
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 95600a99ae93..fc34816c6f04 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -51,8 +51,8 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
-DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -76,7 +76,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	u32 *isp, *prev_esp, arg1;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(hardirq_stack);
+	irqstk = __this_cpu_read(hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -107,27 +107,28 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 }
 
 /*
- * allocate per-cpu stacks for hardirq and for softirq processing
+ * Allocate per-cpu stacks for hardirq and softirq processing
  */
-void irq_ctx_init(int cpu)
+int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	struct irq_stack *irqstk;
-
-	if (per_cpu(hardirq_stack, cpu))
-		return;
+	int node = cpu_to_node(cpu);
+	struct page *ph, *ps;
 
-	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
-					       THREADINFO_GFP,
-					       THREAD_SIZE_ORDER));
-	per_cpu(hardirq_stack, cpu) = irqstk;
+	if (per_cpu(hardirq_stack_ptr, cpu))
+		return 0;
 
-	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
-					       THREADINFO_GFP,
-					       THREAD_SIZE_ORDER));
-	per_cpu(softirq_stack, cpu) = irqstk;
+	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
+	if (!ph)
+		return -ENOMEM;
+	ps = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
+	if (!ps) {
+		__free_pages(ph, THREAD_SIZE_ORDER);
+		return -ENOMEM;
+	}
 
-	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
+	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
+	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
+	return 0;
 }
 
 void do_softirq_own_stack(void)
@@ -135,7 +136,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(softirq_stack);
+	irqstk = __this_cpu_read(softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 0469cd078db1..6bf6517a05bb 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,63 +18,64 @@
 #include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/sched/task_stack.h>
+
+#include <asm/cpu_entry_area.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
-int sysctl_panic_on_stackoverflow;
+DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
+DECLARE_INIT_PER_CPU(irq_stack_backing_store);
 
-/*
- * Probabilistic stack overflow check:
- *
- * Only check the stack in process context, because everything else
- * runs on the big interrupt stacks. Checking reliably is too expensive,
- * so we just check from interrupts.
- */
-static inline void stack_overflow_check(struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-#define STACK_TOP_MARGIN	128
-	struct orig_ist *oist;
-	u64 irq_stack_top, irq_stack_bottom;
-	u64 estack_top, estack_bottom;
-	u64 curbase = (u64)task_stack_page(current);
+	if (IS_ERR_OR_NULL(desc))
+		return false;
 
-	if (user_mode(regs))
-		return;
+	generic_handle_irq_desc(desc);
+	return true;
+}
 
-	if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
-	    regs->sp <= curbase + THREAD_SIZE)
-		return;
+#ifdef CONFIG_VMAP_STACK
+/*
+ * VMAP the backing store with guard pages
+ */
+static int map_irq_stack(unsigned int cpu)
+{
+	char *stack = (char *)per_cpu_ptr(&irq_stack_backing_store, cpu);
+	struct page *pages[IRQ_STACK_SIZE / PAGE_SIZE];
+	void *va;
+	int i;
 
-	irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
-			STACK_TOP_MARGIN;
-	irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
-	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
-		return;
+	for (i = 0; i < IRQ_STACK_SIZE / PAGE_SIZE; i++) {
+		phys_addr_t pa = per_cpu_ptr_to_phys(stack + (i << PAGE_SHIFT));
 
-	oist = this_cpu_ptr(&orig_ist);
-	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
-	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
-	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
-		return;
+		pages[i] = pfn_to_page(pa >> PAGE_SHIFT);
+	}
 
-	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
-		current->comm, curbase, regs->sp,
-		irq_stack_top, irq_stack_bottom,
-		estack_top, estack_bottom, (void *)regs->ip);
+	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+	if (!va)
+		return -ENOMEM;
 
-	if (sysctl_panic_on_stackoverflow)
-		panic("low stack detected by irq handler - check messages\n");
-#endif
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	return 0;
 }
-
-bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
+#else
+/*
+ * If VMAP stacks are disabled due to KASAN, just use the per cpu
+ * backing store without guard pages.
+ */
+static int map_irq_stack(unsigned int cpu)
 {
-	stack_overflow_check(regs);
+	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
-	if (IS_ERR_OR_NULL(desc))
-		return false;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	return 0;
+}
+#endif
 
-	generic_handle_irq_desc(desc);
-	return true;
+int irq_init_percpu_irqstack(unsigned int cpu)
+{
+	if (per_cpu(hardirq_stack_ptr, cpu))
+		return 0;
+	return map_irq_stack(cpu);
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a0693b71cfc1..16919a9671fa 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -91,6 +91,8 @@ void __init init_IRQ(void)
 	for (i = 0; i < nr_legacy_irqs(); i++)
 		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i);
 
+	BUG_ON(irq_init_percpu_irqstack(smp_processor_id()));
+
 	x86_init.irqs.intr_init();
 }
 
@@ -104,6 +106,4 @@ void __init native_init_IRQ(void)
 
 	if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
 		setup_irq(2, &irq2);
-
-	irq_ctx_init(smp_processor_id());
 }
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index f99bd26bd3f1..e631c358f7f4 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,7 +37,6 @@ static void bug_at(unsigned char *ip, int line)
 
 static void __ref __jump_label_transform(struct jump_entry *entry,
 					 enum jump_label_type type,
-					 void *(*poker)(void *, const void *, size_t),
 					 int init)
 {
 	union jump_code_union jmp;
@@ -50,9 +49,6 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 	jmp.offset = jump_entry_target(entry) -
 		     (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
 
-	if (early_boot_irqs_disabled)
-		poker = text_poke_early;
-
 	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			expect = default_nop; line = __LINE__;
@@ -75,16 +71,19 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 		bug_at((void *)jump_entry_code(entry), line);
 
 	/*
-	 * Make text_poke_bp() a default fallback poker.
+	 * As long as only a single processor is running and the code is still
+	 * not marked as RO, text_poke_early() can be used; Checking that
+	 * system_state is SYSTEM_BOOTING guarantees it. It will be set to
+	 * SYSTEM_SCHEDULING before other cores are awaken and before the
+	 * code is write-protected.
 	 *
 	 * At the time the change is being done, just ignore whether we
 	 * are doing nop -> jump or jump -> nop transition, and assume
 	 * always nop being the 'currently valid' instruction
-	 *
 	 */
-	if (poker) {
-		(*poker)((void *)jump_entry_code(entry), code,
-			 JUMP_LABEL_NOP_SIZE);
+	if (init || system_state == SYSTEM_BOOTING) {
+		text_poke_early((void *)jump_entry_code(entry), code,
+				JUMP_LABEL_NOP_SIZE);
 		return;
 	}
 
@@ -96,7 +95,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
 	mutex_lock(&text_mutex);
-	__jump_label_transform(entry, type, NULL, 0);
+	__jump_label_transform(entry, type, 0);
 	mutex_unlock(&text_mutex);
 }
 
@@ -126,5 +125,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 			jlstate = JL_STATE_NO_UPDATE;
 	}
 	if (jlstate == JL_STATE_UPDATE)
-		__jump_label_transform(entry, type, text_poke_early, 1);
+		__jump_label_transform(entry, type, 1);
 }
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 4ff6b4cdb941..13b13311b792 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -747,7 +747,6 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
-	char opc[BREAK_INSTR_SIZE];
 
 	bpt->type = BP_BREAKPOINT;
 	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
@@ -759,18 +758,13 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	if (!err)
 		return err;
 	/*
-	 * It is safe to call text_poke() because normal kernel execution
+	 * It is safe to call text_poke_kgdb() because normal kernel execution
 	 * is stopped on all cores, so long as the text_mutex is not locked.
 	 */
 	if (mutex_is_locked(&text_mutex))
 		return -EBUSY;
-	text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
-		  BREAK_INSTR_SIZE);
-	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
-	if (err)
-		return err;
-	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
-		return -EINVAL;
+	text_poke_kgdb((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+		       BREAK_INSTR_SIZE);
 	bpt->type = BP_POKE_BREAKPOINT;
 
 	return err;
@@ -778,22 +772,17 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	int err;
-	char opc[BREAK_INSTR_SIZE];
-
 	if (bpt->type != BP_POKE_BREAKPOINT)
 		goto knl_write;
 	/*
-	 * It is safe to call text_poke() because normal kernel execution
+	 * It is safe to call text_poke_kgdb() because normal kernel execution
 	 * is stopped on all cores, so long as the text_mutex is not locked.
 	 */
 	if (mutex_is_locked(&text_mutex))
 		goto knl_write;
-	text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
-	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
-	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
-		goto knl_write;
-	return err;
+	text_poke_kgdb((void *)bpt->bpt_addr, bpt->saved_instr,
+		       BREAK_INSTR_SIZE);
+	return 0;
 
 knl_write:
 	return probe_kernel_write((char *)bpt->bpt_addr,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fed46ddb1eef..cf52ee0d8711 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -431,8 +431,21 @@ void *alloc_insn_page(void)
 	void *page;
 
 	page = module_alloc(PAGE_SIZE);
-	if (page)
-		set_memory_ro((unsigned long)page & PAGE_MASK, 1);
+	if (!page)
+		return NULL;
+
+	set_vm_flush_reset_perms(page);
+	/*
+	 * First make the page read-only, and only then make it executable to
+	 * prevent it from being W+X in between.
+	 */
+	set_memory_ro((unsigned long)page, 1);
+
+	/*
+	 * TODO: Once additional kernel code protection mechanisms are set, ensure
+	 * that the page was not maliciously altered and it is still zeroed.
+	 */
+	set_memory_x((unsigned long)page, 1);
 
 	return page;
 }
@@ -440,8 +453,6 @@ void *alloc_insn_page(void)
 /* Recover page to RW mode before releasing it */
 void free_insn_page(void *page)
 {
-	set_memory_nx((unsigned long)page & PAGE_MASK, 1);
-	set_memory_rw((unsigned long)page & PAGE_MASK, 1);
 	module_memfree(page);
 }
 
@@ -716,6 +727,7 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
 asm(
+	".text\n"
 	".global kretprobe_trampoline\n"
 	".type kretprobe_trampoline, @function\n"
 	"kretprobe_trampoline:\n"
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5c93a65ee1e5..3f0cc828cc36 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -67,7 +67,7 @@ static int __init parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
-static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
+DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
 /*
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 6135ae8ce036..b2463fcb20a8 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -113,7 +113,7 @@ static void do_sanity_check(struct mm_struct *mm,
 		 * tables.
 		 */
 		WARN_ON(!had_kernel_mapping);
-		if (static_cpu_has(X86_FEATURE_PTI))
+		if (boot_cpu_has(X86_FEATURE_PTI))
 			WARN_ON(!had_user_mapping);
 	} else {
 		/*
@@ -121,7 +121,7 @@ static void do_sanity_check(struct mm_struct *mm,
 		 * Sync the pgd to the usermode tables.
 		 */
 		WARN_ON(had_kernel_mapping);
-		if (static_cpu_has(X86_FEATURE_PTI))
+		if (boot_cpu_has(X86_FEATURE_PTI))
 			WARN_ON(had_user_mapping);
 	}
 }
@@ -156,7 +156,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
 	k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
 	u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
 
-	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+	if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
 		set_pmd(u_pmd, *k_pmd);
 }
 
@@ -181,7 +181,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
 {
 	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
 
-	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+	if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
 		set_pgd(kernel_to_user_pgdp(pgd), *pgd);
 }
 
@@ -208,7 +208,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	spinlock_t *ptl;
 	int i, nr_pages;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return 0;
 
 	/*
@@ -271,7 +271,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
 		return;
 
 	/* LDT map/unmap is only required for PTI */
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
@@ -311,7 +311,7 @@ static void free_ldt_pgtables(struct mm_struct *mm)
 	unsigned long start = LDT_BASE_ADDR;
 	unsigned long end = LDT_END_ADDR;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	tlb_gather_mmu(&tlb, mm, start, end);
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b052e883dd8c..cfa3106faee4 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -87,7 +87,7 @@ void *module_alloc(unsigned long size)
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
 				    MODULES_VADDR + get_module_load_offset(),
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 	if (p && (kasan_module_alloc(p, size) < 0)) {
 		vfree(p);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 18bc9b51ac9b..3755d0310026 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -21,13 +21,14 @@
 #include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/atomic.h>
 #include <linux/sched/clock.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
 #endif
 
-#include <linux/atomic.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/traps.h>
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
@@ -487,6 +488,23 @@ static DEFINE_PER_CPU(unsigned long, nmi_cr2);
  * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+
+static bool notrace is_debug_stack(unsigned long addr)
+{
+	struct cea_exception_stacks *cs = __this_cpu_read(cea_exception_stacks);
+	unsigned long top = CEA_ESTACK_TOP(cs, DB);
+	unsigned long bot = CEA_ESTACK_BOT(cs, DB1);
+
+	if (__this_cpu_read(debug_stack_usage))
+		return true;
+	/*
+	 * Note, this covers the guard page between DB and DB1 as well to
+	 * avoid two checks. But by all means @addr can never point into
+	 * the guard page.
+	 */
+	return addr >= bot && addr < top;
+}
+NOKPROBE_SYMBOL(is_debug_stack);
 #endif
 
 dotraplinkage notrace void
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c0e0101133f3..7bbaa6baf37f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -121,7 +121,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
 
 void __init native_pv_lock_init(void)
 {
-	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		static_branch_disable(&virt_spin_lock_key);
 }
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index c06c4c16c6b6..07c30ee17425 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
 
 u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
+	struct x86_perf_regs *perf_regs;
+
+	if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+		perf_regs = container_of(regs, struct x86_perf_regs, regs);
+		if (!perf_regs->xmm_regs)
+			return 0;
+		return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+	}
+
 	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
 		return 0;
 
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
-
 #ifdef CONFIG_X86_32
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
+		       (1ULL << PERF_REG_X86_R9) | \
+		       (1ULL << PERF_REG_X86_R10) | \
+		       (1ULL << PERF_REG_X86_R11) | \
+		       (1ULL << PERF_REG_X86_R12) | \
+		       (1ULL << PERF_REG_X86_R13) | \
+		       (1ULL << PERF_REG_X86_R14) | \
+		       (1ULL << PERF_REG_X86_R15))
+
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || mask & REG_RESERVED)
+	if (!mask || (mask & REG_NOSUPPORT))
 		return -EINVAL;
 
 	return 0;
@@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || mask & REG_RESERVED)
-		return -EINVAL;
-
-	if (mask & REG_NOSUPPORT)
+	if (!mask || (mask & REG_NOSUPPORT))
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 957eae13b370..d1d312d012a6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -236,7 +236,7 @@ static int get_cpuid_mode(void)
 
 static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
 {
-	if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+	if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
 		return -ENODEV;
 
 	if (cpuid_enabled)
@@ -670,7 +670,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
-	if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
+	if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))
 		return 0;
 
 	return 1;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e471d8e6f0b2..70933193878c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct task_struct *tsk;
 	int err;
 
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6a62f4af9fcf..844a28b29967 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -392,6 +392,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
+
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 8fd3cedd9acc..09d6bded3c1e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -121,7 +121,7 @@ void __noreturn machine_real_restart(unsigned int type)
 	write_cr3(real_mode_header->trampoline_pgd);
 
 	/* Exiting long mode will fail if CR4.PCIDE is set. */
-	if (static_cpu_has(X86_FEATURE_PCID))
+	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3d872a527cd9..905dae880563 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -71,6 +71,7 @@
 #include <linux/tboot.h>
 #include <linux/jiffies.h>
 #include <linux/mem_encrypt.h>
+#include <linux/sizes.h>
 
 #include <linux/usb/xhci-dbgp.h>
 #include <video/edid.h>
@@ -448,18 +449,17 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 #ifdef CONFIG_KEXEC_CORE
 
 /* 16M alignment for crash kernel regions */
-#define CRASH_ALIGN		(16 << 20)
+#define CRASH_ALIGN		SZ_16M
 
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
- * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_ADDR_LOW_MAX	(512 << 20)
-# define CRASH_ADDR_HIGH_MAX	(512 << 20)
+# define CRASH_ADDR_LOW_MAX	SZ_512M
+# define CRASH_ADDR_HIGH_MAX	SZ_512M
 #else
-# define CRASH_ADDR_LOW_MAX	(896UL << 20)
+# define CRASH_ADDR_LOW_MAX	SZ_4G
 # define CRASH_ADDR_HIGH_MAX	MAXMEM
 #endif
 
@@ -541,21 +541,27 @@ static void __init reserve_crashkernel(void)
 	}
 
 	/* 0 means: find the address automatically */
-	if (crash_base <= 0) {
+	if (!crash_base) {
 		/*
 		 * Set CRASH_ADDR_LOW_MAX upper bound for crash memory,
-		 * as old kexec-tools loads bzImage below that, unless
-		 * "crashkernel=size[KMG],high" is specified.
+		 * crashkernel=x,high reserves memory over 4G, also allocates
+		 * 256M extra low memory for DMA buffers and swiotlb.
+		 * But the extra memory is not required for all machines.
+		 * So try low memory first and fall back to high memory
+		 * unless "crashkernel=size[KMG],high" is specified.
 		 */
-		crash_base = memblock_find_in_range(CRASH_ALIGN,
-						    high ? CRASH_ADDR_HIGH_MAX
-							 : CRASH_ADDR_LOW_MAX,
-						    crash_size, CRASH_ALIGN);
+		if (!high)
+			crash_base = memblock_find_in_range(CRASH_ALIGN,
+						CRASH_ADDR_LOW_MAX,
+						crash_size, CRASH_ALIGN);
+		if (!crash_base)
+			crash_base = memblock_find_in_range(CRASH_ALIGN,
+						CRASH_ADDR_HIGH_MAX,
+						crash_size, CRASH_ALIGN);
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
-
 	} else {
 		unsigned long long start;
 
@@ -1005,13 +1011,11 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
-	dmi_scan_machine();
-	dmi_memdev_walk();
-	dmi_set_dump_stack_arch_desc();
+	dmi_setup();
 
 	/*
 	 * VMware detection requires dmi to be available, so this
-	 * needs to be done after dmi_scan_machine(), for the boot CPU.
+	 * needs to be done after dmi_setup(), for the boot CPU.
 	 */
 	init_hypervisor_platform();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 4bf46575568a..86663874ef04 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -244,11 +244,6 @@ void __init setup_per_cpu_areas(void)
 		per_cpu(x86_cpu_to_logical_apicid, cpu) =
 			early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
 #endif
-#ifdef CONFIG_X86_64
-		per_cpu(irq_stack_ptr, cpu) =
-			per_cpu(irq_stack_union.irq_stack, cpu) +
-			IRQ_STACK_SIZE;
-#endif
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 08dfd4c1a4f9..dff90fb6a9af 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -132,16 +132,6 @@ static int restore_sigcontext(struct pt_regs *regs,
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
 
-#ifdef CONFIG_X86_64
-		/*
-		 * Fix up SS if needed for the benefit of old DOSEMU and
-		 * CRIU.
-		 */
-		if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
-			     user_64bit_mode(regs)))
-			force_valid_ss(regs);
-#endif
-
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
 		regs->orig_ax = -1;		/* disable syscall checks */
@@ -150,6 +140,15 @@ static int restore_sigcontext(struct pt_regs *regs,
 		buf = (void __user *)buf_val;
 	} get_user_catch(err);
 
+#ifdef CONFIG_X86_64
+	/*
+	 * Fix up SS if needed for the benefit of old DOSEMU and
+	 * CRIU.
+	 */
+	if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
+		force_valid_ss(regs);
+#endif
+
 	err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
 
 	force_iret();
@@ -461,6 +460,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 {
 	struct rt_sigframe __user *frame;
 	void __user *fp = NULL;
+	unsigned long uc_flags;
 	int err = 0;
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
@@ -473,9 +473,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 			return -EFAULT;
 	}
 
+	uc_flags = frame_uc_flags(regs);
+
 	put_user_try {
 		/* Create the ucontext.  */
-		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+		put_user_ex(uc_flags, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
@@ -541,6 +543,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 {
 #ifdef CONFIG_X86_X32_ABI
 	struct rt_sigframe_x32 __user *frame;
+	unsigned long uc_flags;
 	void __user *restorer;
 	int err = 0;
 	void __user *fpstate = NULL;
@@ -555,9 +558,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 			return -EFAULT;
 	}
 
+	uc_flags = frame_uc_flags(regs);
+
 	put_user_try {
 		/* Create the ucontext.  */
-		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+		put_user_ex(uc_flags, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
@@ -688,10 +693,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *set = sigmask_to_save();
 	compat_sigset_t *cset = (compat_sigset_t *) set;
 
-	/*
-	 * Increment event counter and perform fixup for the pre-signal
-	 * frame.
-	 */
+	/* Perform fixup for the pre-signal frame. */
 	rseq_signal_deliver(ksig, regs);
 
 	/* Set up the stack frame */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ce1a67b70168..73e69aaaa117 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -455,7 +455,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  * multicore group inside a NUMA node.  If this happens, we will
  * discard the MC level of the topology later.
  */
-static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
 	if (c->phys_proc_id == o->phys_proc_id)
 		return true;
@@ -546,7 +546,7 @@ void set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_mp && match_die(c, o))) {
+		if ((i == cpu) || (has_mp && match_pkg(c, o))) {
 			link_mask(topology_core_cpumask, cpu, i);
 
 			/*
@@ -570,7 +570,7 @@ void set_cpu_sibling_map(int cpu)
 			} else if (i != cpu && !c->booted_cores)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
-		if (match_die(c, o) && !topology_same_node(c, o))
+		if (match_pkg(c, o) && !topology_same_node(c, o))
 			x86_has_numa_in_package = true;
 	}
 
@@ -935,20 +935,27 @@ out:
 	return boot_error;
 }
 
-void common_cpu_up(unsigned int cpu, struct task_struct *idle)
+int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
+	int ret;
+
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
 	per_cpu(current_task, cpu) = idle;
 
+	/* Initialize the interrupt stack(s) */
+	ret = irq_init_percpu_irqstack(cpu);
+	if (ret)
+		return ret;
+
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	irq_ctx_init(cpu);
 	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #else
 	initial_gs = per_cpu_offset(cpu);
 #endif
+	return 0;
 }
 
 /*
@@ -1106,7 +1113,9 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	/* the FPU context is blank, nobody can own it */
 	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
-	common_cpu_up(cpu, tidle);
+	err = common_cpu_up(cpu, tidle);
+	if (err)
+		return err;
 
 	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 5c2d71a1dc06..2abf27d7df6b 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -12,78 +12,31 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
-static int save_stack_address(struct stack_trace *trace, unsigned long addr,
-			      bool nosched)
-{
-	if (nosched && in_sched_functions(addr))
-		return 0;
-
-	if (trace->skip > 0) {
-		trace->skip--;
-		return 0;
-	}
-
-	if (trace->nr_entries >= trace->max_entries)
-		return -1;
-
-	trace->entries[trace->nr_entries++] = addr;
-	return 0;
-}
-
-static void noinline __save_stack_trace(struct stack_trace *trace,
-			       struct task_struct *task, struct pt_regs *regs,
-			       bool nosched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs)
 {
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (regs)
-		save_stack_address(trace, regs->ip, nosched);
+	if (regs && !consume_entry(cookie, regs->ip, false))
+		return;
 
 	for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
-		if (!addr || save_stack_address(trace, addr, nosched))
+		if (!addr || !consume_entry(cookie, addr, false))
 			break;
 	}
-
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 /*
- * Save stack-backtrace addresses into a stack_trace buffer.
+ * This function returns an error if it detects any unreliable features of the
+ * stack.  Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
  */
-void save_stack_trace(struct stack_trace *trace)
-{
-	trace->skip++;
-	__save_stack_trace(trace, current, NULL, false);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
-	__save_stack_trace(trace, current, regs, false);
-}
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
-	if (!try_get_task_stack(tsk))
-		return;
-
-	if (tsk == current)
-		trace->skip++;
-	__save_stack_trace(trace, tsk, NULL, true);
-
-	put_task_stack(tsk);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
-
-static int __always_inline
-__save_stack_trace_reliable(struct stack_trace *trace,
-			    struct task_struct *task)
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+			     void *cookie, struct task_struct *task)
 {
 	struct unwind_state state;
 	struct pt_regs *regs;
@@ -97,7 +50,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		if (regs) {
 			/* Success path for user tasks */
 			if (user_mode(regs))
-				goto success;
+				return 0;
 
 			/*
 			 * Kernel mode registers on the stack indicate an
@@ -120,7 +73,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		if (!addr)
 			return -EINVAL;
 
-		if (save_stack_address(trace, addr, false))
+		if (!consume_entry(cookie, addr, false))
 			return -EINVAL;
 	}
 
@@ -132,39 +85,9 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
 		return -EINVAL;
 
-success:
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
-
 	return 0;
 }
 
-/*
- * This function returns an error if it detects any unreliable features of the
- * stack.  Otherwise it guarantees that the stack trace is reliable.
- *
- * If the task is not 'current', the caller *must* ensure the task is inactive.
- */
-int save_stack_trace_tsk_reliable(struct task_struct *tsk,
-				  struct stack_trace *trace)
-{
-	int ret;
-
-	/*
-	 * If the task doesn't have a stack (e.g., a zombie), the stack is
-	 * "reliably" empty.
-	 */
-	if (!try_get_task_stack(tsk))
-		return 0;
-
-	ret = __save_stack_trace_reliable(trace, tsk);
-
-	put_task_stack(tsk);
-
-	return ret;
-}
-#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
-
 /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
 
 struct stack_frame_user {
@@ -189,15 +112,15 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 	return ret;
 }
 
-static inline void __save_stack_trace_user(struct stack_trace *trace)
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+			  const struct pt_regs *regs)
 {
-	const struct pt_regs *regs = task_pt_regs(current);
 	const void __user *fp = (const void __user *)regs->bp;
 
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = regs->ip;
+	if (!consume_entry(cookie, regs->ip, false))
+		return;
 
-	while (trace->nr_entries < trace->max_entries) {
+	while (1) {
 		struct stack_frame_user frame;
 
 		frame.next_fp = NULL;
@@ -207,8 +130,8 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
 		if ((unsigned long)fp < regs->sp)
 			break;
 		if (frame.ret_addr) {
-			trace->entries[trace->nr_entries++] =
-				frame.ret_addr;
+			if (!consume_entry(cookie, frame.ret_addr, false))
+				return;
 		}
 		if (fp == frame.next_fp)
 			break;
@@ -216,14 +139,3 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
 	}
 }
 
-void save_stack_trace_user(struct stack_trace *trace)
-{
-	/*
-	 * Trace user stack if we are not a kernel thread
-	 */
-	if (current->mm) {
-		__save_stack_trace_user(trace);
-	}
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 738bf42b0218..be5bc2e47c71 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -71,7 +71,7 @@ int _debug_hotplug_cpu(int cpu, int action)
 	case 0:
 		ret = cpu_down(cpu);
 		if (!ret) {
-			pr_info("CPU %u is now offline\n", cpu);
+			pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu);
 			dev->offline = true;
 			kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
 		} else
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cc6df5c6d7b3..15b5e98a86f9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -282,6 +282,7 @@ int __init notsc_setup(char *str)
 __setup("notsc", notsc_setup);
 
 static int no_sched_irq_time;
+static int no_tsc_watchdog;
 
 static int __init tsc_setup(char *str)
 {
@@ -291,6 +292,8 @@ static int __init tsc_setup(char *str)
 		no_sched_irq_time = 1;
 	if (!strcmp(str, "unstable"))
 		mark_tsc_unstable("boot parameter");
+	if (!strcmp(str, "nowatchdog"))
+		no_tsc_watchdog = 1;
 	return 1;
 }
 
@@ -1348,7 +1351,7 @@ static int __init init_tsc_clocksource(void)
 	if (tsc_unstable)
 		goto unreg;
 
-	if (tsc_clocksource_reliable)
+	if (tsc_clocksource_reliable || no_tsc_watchdog)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index a092b6b40c6b..6a38717d179c 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -369,7 +369,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	preempt_disable();
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has(X86_FEATURE_SEP)) {
+	if (boot_cpu_has(X86_FEATURE_SEP)) {
 		tsk->thread.sysenter_cs = 0;
 		refresh_sysenter_cs(&tsk->thread);
 	}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a5127b2c195f..0850b5149345 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -141,11 +141,11 @@ SECTIONS
 		*(.text.__x86.indirect_thunk)
 		__indirect_thunk_end = .;
 #endif
-
-		/* End of text section */
-		_etext = .;
 	} :text = 0x9090
 
+	/* End of text section */
+	_etext = .;
+
 	NOTES :text :note
 
 	EXCEPTION_TABLE(16) :text = 0x9090
@@ -403,7 +403,8 @@ SECTIONS
  */
 #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
 INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
+INIT_PER_CPU(fixed_percpu_data);
+INIT_PER_CPU(irq_stack_backing_store);
 
 /*
  * Build-time check on the image size:
@@ -412,8 +413,8 @@ INIT_PER_CPU(irq_stack_union);
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-. = ASSERT((irq_stack_union == 0),
-           "irq_stack_union is not at start of per-cpu area");
+. = ASSERT((fixed_percpu_data == 0),
+           "fixed_percpu_data is not at start of per-cpu area");
 #endif
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 421899f6ad7b..cc24b3a32c44 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1371,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 
 		valid_bank_mask = BIT_ULL(0);
 		sparse_banks[0] = flush.processor_mask;
-		all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+		/*
+		 * Work around possible WS2012 bug: it sends hypercalls
+		 * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+		 * while also expecting us to flush something and crashing if
+		 * we don't. Let's treat processor_mask == 0 same as
+		 * HV_FLUSH_ALL_PROCESSORS.
+		 */
+		all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+			flush.processor_mask == 0;
 	} else {
 		if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
 					    sizeof(flush_ex))))
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9bf70cf84564..bd13fdddbdc4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,7 +70,6 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
-static bool lapic_timer_advance_adjust_done = false;
 #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
@@ -1482,14 +1481,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
 	return false;
 }
 
+static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
+{
+	u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+
+	/*
+	 * If the guest TSC is running at a different ratio than the host, then
+	 * convert the delay to nanoseconds to achieve an accurate delay.  Note
+	 * that __delay() uses delay_tsc whenever the hardware has TSC, thus
+	 * always for VMX enabled hardware.
+	 */
+	if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+		__delay(min(guest_cycles,
+			nsec_to_cycles(vcpu, timer_advance_ns)));
+	} else {
+		u64 delay_ns = guest_cycles * 1000000ULL;
+		do_div(delay_ns, vcpu->arch.virtual_tsc_khz);
+		ndelay(min_t(u32, delay_ns, timer_advance_ns));
+	}
+}
+
 void wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
 	u64 guest_tsc, tsc_deadline, ns;
 
-	if (!lapic_in_kernel(vcpu))
-		return;
-
 	if (apic->lapic_timer.expired_tscdeadline == 0)
 		return;
 
@@ -1501,33 +1518,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
 
-	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
 	if (guest_tsc < tsc_deadline)
-		__delay(min(tsc_deadline - guest_tsc,
-			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
 
-	if (!lapic_timer_advance_adjust_done) {
+	if (!apic->lapic_timer.timer_advance_adjust_done) {
 		/* too early */
 		if (guest_tsc < tsc_deadline) {
 			ns = (tsc_deadline - guest_tsc) * 1000000ULL;
 			do_div(ns, vcpu->arch.virtual_tsc_khz);
-			lapic_timer_advance_ns -= min((unsigned int)ns,
-				lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+			timer_advance_ns -= min((u32)ns,
+				timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
 		} else {
 		/* too late */
 			ns = (guest_tsc - tsc_deadline) * 1000000ULL;
 			do_div(ns, vcpu->arch.virtual_tsc_khz);
-			lapic_timer_advance_ns += min((unsigned int)ns,
-				lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+			timer_advance_ns += min((u32)ns,
+				timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
 		}
 		if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
-			lapic_timer_advance_adjust_done = true;
+			apic->lapic_timer.timer_advance_adjust_done = true;
+		if (unlikely(timer_advance_ns > 5000)) {
+			timer_advance_ns = 0;
+			apic->lapic_timer.timer_advance_adjust_done = true;
+		}
+		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
 	}
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
 {
-	u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+	u64 guest_tsc, tscdeadline = ktimer->tscdeadline;
 	u64 ns = 0;
 	ktime_t expire;
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1542,13 +1563,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 
 	now = ktime_get();
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-	if (likely(tscdeadline > guest_tsc)) {
-		ns = (tscdeadline - guest_tsc) * 1000000ULL;
-		do_div(ns, this_tsc_khz);
+
+	ns = (tscdeadline - guest_tsc) * 1000000ULL;
+	do_div(ns, this_tsc_khz);
+
+	if (likely(tscdeadline > guest_tsc) &&
+	    likely(ns > apic->lapic_timer.timer_advance_ns)) {
 		expire = ktime_add_ns(now, ns);
-		expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
-		hrtimer_start(&apic->lapic_timer.timer,
-				expire, HRTIMER_MODE_ABS_PINNED);
+		expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
+		hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED);
 	} else
 		apic_timer_expired(apic);
 
@@ -2255,7 +2278,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu)
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 {
 	struct kvm_lapic *apic;
 
@@ -2279,6 +2302,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS_PINNED);
 	apic->lapic_timer.timer.function = apic_timer_fn;
+	if (timer_advance_ns == -1) {
+		apic->lapic_timer.timer_advance_ns = 1000;
+		apic->lapic_timer.timer_advance_adjust_done = false;
+	} else {
+		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+		apic->lapic_timer.timer_advance_adjust_done = true;
+	}
+
 
 	/*
 	 * APIC is created enabled. This will prevent kvm_lapic_set_base from
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index ff6ef9c3d760..d6d049ba3045 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -31,8 +31,10 @@ struct kvm_timer {
 	u32 timer_mode_mask;
 	u64 tscdeadline;
 	u64 expired_tscdeadline;
+	u32 timer_advance_ns;
 	atomic_t pending;			/* accumulated triggered timers */
 	bool hv_timer_in_use;
+	bool timer_advance_adjust_done;
 };
 
 struct kvm_lapic {
@@ -62,7 +64,7 @@ struct kvm_lapic {
 
 struct dest_map;
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu);
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e10962dfc203..d9c7b45d231f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4781,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
 	union kvm_mmu_extended_role ext = {0};
 
 	ext.cr0_pg = !!is_paging(vcpu);
+	ext.cr4_pae = !!is_pae(vcpu);
 	ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
 	ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	ext.cr4_pse = !!is_pse(vcpu);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 6401eb7ef19c..0c601d079cd2 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5423,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		return ret;
 
 	/* Empty 'VMXON' state is permitted */
-	if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
 		return 0;
 
 	if (kvm_state->vmx.vmcs_pa != -1ull) {
@@ -5467,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	    vmcs12->vmcs_link_pointer != -1ull) {
 		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
 
-		if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12))
+		if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
 			return -EINVAL;
 
 		if (copy_from_user(shadow_vmcs12,
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 7b272738c576..d4cb1945b2e3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -3,6 +3,7 @@
 #include <asm/asm.h>
 #include <asm/bitsperlong.h>
 #include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
 
 #define WORD_SIZE (BITS_PER_LONG / 8)
 
@@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter)
  * referred to by VMCS.HOST_RIP.
  */
 ENTRY(vmx_vmexit)
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
+	/* Preserve guest's RAX, it's used to stuff the RSB. */
+	push %_ASM_AX
+
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+
+	pop %_ASM_AX
+.Lvmexit_skip_rsb:
+#endif
 	ret
 ENDPROC(vmx_vmexit)
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b4e7d645275a..0c955bb286ff 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6462,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
 
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs))
 		current_evmcs->hv_clean_fields |=
@@ -7032,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
 	struct vcpu_vmx *vmx;
 	u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
+	struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer;
 
 	if (kvm_mwait_in_guest(vcpu->kvm))
 		return -EOPNOTSUPP;
@@ -7040,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 	tscl = rdtsc();
 	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
 	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
-	lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+	lapic_timer_advance_cycles = nsec_to_cycles(vcpu,
+						    ktimer->timer_advance_ns);
 
 	if (delta_tsc > lapic_timer_advance_cycles)
 		delta_tsc -= lapic_timer_advance_cycles;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a0d1fc80ac5a..b5edc8e3ce1d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 1000;
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns.  '0' disables
+ * advancement entirely.  Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -6535,6 +6539,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+	return 1;
+}
+
 static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pio.count = 0;
@@ -6551,12 +6561,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
 					    size, port, &val, 1);
+	if (ret)
+		return ret;
 
-	if (!ret) {
+	/*
+	 * Workaround userspace that relies on old KVM behavior of %rip being
+	 * incremented prior to exiting to userspace to handle "OUT 0x7e".
+	 */
+	if (port == 0x7e &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+		vcpu->arch.complete_userspace_io =
+			complete_fast_pio_out_port_0x7e;
+		kvm_skip_emulated_instruction(vcpu);
+	} else {
 		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
 		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
 	}
-	return ret;
+	return 0;
 }
 
 static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
@@ -7873,7 +7894,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	if (lapic_timer_advance_ns)
+	if (lapic_in_kernel(vcpu) &&
+	    vcpu->arch.apic->lapic_timer.timer_advance_ns)
 		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
@@ -9061,7 +9083,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
 		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
-		r = kvm_create_lapic(vcpu);
+		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
 	} else
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index aedc5d0d4989..534d3f28bb01 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void);
 
 extern unsigned int min_timer_period_us;
 
-extern unsigned int lapic_timer_advance_ns;
-
 extern bool enable_vmware_backdoor;
 
 extern struct static_key kvm_no_apic_vcpu;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 140e61843a07..5246db42de45 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -6,6 +6,18 @@
 # Produces uninteresting flaky coverage.
 KCOV_INSTRUMENT_delay.o	:= n
 
+# Early boot use of cmdline; don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KCOV_INSTRUMENT_cmdline.o := n
+KASAN_SANITIZE_cmdline.o  := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_cmdline.o = -pg
+endif
+
+CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector)
+endif
+
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
 quiet_cmd_inat_tables = GEN     $@
@@ -23,7 +35,6 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 lib-y := delay.o misc.o cmdline.o cpu.o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index db4e5aa0858b..b2f1822084ae 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -16,6 +16,30 @@
 #include <asm/smap.h>
 #include <asm/export.h>
 
+.macro ALIGN_DESTINATION
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE_UA(100b, 103b)
+	_ASM_EXTABLE_UA(101b, 103b)
+	.endm
+
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
  * This version is for CPUs like P4 that don't have efficient micro
@@ -194,6 +218,30 @@ ENDPROC(copy_user_enhanced_fast_string)
 EXPORT_SYMBOL(copy_user_enhanced_fast_string)
 
 /*
+ * Try to copy last bytes and clear the rest if needed.
+ * Since protection fault in copy_from/to_user is not a normal situation,
+ * it is not necessary to optimize tail handling.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ALIGN;
+copy_user_handle_tail:
+	movl %edx,%ecx
+1:	rep movsb
+2:	mov %ecx,%eax
+	ASM_CLAC
+	ret
+
+	_ASM_EXTABLE_UA(1b, 2b)
+ENDPROC(copy_user_handle_tail)
+
+/*
  * copy_user_nocache - Uncached memory copy with exception handling
  * This will force destination out of cache for more performance.
  *
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index f5b7f1b3b6d7..b7375dc6898f 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -162,7 +162,7 @@ void __delay(unsigned long loops)
 }
 EXPORT_SYMBOL(__delay);
 
-void __const_udelay(unsigned long xloops)
+noinline void __const_udelay(unsigned long xloops)
 {
 	unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
 	int d0;
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
index 3cdf06128d13..be5b5fb1598b 100644
--- a/arch/x86/lib/error-inject.c
+++ b/arch/x86/lib/error-inject.c
@@ -6,6 +6,7 @@
 asmlinkage void just_return_func(void);
 
 asm(
+	".text\n"
 	".type just_return_func, @function\n"
 	".globl just_return_func\n"
 	"just_return_func:\n"
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 3b24dc05251c..9d05572370ed 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe)
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorl %eax, %eax
+.L_done:
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
@@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 	addl	%edx, %ecx
 .E_trailing_bytes:
 	mov	%ecx, %eax
-	ret
+	jmp	.L_done
 
 	/*
 	 * For write fault handling, given the destination is unaligned,
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
deleted file mode 100644
index dc2ab6ea6768..000000000000
--- a/arch/x86/lib/rwsem.S
+++ /dev/null
@@ -1,156 +0,0 @@
-/*
- * x86 semaphore implementation.
- *
- * (C) Copyright 1999 Linus Torvalds
- *
- * Portions Copyright 1999 Red Hat, Inc.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
- */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-
-#define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
-#define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
-
-#ifdef CONFIG_X86_32
-
-/*
- * The semaphore operations have a special calling sequence that
- * allow us to do a simpler in-line version of them. These routines
- * need to convert that sequence back into the C sequence when
- * there is contention on the semaphore.
- *
- * %eax contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax which is either a return
- * value or just gets clobbered. Same is true for %edx so make sure GCC
- * reloads it after the slow path, by making it hold a temporary, for
- * example see ____down_write().
- */
-
-#define save_common_regs \
-	pushl %ecx
-
-#define restore_common_regs \
-	popl %ecx
-
-	/* Avoid uglifying the argument copying x86-64 needs to do. */
-	.macro movq src, dst
-	.endm
-
-#else
-
-/*
- * x86-64 rwsem wrappers
- *
- * This interfaces the inline asm code to the slow-path
- * C routines. We need to save the call-clobbered regs
- * that the asm does not mark as clobbered, and move the
- * argument from %rax to %rdi.
- *
- * NOTE! We don't need to save %rax, because the functions
- * will always return the semaphore pointer in %rax (which
- * is also the input argument to these helpers)
- *
- * The following can clobber %rdx because the asm clobbers it:
- *   call_rwsem_down_write_failed
- *   call_rwsem_wake
- * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
- */
-
-#define save_common_regs \
-	pushq %rdi; \
-	pushq %rsi; \
-	pushq %rcx; \
-	pushq %r8;  \
-	pushq %r9;  \
-	pushq %r10; \
-	pushq %r11
-
-#define restore_common_regs \
-	popq %r11; \
-	popq %r10; \
-	popq %r9; \
-	popq %r8; \
-	popq %rcx; \
-	popq %rsi; \
-	popq %rdi
-
-#endif
-
-/* Fix up special calling conventions */
-ENTRY(call_rwsem_down_read_failed)
-	FRAME_BEGIN
-	save_common_regs
-	__ASM_SIZE(push,) %__ASM_REG(dx)
-	movq %rax,%rdi
-	call rwsem_down_read_failed
-	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_read_failed)
-
-ENTRY(call_rwsem_down_read_failed_killable)
-	FRAME_BEGIN
-	save_common_regs
-	__ASM_SIZE(push,) %__ASM_REG(dx)
-	movq %rax,%rdi
-	call rwsem_down_read_failed_killable
-	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_read_failed_killable)
-
-ENTRY(call_rwsem_down_write_failed)
-	FRAME_BEGIN
-	save_common_regs
-	movq %rax,%rdi
-	call rwsem_down_write_failed
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_write_failed)
-
-ENTRY(call_rwsem_down_write_failed_killable)
-	FRAME_BEGIN
-	save_common_regs
-	movq %rax,%rdi
-	call rwsem_down_write_failed_killable
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_write_failed_killable)
-
-ENTRY(call_rwsem_wake)
-	FRAME_BEGIN
-	/* do nothing if still outstanding active readers */
-	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
-	jnz 1f
-	save_common_regs
-	movq %rax,%rdi
-	call rwsem_wake
-	restore_common_regs
-1:	FRAME_END
-	ret
-ENDPROC(call_rwsem_wake)
-
-ENTRY(call_rwsem_downgrade_wake)
-	FRAME_BEGIN
-	save_common_regs
-	__ASM_SIZE(push,) %__ASM_REG(dx)
-	movq %rax,%rdi
-	call rwsem_downgrade_wake
-	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index ee42bb0cbeb3..9952a01cad24 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -55,26 +55,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 EXPORT_SYMBOL(clear_user);
 
 /*
- * Try to copy last bytes and clear the rest if needed.
- * Since protection fault in copy_from/to_user is not a normal situation,
- * it is not necessary to optimize tail handling.
- */
-__visible unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++) {
-		char c;
-
-		if (__get_user_nocheck(c, from++, sizeof(char)))
-			break;
-		if (__put_user_nocheck(c, to, sizeof(char)))
-			break;
-	}
-	clac();
-	return len;
-}
-
-/*
  * Similar to copy_user_handle_tail, probe for the write fault point,
  * but reuse __memcpy_mcsafe in case a new read error is encountered.
  * clac() is handled in _copy_to_iter_mcsafe().
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 19c6abf9ea31..752ad11d6868 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -13,8 +13,8 @@
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
 
 #ifdef CONFIG_X86_64
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
+DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
 #endif
 
 struct cpu_entry_area *get_cpu_entry_area(int cpu)
@@ -52,10 +52,10 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
 		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
 }
 
-static void __init percpu_setup_debug_store(int cpu)
+static void __init percpu_setup_debug_store(unsigned int cpu)
 {
 #ifdef CONFIG_CPU_SUP_INTEL
-	int npages;
+	unsigned int npages;
 	void *cea;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
@@ -78,9 +78,43 @@ static void __init percpu_setup_debug_store(int cpu)
 #endif
 }
 
+#ifdef CONFIG_X86_64
+
+#define cea_map_stack(name) do {					\
+	npages = sizeof(estacks->name## _stack) / PAGE_SIZE;		\
+	cea_map_percpu_pages(cea->estacks.name## _stack,		\
+			estacks->name## _stack, npages, PAGE_KERNEL);	\
+	} while (0)
+
+static void __init percpu_setup_exception_stacks(unsigned int cpu)
+{
+	struct exception_stacks *estacks = per_cpu_ptr(&exception_stacks, cpu);
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+	unsigned int npages;
+
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+
+	per_cpu(cea_exception_stacks, cpu) = &cea->estacks;
+
+	/*
+	 * The exceptions stack mappings in the per cpu area are protected
+	 * by guard pages so each stack must be mapped separately. DB2 is
+	 * not mapped; it just exists to catch triple nesting of #DB.
+	 */
+	cea_map_stack(DF);
+	cea_map_stack(NMI);
+	cea_map_stack(DB1);
+	cea_map_stack(DB);
+	cea_map_stack(MCE);
+}
+#else
+static inline void percpu_setup_exception_stacks(unsigned int cpu) {}
+#endif
+
 /* Setup the fixmap mappings only once per-processor */
-static void __init setup_cpu_entry_area(int cpu)
+static void __init setup_cpu_entry_area(unsigned int cpu)
 {
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
 #ifdef CONFIG_X86_64
 	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
 	pgprot_t gdt_prot = PAGE_KERNEL_RO;
@@ -101,10 +135,9 @@ static void __init setup_cpu_entry_area(int cpu)
 	pgprot_t tss_prot = PAGE_KERNEL;
 #endif
 
-	cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
-		    gdt_prot);
+	cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot);
 
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+	cea_map_percpu_pages(&cea->entry_stack_page,
 			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
 			     PAGE_KERNEL);
 
@@ -128,22 +161,15 @@ static void __init setup_cpu_entry_area(int cpu)
 	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
 		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
 	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
-			     &per_cpu(cpu_tss_rw, cpu),
+	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
 			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
 
 #ifdef CONFIG_X86_32
-	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
+	per_cpu(cpu_entry_area, cpu) = cea;
 #endif
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
-	BUILD_BUG_ON(sizeof(exception_stacks) !=
-		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
-			     &per_cpu(exception_stacks, cpu),
-			     sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
-#endif
+	percpu_setup_exception_stacks(cpu);
+
 	percpu_setup_debug_store(cpu);
 }
 
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index c0309ea9abee..6a7302d1161f 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -578,7 +578,7 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-	if (user && static_cpu_has(X86_FEATURE_PTI))
+	if (user && boot_cpu_has(X86_FEATURE_PTI))
 		pgd = kernel_to_user_pgdp(pgd);
 #endif
 	ptdump_walk_pgd_level_core(m, pgd, false, false);
@@ -591,7 +591,7 @@ void ptdump_walk_user_pgd_level_checkwx(void)
 	pgd_t *pgd = INIT_PGD;
 
 	if (!(__supported_pte_mask & _PAGE_NX) ||
-	    !static_cpu_has(X86_FEATURE_PTI))
+	    !boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("x86/mm: Checking user space page tables\n");
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 667f1da36208..46df4c6aae46 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -28,6 +28,7 @@
 #include <asm/mmu_context.h>		/* vma_pkey()			*/
 #include <asm/efi.h>			/* efi_recover_from_page_fault()*/
 #include <asm/desc.h>			/* store_idt(), ...		*/
+#include <asm/cpu_entry_area.h>		/* exception stack		*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -359,8 +360,6 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Copy kernel mappings over when needed. This can also
 	 * happen within a race in page table update. In the later
@@ -603,24 +602,9 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		 name, index, addr, (desc.limit0 | (desc.limit1 << 16)));
 }
 
-/*
- * This helper function transforms the #PF error_code bits into
- * "[PROT] [USER]" type of descriptive, almost human-readable error strings:
- */
-static void err_str_append(unsigned long error_code, char *buf, unsigned long mask, const char *txt)
-{
-	if (error_code & mask) {
-		if (buf[0])
-			strcat(buf, " ");
-		strcat(buf, txt);
-	}
-}
-
 static void
 show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
-	char err_txt[64];
-
 	if (!oops_may_print())
 		return;
 
@@ -644,31 +628,29 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 				from_kuid(&init_user_ns, current_uid()));
 	}
 
-	pr_alert("BUG: unable to handle kernel %s at %px\n",
-		 address < PAGE_SIZE ? "NULL pointer dereference" : "paging request",
-		 (void *)address);
-
-	err_txt[0] = 0;
-
-	/*
-	 * Note: length of these appended strings including the separation space and the
-	 * zero delimiter must fit into err_txt[].
-	 */
-	err_str_append(error_code, err_txt, X86_PF_PROT,  "[PROT]" );
-	err_str_append(error_code, err_txt, X86_PF_WRITE, "[WRITE]");
-	err_str_append(error_code, err_txt, X86_PF_USER,  "[USER]" );
-	err_str_append(error_code, err_txt, X86_PF_RSVD,  "[RSVD]" );
-	err_str_append(error_code, err_txt, X86_PF_INSTR, "[INSTR]");
-	err_str_append(error_code, err_txt, X86_PF_PK,    "[PK]"   );
-
-	pr_alert("#PF error: %s\n", error_code ? err_txt : "[normal kernel read fault]");
+	if (address < PAGE_SIZE && !user_mode(regs))
+		pr_alert("BUG: kernel NULL pointer dereference, address: %px\n",
+			(void *)address);
+	else
+		pr_alert("BUG: unable to handle page fault for address: %px\n",
+			(void *)address);
+
+	pr_alert("#PF: %s %s in %s mode\n",
+		 (error_code & X86_PF_USER)  ? "user" : "supervisor",
+		 (error_code & X86_PF_INSTR) ? "instruction fetch" :
+		 (error_code & X86_PF_WRITE) ? "write access" :
+					       "read access",
+			     user_mode(regs) ? "user" : "kernel");
+	pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code,
+		 !(error_code & X86_PF_PROT) ? "not-present page" :
+		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
+		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
 		struct desc_ptr idt, gdt;
 		u16 ldtr, tr;
 
-		pr_alert("This was a system access from user code\n");
-
 		/*
 		 * This can happen for quite a few reasons.  The more obvious
 		 * ones are faults accessing the GDT, or LDT.  Perhaps
@@ -793,7 +775,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	if (is_vmalloc_addr((void *)address) &&
 	    (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
 	     address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
-		unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
+		unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
 		/*
 		 * We're likely to be running with very little stack space
 		 * left.  It's plausible that we'd hit this condition but
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 8dacdb96899e..fd10d91a6115 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -6,6 +6,7 @@
 #include <linux/swapfile.h>
 #include <linux/swapops.h>
 #include <linux/kmemleak.h>
+#include <linux/sched/task.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -23,6 +24,7 @@
 #include <asm/hypervisor.h>
 #include <asm/cpufeature.h>
 #include <asm/pti.h>
+#include <asm/text-patching.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -702,6 +704,41 @@ void __init init_mem_mapping(void)
 }
 
 /*
+ * Initialize an mm_struct to be used during poking and a pointer to be used
+ * during patching.
+ */
+void __init poking_init(void)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	poking_mm = copy_init_mm();
+	BUG_ON(!poking_mm);
+
+	/*
+	 * Randomize the poking address, but make sure that the following page
+	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
+	 * and adjust the address if the PMD ends after the first one.
+	 */
+	poking_addr = TASK_UNMAPPED_BASE;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+			(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
+
+	if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		poking_addr += PAGE_SIZE;
+
+	/*
+	 * We need to trigger the allocation of the page-tables that will be
+	 * needed for poking now. Later, poking may be performed in an atomic
+	 * section, which might cause allocation to fail.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	BUG_ON(!ptep);
+	pte_unmap_unlock(ptep, ptl);
+}
+
+/*
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.
  *
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index d669c5e797e0..dc3f058bdf9b 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -125,10 +125,7 @@ void __init kernel_randomize_memory(void)
 		 */
 		entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
 		prandom_bytes_state(&rand_state, &rand, sizeof(rand));
-		if (pgtable_l5_enabled())
-			entropy = (rand % (entropy + 1)) & P4D_MASK;
-		else
-			entropy = (rand % (entropy + 1)) & PUD_MASK;
+		entropy = (rand % (entropy + 1)) & PUD_MASK;
 		vaddr += entropy;
 		*kaslr_regions[i].base = vaddr;
 
@@ -137,84 +134,71 @@ void __init kernel_randomize_memory(void)
 		 * randomization alignment.
 		 */
 		vaddr += get_padding(&kaslr_regions[i]);
-		if (pgtable_l5_enabled())
-			vaddr = round_up(vaddr + 1, P4D_SIZE);
-		else
-			vaddr = round_up(vaddr + 1, PUD_SIZE);
+		vaddr = round_up(vaddr + 1, PUD_SIZE);
 		remain_entropy -= entropy;
 	}
 }
 
 static void __meminit init_trampoline_pud(void)
 {
-	unsigned long paddr, paddr_next;
+	pud_t *pud_page_tramp, *pud, *pud_tramp;
+	p4d_t *p4d_page_tramp, *p4d, *p4d_tramp;
+	unsigned long paddr, vaddr;
 	pgd_t *pgd;
-	pud_t *pud_page, *pud_page_tramp;
-	int i;
 
 	pud_page_tramp = alloc_low_page();
 
+	/*
+	 * There are two mappings for the low 1MB area, the direct mapping
+	 * and the 1:1 mapping for the real mode trampoline:
+	 *
+	 * Direct mapping: virt_addr = phys_addr + PAGE_OFFSET
+	 * 1:1 mapping:    virt_addr = phys_addr
+	 */
 	paddr = 0;
-	pgd = pgd_offset_k((unsigned long)__va(paddr));
-	pud_page = (pud_t *) pgd_page_vaddr(*pgd);
-
-	for (i = pud_index(paddr); i < PTRS_PER_PUD; i++, paddr = paddr_next) {
-		pud_t *pud, *pud_tramp;
-		unsigned long vaddr = (unsigned long)__va(paddr);
+	vaddr = (unsigned long)__va(paddr);
+	pgd = pgd_offset_k(vaddr);
 
-		pud_tramp = pud_page_tramp + pud_index(paddr);
-		pud = pud_page + pud_index(vaddr);
-		paddr_next = (paddr & PUD_MASK) + PUD_SIZE;
-
-		*pud_tramp = *pud;
-	}
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 
-	set_pgd(&trampoline_pgd_entry,
-		__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
-}
-
-static void __meminit init_trampoline_p4d(void)
-{
-	unsigned long paddr, paddr_next;
-	pgd_t *pgd;
-	p4d_t *p4d_page, *p4d_page_tramp;
-	int i;
+	pud_tramp = pud_page_tramp + pud_index(paddr);
+	*pud_tramp = *pud;
 
-	p4d_page_tramp = alloc_low_page();
-
-	paddr = 0;
-	pgd = pgd_offset_k((unsigned long)__va(paddr));
-	p4d_page = (p4d_t *) pgd_page_vaddr(*pgd);
-
-	for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) {
-		p4d_t *p4d, *p4d_tramp;
-		unsigned long vaddr = (unsigned long)__va(paddr);
+	if (pgtable_l5_enabled()) {
+		p4d_page_tramp = alloc_low_page();
 
 		p4d_tramp = p4d_page_tramp + p4d_index(paddr);
-		p4d = p4d_page + p4d_index(vaddr);
-		paddr_next = (paddr & P4D_MASK) + P4D_SIZE;
 
-		*p4d_tramp = *p4d;
-	}
+		set_p4d(p4d_tramp,
+			__p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
 
-	set_pgd(&trampoline_pgd_entry,
-		__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+		set_pgd(&trampoline_pgd_entry,
+			__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+	} else {
+		set_pgd(&trampoline_pgd_entry,
+			__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
+	}
 }
 
 /*
- * Create PGD aligned trampoline table to allow real mode initialization
- * of additional CPUs. Consume only 1 low memory page.
+ * The real mode trampoline, which is required for bootstrapping CPUs
+ * occupies only a small area under the low 1MB.  See reserve_real_mode()
+ * for details.
+ *
+ * If KASLR is disabled the first PGD entry of the direct mapping is copied
+ * to map the real mode trampoline.
+ *
+ * If KASLR is enabled, copy only the PUD which covers the low 1MB
+ * area. This limits the randomization granularity to 1GB for both 4-level
+ * and 5-level paging.
  */
 void __meminit init_trampoline(void)
 {
-
 	if (!kaslr_memory_enabled()) {
 		init_trampoline_default();
 		return;
 	}
 
-	if (pgtable_l5_enabled())
-		init_trampoline_p4d();
-	else
-		init_trampoline_pud();
+	init_trampoline_pud();
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 4c570612e24e..daf4d645e537 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -2209,8 +2209,6 @@ int set_pages_rw(struct page *page, int numpages)
 	return set_memory_rw(addr, numpages);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-
 static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
@@ -2249,6 +2247,16 @@ static int __set_pages_np(struct page *page, int numpages)
 	return __change_page_attr_set_clr(&cpa, 0);
 }
 
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_pages_np(page, 1);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_pages_p(page, 1);
+}
+
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
@@ -2282,7 +2290,6 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 }
 
 #ifdef CONFIG_HIBERNATION
-
 bool kernel_page_present(struct page *page)
 {
 	unsigned int level;
@@ -2294,11 +2301,8 @@ bool kernel_page_present(struct page *page)
 	pte = lookup_address((unsigned long)page_address(page), &level);
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
-
 #endif /* CONFIG_HIBERNATION */
 
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)
 {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 7bd01709a091..1f67b1e15bf6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -190,7 +190,7 @@ static void pgd_dtor(pgd_t *pgd)
  * when PTI is enabled. We need them to map the per-process LDT into the
  * user-space page-table.
  */
-#define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
+#define PREALLOCATED_USER_PMDS	 (boot_cpu_has(X86_FEATURE_PTI) ? \
 					KERNEL_PGD_PTRS : 0)
 #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
 
@@ -292,7 +292,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pgdp = kernel_to_user_pgdp(pgdp);
@@ -373,14 +373,14 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 
 static struct kmem_cache *pgd_cache;
 
-static int __init pgd_cache_init(void)
+void __init pgd_cache_init(void)
 {
 	/*
 	 * When PAE kernel is running as a Xen domain, it does not use
 	 * shared kernel pmd. And this requires a whole page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return 0;
+		return;
 
 	/*
 	 * when PAE kernel is not running as a Xen domain, it uses
@@ -390,9 +390,7 @@ static int __init pgd_cache_init(void)
 	 */
 	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
 				      SLAB_PANIC, NULL);
-	return 0;
 }
-core_initcall(pgd_cache_init);
 
 static inline pgd_t *_pgd_alloc(void)
 {
@@ -420,6 +418,10 @@ static inline void _pgd_free(pgd_t *pgd)
 }
 #else
 
+void __init pgd_cache_init(void)
+{
+}
+
 static inline pgd_t *_pgd_alloc(void)
 {
 	return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 139b28a01ce4..9c2463bc158f 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -35,6 +35,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
+#include <linux/cpu.h>
 
 #include <asm/cpufeature.h>
 #include <asm/hypervisor.h>
@@ -115,7 +116,8 @@ void __init pti_check_boottime_disable(void)
 		}
 	}
 
-	if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+	if (cmdline_find_option_bool(boot_command_line, "nopti") ||
+	    cpu_mitigations_off()) {
 		pti_mode = PTI_FORCE_OFF;
 		pti_print_if_insecure("disabled on command line.");
 		return;
@@ -626,7 +628,7 @@ static void pti_set_kernel_image_nonglobal(void)
  */
 void __init pti_init(void)
 {
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("enabled\n");
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 487b8474c01c..7f61431c75fb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -634,7 +634,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);
 }
 
-static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason)
+static void flush_tlb_func_local(const void *info, enum tlb_flush_reason reason)
 {
 	const struct flush_tlb_info *f = info;
 
@@ -722,43 +722,81 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
  */
 unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info);
+
+#ifdef CONFIG_DEBUG_VM
+static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
+#endif
+
+static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			unsigned int stride_shift, bool freed_tables,
+			u64 new_tlb_gen)
+{
+	struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);
+
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * Ensure that the following code is non-reentrant and flush_tlb_info
+	 * is not overwritten. This means no TLB flushing is initiated by
+	 * interrupt handlers and machine-check exception handlers.
+	 */
+	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
+#endif
+
+	info->start		= start;
+	info->end		= end;
+	info->mm		= mm;
+	info->stride_shift	= stride_shift;
+	info->freed_tables	= freed_tables;
+	info->new_tlb_gen	= new_tlb_gen;
+
+	return info;
+}
+
+static inline void put_flush_tlb_info(void)
+{
+#ifdef CONFIG_DEBUG_VM
+	/* Complete reentrency prevention checks */
+	barrier();
+	this_cpu_dec(flush_tlb_info_idx);
+#endif
+}
+
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned int stride_shift,
 				bool freed_tables)
 {
+	struct flush_tlb_info *info;
+	u64 new_tlb_gen;
 	int cpu;
 
-	struct flush_tlb_info info = {
-		.mm = mm,
-		.stride_shift = stride_shift,
-		.freed_tables = freed_tables,
-	};
-
 	cpu = get_cpu();
 
-	/* This is also a barrier that synchronizes with switch_mm(). */
-	info.new_tlb_gen = inc_mm_tlb_gen(mm);
-
 	/* Should we flush just the requested range? */
-	if ((end != TLB_FLUSH_ALL) &&
-	    ((end - start) >> stride_shift) <= tlb_single_page_flush_ceiling) {
-		info.start = start;
-		info.end = end;
-	} else {
-		info.start = 0UL;
-		info.end = TLB_FLUSH_ALL;
+	if ((end == TLB_FLUSH_ALL) ||
+	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
 	}
 
+	/* This is also a barrier that synchronizes with switch_mm(). */
+	new_tlb_gen = inc_mm_tlb_gen(mm);
+
+	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
+				  new_tlb_gen);
+
 	if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
-		VM_WARN_ON(irqs_disabled());
+		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN);
+		flush_tlb_func_local(info, TLB_LOCAL_MM_SHOOTDOWN);
 		local_irq_enable();
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), &info);
+		flush_tlb_others(mm_cpumask(mm), info);
 
+	put_flush_tlb_info();
 	put_cpu();
 }
 
@@ -787,38 +825,48 @@ static void do_kernel_range_flush(void *info)
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-
 	/* Balance as user space task's flush, a bit conservative */
 	if (end == TLB_FLUSH_ALL ||
 	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
 	} else {
-		struct flush_tlb_info info;
-		info.start = start;
-		info.end = end;
-		on_each_cpu(do_kernel_range_flush, &info, 1);
+		struct flush_tlb_info *info;
+
+		preempt_disable();
+		info = get_flush_tlb_info(NULL, start, end, 0, false, 0);
+
+		on_each_cpu(do_kernel_range_flush, info, 1);
+
+		put_flush_tlb_info();
+		preempt_enable();
 	}
 }
 
+/*
+ * arch_tlbbatch_flush() performs a full TLB flush regardless of the active mm.
+ * This means that the 'struct flush_tlb_info' that describes which mappings to
+ * flush is actually fixed. We therefore set a single fixed struct and use it in
+ * arch_tlbbatch_flush().
+ */
+static const struct flush_tlb_info full_flush_tlb_info = {
+	.mm = NULL,
+	.start = 0,
+	.end = TLB_FLUSH_ALL,
+};
+
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	struct flush_tlb_info info = {
-		.mm = NULL,
-		.start = 0UL,
-		.end = TLB_FLUSH_ALL,
-	};
-
 	int cpu = get_cpu();
 
 	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
-		VM_WARN_ON(irqs_disabled());
+		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN);
+		flush_tlb_func_local(&full_flush_tlb_info, TLB_LOCAL_SHOOTDOWN);
 		local_irq_enable();
 	}
 
 	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&batch->cpumask, &info);
+		flush_tlb_others(&batch->cpumask, &full_flush_tlb_info);
 
 	cpumask_clear(&batch->cpumask);
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 2c53b0f19329..1297e185b8c8 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -2133,14 +2133,19 @@ static int __init summarize_uvhub_sockets(int nuvhubs,
  */
 static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
 {
-	unsigned char *uvhub_mask;
 	struct uvhub_desc *uvhub_descs;
+	unsigned char *uvhub_mask = NULL;
 
 	if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub())
 		timeout_us = calculate_destination_timeout();
 
 	uvhub_descs = kcalloc(nuvhubs, sizeof(struct uvhub_desc), GFP_KERNEL);
+	if (!uvhub_descs)
+		goto fail;
+
 	uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
+	if (!uvhub_mask)
+		goto fail;
 
 	if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask))
 		goto fail;
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index b629f6992d9f..ce7188cbdae5 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -11,7 +11,9 @@
 #define Elf_Shdr		ElfW(Shdr)
 #define Elf_Sym			ElfW(Sym)
 
-static Elf_Ehdr ehdr;
+static Elf_Ehdr		ehdr;
+static unsigned long	shnum;
+static unsigned int	shstrndx;
 
 struct relocs {
 	uint32_t	*offset;
@@ -241,9 +243,9 @@ static const char *sec_name(unsigned shndx)
 {
 	const char *sec_strtab;
 	const char *name;
-	sec_strtab = secs[ehdr.e_shstrndx].strtab;
+	sec_strtab = secs[shstrndx].strtab;
 	name = "<noname>";
-	if (shndx < ehdr.e_shnum) {
+	if (shndx < shnum) {
 		name = sec_strtab + secs[shndx].shdr.sh_name;
 	}
 	else if (shndx == SHN_ABS) {
@@ -271,7 +273,7 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 static Elf_Sym *sym_lookup(const char *symname)
 {
 	int i;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		long nsyms;
 		char *strtab;
@@ -366,27 +368,41 @@ static void read_ehdr(FILE *fp)
 	ehdr.e_shnum     = elf_half_to_cpu(ehdr.e_shnum);
 	ehdr.e_shstrndx  = elf_half_to_cpu(ehdr.e_shstrndx);
 
-	if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) {
+	shnum = ehdr.e_shnum;
+	shstrndx = ehdr.e_shstrndx;
+
+	if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN))
 		die("Unsupported ELF header type\n");
-	}
-	if (ehdr.e_machine != ELF_MACHINE) {
+	if (ehdr.e_machine != ELF_MACHINE)
 		die("Not for %s\n", ELF_MACHINE_NAME);
-	}
-	if (ehdr.e_version != EV_CURRENT) {
+	if (ehdr.e_version != EV_CURRENT)
 		die("Unknown ELF version\n");
-	}
-	if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) {
+	if (ehdr.e_ehsize != sizeof(Elf_Ehdr))
 		die("Bad Elf header size\n");
-	}
-	if (ehdr.e_phentsize != sizeof(Elf_Phdr)) {
+	if (ehdr.e_phentsize != sizeof(Elf_Phdr))
 		die("Bad program header entry\n");
-	}
-	if (ehdr.e_shentsize != sizeof(Elf_Shdr)) {
+	if (ehdr.e_shentsize != sizeof(Elf_Shdr))
 		die("Bad section header entry\n");
+
+
+	if (shnum == SHN_UNDEF || shstrndx == SHN_XINDEX) {
+		Elf_Shdr shdr;
+
+		if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+			die("Seek to %d failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
+			die("Cannot read initial ELF section header: %s\n", strerror(errno));
+
+		if (shnum == SHN_UNDEF)
+			shnum = elf_xword_to_cpu(shdr.sh_size);
+
+		if (shstrndx == SHN_XINDEX)
+			shstrndx = elf_word_to_cpu(shdr.sh_link);
 	}
-	if (ehdr.e_shstrndx >= ehdr.e_shnum) {
+
+	if (shstrndx >= shnum)
 		die("String table index out of bounds\n");
-	}
 }
 
 static void read_shdrs(FILE *fp)
@@ -394,20 +410,20 @@ static void read_shdrs(FILE *fp)
 	int i;
 	Elf_Shdr shdr;
 
-	secs = calloc(ehdr.e_shnum, sizeof(struct section));
+	secs = calloc(shnum, sizeof(struct section));
 	if (!secs) {
 		die("Unable to allocate %d section headers\n",
-		    ehdr.e_shnum);
+		    shnum);
 	}
 	if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
 		die("Seek to %d failed: %s\n",
 			ehdr.e_shoff, strerror(errno));
 	}
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
 			die("Cannot read ELF section headers %d/%d: %s\n",
-			    i, ehdr.e_shnum, strerror(errno));
+			    i, shnum, strerror(errno));
 		sec->shdr.sh_name      = elf_word_to_cpu(shdr.sh_name);
 		sec->shdr.sh_type      = elf_word_to_cpu(shdr.sh_type);
 		sec->shdr.sh_flags     = elf_xword_to_cpu(shdr.sh_flags);
@@ -418,7 +434,7 @@ static void read_shdrs(FILE *fp)
 		sec->shdr.sh_info      = elf_word_to_cpu(shdr.sh_info);
 		sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign);
 		sec->shdr.sh_entsize   = elf_xword_to_cpu(shdr.sh_entsize);
-		if (sec->shdr.sh_link < ehdr.e_shnum)
+		if (sec->shdr.sh_link < shnum)
 			sec->link = &secs[sec->shdr.sh_link];
 	}
 
@@ -427,7 +443,7 @@ static void read_shdrs(FILE *fp)
 static void read_strtabs(FILE *fp)
 {
 	int i;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (sec->shdr.sh_type != SHT_STRTAB) {
 			continue;
@@ -452,7 +468,7 @@ static void read_strtabs(FILE *fp)
 static void read_symtabs(FILE *fp)
 {
 	int i,j;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
@@ -485,7 +501,7 @@ static void read_symtabs(FILE *fp)
 static void read_relocs(FILE *fp)
 {
 	int i,j;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (sec->shdr.sh_type != SHT_REL_TYPE) {
 			continue;
@@ -528,7 +544,7 @@ static void print_absolute_symbols(void)
 
 	printf("Absolute symbols\n");
 	printf(" Num:    Value Size  Type       Bind        Visibility  Name\n");
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		char *sym_strtab;
 		int j;
@@ -566,7 +582,7 @@ static void print_absolute_relocs(void)
 	else
 		format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32"  %s\n";
 
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		struct section *sec_applies, *sec_symtab;
 		char *sym_strtab;
@@ -650,7 +666,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 {
 	int i;
 	/* Walk through the relocations */
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		char *sym_strtab;
 		Elf_Sym *sh_symtab;
 		struct section *sec_applies, *sec_symtab;
@@ -706,7 +722,7 @@ static Elf_Addr per_cpu_load_addr;
 static void percpu_init(void)
 {
 	int i;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		ElfW(Sym) *sym;
 		if (strcmp(sec_name(i), ".data..percpu"))
 			continue;
@@ -738,7 +754,7 @@ static void percpu_init(void)
  *	__per_cpu_load
  *
  * The "gold" linker incorrectly associates:
- *	init_per_cpu__irq_stack_union
+ *	init_per_cpu__fixed_percpu_data
  *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index a9e80e44178c..a8985e1f7432 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -32,12 +32,6 @@ config ARCH_DEFCONFIG
 	default "arch/um/configs/i386_defconfig" if X86_32
 	default "arch/um/configs/x86_64_defconfig" if X86_64
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool 64BIT
-
-config RWSEM_GENERIC_SPINLOCK
-	def_bool !RWSEM_XCHGADD_ALGORITHM
-
 config 3_LEVEL_PGTABLES
 	bool "Three-level pagetables" if !64BIT
 	default 64BIT
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index 2d686ae54681..33c51c064c77 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -21,14 +21,12 @@ obj-y += checksum_32.o syscalls_32.o
 obj-$(CONFIG_ELF_CORE) += elfcore.o
 
 subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
-subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o
 
 else
 
 obj-y += syscalls_64.o vdso/
 
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
-		../lib/rwsem.o
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o
 
 endif
 
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index bf94060fc06f..0caddd6acb22 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -62,7 +62,7 @@ quiet_cmd_vdso = VDSO    $@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index a21e1734fc1f..beb44e22afdf 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2318,8 +2318,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #elif defined(CONFIG_X86_VSYSCALL_EMULATION)
 	case VSYSCALL_PAGE:
 #endif
-	case FIX_TEXT_POKE0:
-	case FIX_TEXT_POKE1:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 145506f9fdbe..590fcf863006 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -361,7 +361,9 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int rc;
 
-	common_cpu_up(cpu, idle);
+	rc = common_cpu_up(cpu, idle);
+	if (rc)
+		return rc;
 
 	xen_setup_runstate_info(cpu);
 
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 5077ead5e59c..c1d8b90aa4e2 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -40,13 +40,13 @@ ENTRY(startup_xen)
 #ifdef CONFIG_X86_64
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to the bottom of the irqstack
-	 * union.  If the stack protector canary is enabled, it is
-	 * located at %gs:40.  Note that, on SMP, the boot cpu uses
-	 * init data section till per cpu areas are set up.
+	 * The base of %gs always points to fixed_percpu_data.  If the
+	 * stack protector canary is enabled, it is located at %gs:40.
+	 * Note that, on SMP, the boot cpu uses init data section until
+	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(irq_stack_union),%rax
+	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
 	cdq
 	wrmsr
 #endif
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 4b9aafe766c5..35c8d91e6106 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -46,9 +46,6 @@ config XTENSA
 	  with reasonable minimum requirements.  The Xtensa Linux project has
 	  a home page at <http://www.linux-xtensa.org/>.
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 3843198e03d4..35f83c4bf239 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -20,12 +20,12 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
-generic-y += rwsem.h
 generic-y += sections.h
 generic-y += socket.h
 generic-y += topology.h
diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h
index 0d766f9c1083..50889935138a 100644
--- a/arch/xtensa/include/asm/tlb.h
+++ b/arch/xtensa/include/asm/tlb.h
@@ -14,32 +14,6 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 
-#if (DCACHE_WAY_SIZE <= PAGE_SIZE)
-
-/* Note, read http://lkml.org/lkml/2004/1/15/6 */
-
-# define tlb_start_vma(tlb,vma)			do { } while (0)
-# define tlb_end_vma(tlb,vma)			do { } while (0)
-
-#else
-
-# define tlb_start_vma(tlb, vma)					      \
-	do {								      \
-		if (!tlb->fullmm)					      \
-			flush_cache_range(vma, vma->vm_start, vma->vm_end);   \
-	} while(0)
-
-# define tlb_end_vma(tlb, vma)						      \
-	do {								      \
-		if (!tlb->fullmm)					      \
-			flush_tlb_range(vma, vma->vm_start, vma->vm_end);     \
-	} while(0)
-
-#endif
-
-#define __tlb_remove_tlb_entry(tlb,pte,addr)	do { } while (0)
-#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, address)	pte_free((tlb)->mm, pte)
diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c
index 81bfc6197293..f92033661239 100644
--- a/drivers/acpi/acpi_configfs.c
+++ b/drivers/acpi/acpi_configfs.c
@@ -109,7 +109,7 @@ static ssize_t acpi_table_signature_show(struct config_item *cfg, char *str)
 	if (!h)
 		return -EINVAL;
 
-	return sprintf(str, "%.*s\n", ACPI_NAME_SIZE, h->signature);
+	return sprintf(str, "%.*s\n", ACPI_NAMESEG_SIZE, h->signature);
 }
 
 static ssize_t acpi_table_length_show(struct config_item *cfg, char *str)
@@ -170,7 +170,7 @@ static ssize_t acpi_table_asl_compiler_id_show(struct config_item *cfg,
 	if (!h)
 		return -EINVAL;
 
-	return sprintf(str, "%.*s\n", ACPI_NAME_SIZE, h->asl_compiler_id);
+	return sprintf(str, "%.*s\n", ACPI_NAMESEG_SIZE, h->asl_compiler_id);
 }
 
 static ssize_t acpi_table_asl_compiler_revision_show(struct config_item *cfg,
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index 4a434c23a196..d18246a2a65e 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -390,7 +390,7 @@ again:
 	return size > 0 ? size : ret;
 }
 
-static int acpi_aml_thread(void *unsed)
+static int acpi_aml_thread(void *unused)
 {
 	acpi_osd_exec_callback function = NULL;
 	void *context;
diff --git a/drivers/acpi/acpi_lpat.c b/drivers/acpi/acpi_lpat.c
index 2cd9f738812b..43f1b99c86ca 100644
--- a/drivers/acpi/acpi_lpat.c
+++ b/drivers/acpi/acpi_lpat.c
@@ -22,7 +22,7 @@
  * LPAT conversion table
  *
  * @lpat_table: the temperature_raw mapping table structure
- * @raw: the raw value, used as a key to get the temerature from the
+ * @raw: the raw value, used as a key to get the temperature from the
  *       above mapping table
  *
  * A positive converted temperature value will be returned on success,
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 1e2a10a06b9d..cf768608437e 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -1142,8 +1142,8 @@ static struct dev_pm_domain acpi_lpss_pm_domain = {
 		.thaw_noirq = acpi_subsys_thaw_noirq,
 		.poweroff = acpi_subsys_suspend,
 		.poweroff_late = acpi_lpss_suspend_late,
-		.poweroff_noirq = acpi_subsys_suspend_noirq,
-		.restore_noirq = acpi_subsys_resume_noirq,
+		.poweroff_noirq = acpi_lpss_suspend_noirq,
+		.restore_noirq = acpi_lpss_resume_noirq,
 		.restore_early = acpi_lpss_resume_early,
 #endif
 		.runtime_suspend = acpi_lpss_runtime_suspend,
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index a2dfbf6b004e..13d513b81589 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -293,7 +293,7 @@ acpi_status (*acpi_internal_method) (struct acpi_walk_state * walk_state);
  * expected_return_btypes - Allowed type(s) for the return value
  */
 struct acpi_name_info {
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	u16 argument_list;
 	u8 expected_btypes;
 };
@@ -370,7 +370,7 @@ typedef acpi_status (*acpi_object_converter) (struct acpi_namespace_node *
 					      converted_object);
 
 struct acpi_simple_repair_info {
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	u32 unexpected_btypes;
 	u32 package_index;
 	acpi_object_converter object_converter;
diff --git a/drivers/acpi/acpica/dbexec.c b/drivers/acpi/acpica/dbexec.c
index bb43305cb215..4027eaab18a4 100644
--- a/drivers/acpi/acpica/dbexec.c
+++ b/drivers/acpi/acpica/dbexec.c
@@ -453,7 +453,7 @@ acpi_db_execute(char *name, char **args, acpi_object_type *types, u32 flags)
 
 			/* Dump a _PLD buffer if present */
 
-			if (ACPI_COMPARE_NAME
+			if (ACPI_COMPARE_NAMESEG
 			    ((ACPI_CAST_PTR
 			      (struct acpi_namespace_node,
 			       acpi_gbl_db_method_info.method)->name.ascii),
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index 004d34d9369b..63fe30e86807 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -354,7 +354,7 @@ acpi_status acpi_db_find_name_in_namespace(char *name_arg)
 	char acpi_name[5] = "____";
 	char *acpi_name_ptr = acpi_name;
 
-	if (strlen(name_arg) > ACPI_NAME_SIZE) {
+	if (strlen(name_arg) > ACPI_NAMESEG_SIZE) {
 		acpi_os_printf("Name must be no longer than 4 characters\n");
 		return (AE_OK);
 	}
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index a4a24ffe5fae..4ebd23700bbc 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -200,7 +200,7 @@ acpi_ds_initialize_objects(u32 table_index,
 
 	/* DSDT is always the first AML table */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT)) {
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_DSDT)) {
 		ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
 				      "\nInitializing Namespace objects:\n"));
 	}
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 5e9d7348c16f..62d3aa74277b 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -81,12 +81,8 @@ acpi_status acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info)
 
 	ACPI_FUNCTION_TRACE(ev_enable_gpe);
 
-	/* Clear the GPE status */
-	status = acpi_hw_clear_gpe(gpe_event_info);
-	if (ACPI_FAILURE(status))
-		return_ACPI_STATUS(status);
-
 	/* Enable the requested GPE */
+
 	status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE);
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index c92d2f6ebe01..b04f982e59fa 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -292,7 +292,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 	acpi_status status;
 	u32 gpe_number;
 	u8 temp_gpe_number;
-	char name[ACPI_NAME_SIZE + 1];
+	char name[ACPI_NAMESEG_SIZE + 1];
 	u8 type;
 
 	ACPI_FUNCTION_TRACE(ev_match_gpe_method);
@@ -310,7 +310,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 	 * 1) Extract the method name and null terminate it
 	 */
 	ACPI_MOVE_32_TO_32(name, &method_node->name.integer);
-	name[ACPI_NAME_SIZE] = 0;
+	name[ACPI_NAMESEG_SIZE] = 0;
 
 	/* 2) Name must begin with an underscore */
 
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index bd68d66e89f0..6b76be5212a4 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -53,10 +53,10 @@ static char *acpi_ex_allocate_name_string(u32 prefix_count, u32 num_name_segs)
 
 		/* Special case for root */
 
-		size_needed = 1 + (ACPI_NAME_SIZE * num_name_segs) + 2 + 1;
+		size_needed = 1 + (ACPI_NAMESEG_SIZE * num_name_segs) + 2 + 1;
 	} else {
 		size_needed =
-		    prefix_count + (ACPI_NAME_SIZE * num_name_segs) + 2 + 1;
+		    prefix_count + (ACPI_NAMESEG_SIZE * num_name_segs) + 2 + 1;
 	}
 
 	/*
@@ -141,7 +141,7 @@ static acpi_status acpi_ex_name_segment(u8 ** in_aml_address, char *name_string)
 	}
 
 	for (index = 0;
-	     (index < ACPI_NAME_SIZE)
+	     (index < ACPI_NAMESEG_SIZE)
 	     && (acpi_ut_valid_name_char(*aml_address, 0)); index++) {
 		char_buf[index] = *aml_address++;
 	}
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 75192b958544..7b855603f81a 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -683,7 +683,7 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 
 		/* Point to next name segment and make this node current */
 
-		path += ACPI_NAME_SIZE;
+		path += ACPI_NAMESEG_SIZE;
 		current_node = this_node;
 	}
 
diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c
index 5470213b8e64..6eb63db72249 100644
--- a/drivers/acpi/acpica/nsalloc.c
+++ b/drivers/acpi/acpica/nsalloc.c
@@ -74,6 +74,10 @@ void acpi_ns_delete_node(struct acpi_namespace_node *node)
 
 	ACPI_FUNCTION_NAME(ns_delete_node);
 
+	if (!node) {
+		return_VOID;
+	}
+
 	/* Detach an object if there is one */
 
 	acpi_ns_detach_object(node);
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 15070bd0c28a..1b12c172e115 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -70,7 +70,7 @@ void acpi_ns_print_pathname(u32 num_segments, const char *pathname)
 			    acpi_os_printf("?");
 		}
 
-		pathname += ACPI_NAME_SIZE;
+		pathname += ACPI_NAMESEG_SIZE;
 		num_segments--;
 		if (num_segments) {
 			acpi_os_printf(".");
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 19fb8dda870f..53e5d00d3a5e 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -478,7 +478,7 @@ acpi_ns_find_ini_methods(acpi_handle obj_handle,
 
 	/* We are only looking for methods named _INI */
 
-	if (!ACPI_COMPARE_NAME(node->name.ascii, METHOD_NAME__INI)) {
+	if (!ACPI_COMPARE_NAMESEG(node->name.ascii, METHOD_NAME__INI)) {
 		return (AE_OK);
 	}
 
@@ -641,7 +641,7 @@ acpi_ns_init_one_device(acpi_handle obj_handle,
 	 * Note: We know there is an _INI within this subtree, but it may not be
 	 * under this particular device, it may be lower in the branch.
 	 */
-	if (!ACPI_COMPARE_NAME(device_node->name.ascii, "_SB_") ||
+	if (!ACPI_COMPARE_NAMESEG(device_node->name.ascii, "_SB_") ||
 	    device_node->parent != acpi_gbl_root_node) {
 		ACPI_DEBUG_EXEC(acpi_ut_display_init_pathname
 				(ACPI_TYPE_METHOD, device_node,
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index 289c15bb8c6a..370bbc867745 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -108,8 +108,8 @@ acpi_ns_handle_to_name(acpi_handle target_handle, struct acpi_buffer *buffer)
 	/* Just copy the ACPI name from the Node and zero terminate it */
 
 	node_name = acpi_ut_get_node_name(node);
-	ACPI_MOVE_NAME(buffer->pointer, node_name);
-	((char *)buffer->pointer)[ACPI_NAME_SIZE] = 0;
+	ACPI_COPY_NAMESEG(buffer->pointer, node_name);
+	((char *)buffer->pointer)[ACPI_NAMESEG_SIZE] = 0;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "%4.4s\n", (char *)buffer->pointer));
 	return_ACPI_STATUS(AE_OK);
@@ -198,7 +198,7 @@ acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
 			      char *full_path, u32 path_size, u8 no_trailing)
 {
 	u32 length = 0, i;
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	u8 do_no_trailing;
 	char c, *left, *right;
 	struct acpi_namespace_node *next_node;
@@ -446,7 +446,7 @@ static void acpi_ns_normalize_pathname(char *original_path)
 
 		/* Do one nameseg at a time */
 
-		for (i = 0; (i < ACPI_NAME_SIZE) && *input_path; i++) {
+		for (i = 0; (i < ACPI_NAMESEG_SIZE) && *input_path; i++) {
 			if ((i == 0) || (*input_path != '_')) {	/* First char is allowed to be underscore */
 				*new_path = *input_path;
 				new_path++;
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index c0b4f7bedfab..f16cf5e4742c 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -203,7 +203,7 @@ acpi_ns_one_complete_parse(u32 pass_number,
 
 	/* Found OSDT table, enable the namespace override feature */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_OSDT) &&
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_OSDT) &&
 	    pass_number == ACPI_IMODE_LOAD_PASS1) {
 		walk_state->namespace_override = TRUE;
 	}
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 0aacfa48e20d..be86fea8e4d4 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -316,7 +316,7 @@ static const struct acpi_simple_repair_info *acpi_ns_match_simple_repair(struct
 
 	this_name = acpi_object_repair_info;
 	while (this_name->object_converter) {
-		if (ACPI_COMPARE_NAME(node->name.ascii, this_name->name)) {
+		if (ACPI_COMPARE_NAMESEG(node->name.ascii, this_name->name)) {
 
 			/* Check if we can actually repair this name/type combination */
 
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index d5804a6d1d65..8d776256b213 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info,
 				     return_object_ptr);
 
 typedef struct acpi_repair_info {
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	acpi_repair_function repair_function;
 
 } acpi_repair_info;
@@ -188,7 +188,7 @@ static const struct acpi_repair_info *acpi_ns_match_complex_repair(struct
 
 	this_name = acpi_ns_repairable_names;
 	while (this_name->repair_function) {
-		if (ACPI_COMPARE_NAME(node->name.ascii, this_name->name)) {
+		if (ACPI_COMPARE_NAMESEG(node->name.ascii, this_name->name)) {
 			return (this_name);
 		}
 
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index e5cef1edf49f..6bc90d46db5c 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -178,7 +178,7 @@ void acpi_ns_get_internal_name_length(struct acpi_namestring_info *info)
 		}
 	}
 
-	info->length = (ACPI_NAME_SIZE * info->num_segments) +
+	info->length = (ACPI_NAMESEG_SIZE * info->num_segments) +
 	    4 + info->num_carats;
 
 	info->next_external_char = next_external_char;
@@ -249,7 +249,7 @@ acpi_status acpi_ns_build_internal_name(struct acpi_namestring_info *info)
 	/* Build the name (minus path separators) */
 
 	for (; num_segments; num_segments--) {
-		for (i = 0; i < ACPI_NAME_SIZE; i++) {
+		for (i = 0; i < ACPI_NAMESEG_SIZE; i++) {
 			if (ACPI_IS_PATH_SEPARATOR(*external_name) ||
 			    (*external_name == 0)) {
 
@@ -274,7 +274,7 @@ acpi_status acpi_ns_build_internal_name(struct acpi_namestring_info *info)
 		/* Move on the next segment */
 
 		external_name++;
-		result += ACPI_NAME_SIZE;
+		result += ACPI_NAMESEG_SIZE;
 	}
 
 	/* Terminate the string */
@@ -489,12 +489,12 @@ acpi_ns_externalize_name(u32 internal_name_length,
 
 			/* Copy and validate the 4-char name segment */
 
-			ACPI_MOVE_NAME(&(*converted_name)[j],
-				       &internal_name[names_index]);
+			ACPI_COPY_NAMESEG(&(*converted_name)[j],
+					  &internal_name[names_index]);
 			acpi_ut_repair_name(&(*converted_name)[j]);
 
-			j += ACPI_NAME_SIZE;
-			names_index += ACPI_NAME_SIZE;
+			j += ACPI_NAMESEG_SIZE;
+			names_index += ACPI_NAMESEG_SIZE;
 		}
 	}
 
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index de2d3135d6a9..55b4a5b3331f 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -495,8 +495,8 @@ acpi_status acpi_install_method(u8 *buffer)
 
 	/* Table must be a DSDT or SSDT */
 
-	if (!ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT) &&
-	    !ACPI_COMPARE_NAME(table->signature, ACPI_SIG_SSDT)) {
+	if (!ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_DSDT) &&
+	    !ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_SSDT)) {
 		return (AE_BAD_HEADER);
 	}
 
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 9d9d442cd999..e62c7897fdf1 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -150,21 +150,21 @@ char *acpi_ps_get_next_namestring(struct acpi_parse_state *parser_state)
 
 		/* Two name segments */
 
-		end += 1 + (2 * ACPI_NAME_SIZE);
+		end += 1 + (2 * ACPI_NAMESEG_SIZE);
 		break;
 
 	case AML_MULTI_NAME_PREFIX:
 
 		/* Multiple name segments, 4 chars each, count in next byte */
 
-		end += 2 + (*(end + 1) * ACPI_NAME_SIZE);
+		end += 2 + (*(end + 1) * ACPI_NAMESEG_SIZE);
 		break;
 
 	default:
 
 		/* Single name segment */
 
-		end += ACPI_NAME_SIZE;
+		end += ACPI_NAMESEG_SIZE;
 		break;
 	}
 
@@ -522,7 +522,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 		ACPI_MOVE_32_TO_32(&name, parser_state->aml);
 		acpi_ps_set_name(field, name);
-		parser_state->aml += ACPI_NAME_SIZE;
+		parser_state->aml += ACPI_NAMESEG_SIZE;
 
 		ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
 
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 1d6f136e4068..c62be3d91712 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -603,10 +603,10 @@ acpi_walk_resources(acpi_handle device_handle,
 	/* Parameter validation */
 
 	if (!device_handle || !user_function || !name ||
-	    (!ACPI_COMPARE_NAME(name, METHOD_NAME__CRS) &&
-	     !ACPI_COMPARE_NAME(name, METHOD_NAME__PRS) &&
-	     !ACPI_COMPARE_NAME(name, METHOD_NAME__AEI) &&
-	     !ACPI_COMPARE_NAME(name, METHOD_NAME__DMA))) {
+	    (!ACPI_COMPARE_NAMESEG(name, METHOD_NAME__CRS) &&
+	     !ACPI_COMPARE_NAMESEG(name, METHOD_NAME__PRS) &&
+	     !ACPI_COMPARE_NAMESEG(name, METHOD_NAME__AEI) &&
+	     !ACPI_COMPARE_NAMESEG(name, METHOD_NAME__DMA))) {
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index 0cecd0039acf..933f81316ad2 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -480,7 +480,8 @@ acpi_tb_verify_temp_table(struct acpi_table_desc *table_desc,
 
 	/* If a particular signature is expected (DSDT/FACS), it must match */
 
-	if (signature && !ACPI_COMPARE_NAME(&table_desc->signature, signature)) {
+	if (signature &&
+	    !ACPI_COMPARE_NAMESEG(&table_desc->signature, signature)) {
 		ACPI_BIOS_ERROR((AE_INFO,
 				 "Invalid signature 0x%X for ACPI table, expected [%s]",
 				 table_desc->signature.integer, signature));
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index 951bd8e1c50a..b2abb40023a6 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -56,7 +56,7 @@ acpi_tb_find_table(char *signature,
 	/* Normalize the input strings */
 
 	memset(&header, 0, sizeof(struct acpi_table_header));
-	ACPI_MOVE_NAME(header.signature, signature);
+	ACPI_COPY_NAMESEG(header.signature, signature);
 	strncpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
 	strncpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
 
@@ -65,7 +65,7 @@ acpi_tb_find_table(char *signature,
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) {
 		if (memcmp(&(acpi_gbl_root_table_list.tables[i].signature),
-			   header.signature, ACPI_NAME_SIZE)) {
+			   header.signature, ACPI_NAMESEG_SIZE)) {
 
 			/* Not the requested table */
 
@@ -94,14 +94,14 @@ acpi_tb_find_table(char *signature,
 
 		if (!memcmp
 		    (acpi_gbl_root_table_list.tables[i].pointer->signature,
-		     header.signature, ACPI_NAME_SIZE) && (!oem_id[0]
-							   ||
-							   !memcmp
-							   (acpi_gbl_root_table_list.
-							    tables[i].pointer->
-							    oem_id,
-							    header.oem_id,
-							    ACPI_OEM_ID_SIZE))
+		     header.signature, ACPI_NAMESEG_SIZE) && (!oem_id[0]
+							      ||
+							      !memcmp
+							      (acpi_gbl_root_table_list.
+							       tables[i].
+							       pointer->oem_id,
+							       header.oem_id,
+							       ACPI_OEM_ID_SIZE))
 		    && (!oem_table_id[0]
 			|| !memcmp(acpi_gbl_root_table_list.tables[i].pointer->
 				   oem_table_id, header.oem_table_id,
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index be6642bf6366..ef1ffd36ab3f 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -120,7 +120,7 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 	 */
 	if (!reload &&
 	    acpi_gbl_disable_ssdt_table_install &&
-	    ACPI_COMPARE_NAME(&new_table_desc.signature, ACPI_SIG_SSDT)) {
+	    ACPI_COMPARE_NAMESEG(&new_table_desc.signature, ACPI_SIG_SSDT)) {
 		ACPI_INFO(("Ignoring installation of %4.4s at %8.8X%8.8X",
 			   new_table_desc.signature.ascii,
 			   ACPI_FORMAT_UINT64(address)));
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 9b5df95d881b..4764f849cb78 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -69,10 +69,10 @@ acpi_tb_cleanup_table_header(struct acpi_table_header *out_header,
 
 	memcpy(out_header, header, sizeof(struct acpi_table_header));
 
-	acpi_tb_fix_string(out_header->signature, ACPI_NAME_SIZE);
+	acpi_tb_fix_string(out_header->signature, ACPI_NAMESEG_SIZE);
 	acpi_tb_fix_string(out_header->oem_id, ACPI_OEM_ID_SIZE);
 	acpi_tb_fix_string(out_header->oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
-	acpi_tb_fix_string(out_header->asl_compiler_id, ACPI_NAME_SIZE);
+	acpi_tb_fix_string(out_header->asl_compiler_id, ACPI_NAMESEG_SIZE);
 }
 
 /*******************************************************************************
@@ -94,7 +94,7 @@ acpi_tb_print_table_header(acpi_physical_address address,
 {
 	struct acpi_table_header local_header;
 
-	if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_FACS)) {
+	if (ACPI_COMPARE_NAMESEG(header->signature, ACPI_SIG_FACS)) {
 
 		/* FACS only has signature and length fields */
 
@@ -158,8 +158,8 @@ acpi_status acpi_tb_verify_checksum(struct acpi_table_header *table, u32 length)
 	 * They are the odd tables, have no standard ACPI header and no checksum
 	 */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_S3PT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_FACS)) {
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_S3PT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_FACS)) {
 		return (AE_OK);
 	}
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 2469e01310e2..c5f0b8ec70cc 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -332,9 +332,9 @@ acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 							&table_index);
 
 		if (ACPI_SUCCESS(status) &&
-		    ACPI_COMPARE_NAME(&acpi_gbl_root_table_list.
-				      tables[table_index].signature,
-				      ACPI_SIG_FADT)) {
+		    ACPI_COMPARE_NAMESEG(&acpi_gbl_root_table_list.
+					 tables[table_index].signature,
+					 ACPI_SIG_FADT)) {
 			acpi_gbl_fadt_index = table_index;
 			acpi_tb_parse_fadt();
 		}
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 36592888f0e7..1640685bf4ae 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -230,7 +230,7 @@ acpi_get_table_header(char *signature,
 
 	for (i = 0, j = 0; i < acpi_gbl_root_table_list.current_table_count;
 	     i++) {
-		if (!ACPI_COMPARE_NAME
+		if (!ACPI_COMPARE_NAMESEG
 		    (&(acpi_gbl_root_table_list.tables[i].signature),
 		     signature)) {
 			continue;
@@ -323,7 +323,7 @@ acpi_get_table(char *signature,
 	     i++) {
 		table_desc = &acpi_gbl_root_table_list.tables[i];
 
-		if (!ACPI_COMPARE_NAME(&table_desc->signature, signature)) {
+		if (!ACPI_COMPARE_NAMESEG(&table_desc->signature, signature)) {
 			continue;
 		}
 
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 1a2592cc3245..4f30f06a6f78 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -118,7 +118,7 @@ acpi_status acpi_tb_load_namespace(void)
 	table = &acpi_gbl_root_table_list.tables[acpi_gbl_dsdt_index];
 
 	if (!acpi_gbl_root_table_list.current_table_count ||
-	    !ACPI_COMPARE_NAME(table->signature.ascii, ACPI_SIG_DSDT) ||
+	    !ACPI_COMPARE_NAMESEG(table->signature.ascii, ACPI_SIG_DSDT) ||
 	    ACPI_FAILURE(acpi_tb_validate_table(table))) {
 		status = AE_NO_ACPI_TABLES;
 		goto unlock_and_exit;
@@ -170,11 +170,12 @@ acpi_status acpi_tb_load_namespace(void)
 		table = &acpi_gbl_root_table_list.tables[i];
 
 		if (!table->address ||
-		    (!ACPI_COMPARE_NAME(table->signature.ascii, ACPI_SIG_SSDT)
-		     && !ACPI_COMPARE_NAME(table->signature.ascii,
-					   ACPI_SIG_PSDT)
-		     && !ACPI_COMPARE_NAME(table->signature.ascii,
-					   ACPI_SIG_OSDT))
+		    (!ACPI_COMPARE_NAMESEG
+		     (table->signature.ascii, ACPI_SIG_SSDT)
+		     && !ACPI_COMPARE_NAMESEG(table->signature.ascii,
+					      ACPI_SIG_PSDT)
+		     && !ACPI_COMPARE_NAMESEG(table->signature.ascii,
+					      ACPI_SIG_OSDT))
 		    || ACPI_FAILURE(acpi_tb_validate_table(table))) {
 			continue;
 		}
@@ -364,7 +365,7 @@ acpi_status acpi_unload_parent_table(acpi_handle object)
 		 * only these types can contain AML and thus are the only types
 		 * that can create namespace objects.
 		 */
-		if (ACPI_COMPARE_NAME
+		if (ACPI_COMPARE_NAMESEG
 		    (acpi_gbl_root_table_list.tables[i].signature.ascii,
 		     ACPI_SIG_DSDT)) {
 			status = AE_TYPE;
diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c
index 79d7426fd7bf..f6cd7d4f698b 100644
--- a/drivers/acpi/acpica/utascii.c
+++ b/drivers/acpi/acpica/utascii.c
@@ -30,7 +30,7 @@ u8 acpi_ut_valid_nameseg(char *name)
 
 	/* Validate each character in the signature */
 
-	for (i = 0; i < ACPI_NAME_SIZE; i++) {
+	for (i = 0; i < ACPI_NAMESEG_SIZE; i++) {
 		if (!acpi_ut_valid_name_char(name[i], i)) {
 			return (FALSE);
 		}
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index ad9f77eb554f..65beaa237669 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -78,7 +78,7 @@ const char *acpi_gbl_region_types[ACPI_NUM_PREDEFINED_REGIONS] = {
 	"IPMI",			/* 0x07 */
 	"GeneralPurposeIo",	/* 0x08 */
 	"GenericSerialBus",	/* 0x09 */
-	"PCC"			/* 0x0A */
+	"PlatformCommChannel"	/* 0x0A */
 };
 
 const char *acpi_ut_get_region_name(u8 space_id)
@@ -239,7 +239,7 @@ const char *acpi_ut_get_node_name(void *object)
 {
 	struct acpi_namespace_node *node = (struct acpi_namespace_node *)object;
 
-	/* Must return a string of exactly 4 characters == ACPI_NAME_SIZE */
+	/* Must return a string of exactly 4 characters == ACPI_NAMESEG_SIZE */
 
 	if (!object) {
 		return ("NULL");
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index afaadc73196b..8638efacdbf4 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -59,10 +59,10 @@ u8 acpi_ut_is_aml_table(struct acpi_table_header *table)
 
 	/* These are the only tables that contain executable AML */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_PSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_SSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_OSDT) ||
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_DSDT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_PSDT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_SSDT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_OSDT) ||
 	    ACPI_IS_OEM_SIG(table->signature)) {
 		return (TRUE);
 	}
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index a9f08f43c685..1b0f68f5ed8c 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -84,7 +84,7 @@ const union acpi_predefined_info *acpi_ut_match_predefined_method(char *name)
 
 	this_name = acpi_gbl_predefined_methods;
 	while (this_name->info.name[0]) {
-		if (ACPI_COMPARE_NAME(name, this_name->info.name)) {
+		if (ACPI_COMPARE_NAMESEG(name, this_name->info.name)) {
 			return (this_name);
 		}
 
@@ -201,7 +201,7 @@ const union acpi_predefined_info *acpi_ut_match_resource_name(char *name)
 
 	this_name = acpi_gbl_resource_names;
 	while (this_name->info.name[0]) {
-		if (ACPI_COMPARE_NAME(name, this_name->info.name)) {
+		if (ACPI_COMPARE_NAMESEG(name, this_name->info.name)) {
 			return (this_name);
 		}
 
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 5bef0b059406..c39b5483045d 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -141,15 +141,15 @@ void acpi_ut_repair_name(char *name)
 	 * Special case for the root node. This can happen if we get an
 	 * error during the execution of module-level code.
 	 */
-	if (ACPI_COMPARE_NAME(name, ACPI_ROOT_PATHNAME)) {
+	if (ACPI_COMPARE_NAMESEG(name, ACPI_ROOT_PATHNAME)) {
 		return;
 	}
 
-	ACPI_MOVE_NAME(&original_name, name);
+	ACPI_COPY_NAMESEG(&original_name, name);
 
 	/* Check each character in the name */
 
-	for (i = 0; i < ACPI_NAME_SIZE; i++) {
+	for (i = 0; i < ACPI_NAMESEG_SIZE; i++) {
 		if (acpi_ut_valid_name_char(name[i], i)) {
 			continue;
 		}
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index e48894e002ba..adbf7cbedf80 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -356,7 +356,8 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 	if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
 		if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT ||
 		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX ||
-		    node->type == ACPI_IORT_NODE_SMMU_V3) {
+		    node->type == ACPI_IORT_NODE_SMMU_V3 ||
+		    node->type == ACPI_IORT_NODE_PMCG) {
 			*id_out = map->output_base;
 			return parent;
 		}
@@ -394,6 +395,8 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 		}
 
 		return smmu->id_mapping_index;
+	case ACPI_IORT_NODE_PMCG:
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -1218,32 +1221,47 @@ static void __init arm_smmu_v3_init_resources(struct resource *res,
 	}
 }
 
-static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_v3_dma_configure(struct device *dev,
+					     struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
+	enum dev_dma_attr attr;
 
 	/* Retrieve SMMUv3 specific data */
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 
-	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
+	attr = (smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* We expect the dma masks to be equivalent for all SMMUv3 set-ups */
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(dev, attr);
 }
 
 #if defined(CONFIG_ACPI_NUMA)
 /*
  * set numa proximity domain for smmuv3 device
  */
-static void  __init arm_smmu_v3_set_proximity(struct device *dev,
+static int  __init arm_smmu_v3_set_proximity(struct device *dev,
 					      struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
 
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 	if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
-		set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm));
+		int node = acpi_map_pxm_to_node(smmu->pxm);
+
+		if (node != NUMA_NO_NODE && !node_online(node))
+			return -EINVAL;
+
+		set_dev_node(dev, node);
 		pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n",
 			smmu->base_address,
 			smmu->pxm);
 	}
+	return 0;
 }
 #else
 #define arm_smmu_v3_set_proximity NULL
@@ -1301,30 +1319,96 @@ static void __init arm_smmu_init_resources(struct resource *res,
 	}
 }
 
-static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_dma_configure(struct device *dev,
+					  struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu *smmu;
+	enum dev_dma_attr attr;
 
 	/* Retrieve SMMU specific data */
 	smmu = (struct acpi_iort_smmu *)node->node_data;
 
-	return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
+	attr = (smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* We expect the dma masks to be equivalent for SMMU set-ups */
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(dev, attr);
+}
+
+static int __init arm_smmu_v3_pmcg_count_resources(struct acpi_iort_node *node)
+{
+	struct acpi_iort_pmcg *pmcg;
+
+	/* Retrieve PMCG specific data */
+	pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+	/*
+	 * There are always 2 memory resources.
+	 * If the overflow_gsiv is present then add that for a total of 3.
+	 */
+	return pmcg->overflow_gsiv ? 3 : 2;
+}
+
+static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res,
+						   struct acpi_iort_node *node)
+{
+	struct acpi_iort_pmcg *pmcg;
+
+	/* Retrieve PMCG specific data */
+	pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+	res[0].start = pmcg->page0_base_address;
+	res[0].end = pmcg->page0_base_address + SZ_4K - 1;
+	res[0].flags = IORESOURCE_MEM;
+	res[1].start = pmcg->page1_base_address;
+	res[1].end = pmcg->page1_base_address + SZ_4K - 1;
+	res[1].flags = IORESOURCE_MEM;
+
+	if (pmcg->overflow_gsiv)
+		acpi_iort_register_irq(pmcg->overflow_gsiv, "overflow",
+				       ACPI_EDGE_SENSITIVE, &res[2]);
+}
+
+static struct acpi_platform_list pmcg_plat_info[] __initdata = {
+	/* HiSilicon Hip08 Platform */
+	{"HISI  ", "HIP08   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08},
+	{ }
+};
+
+static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev)
+{
+	u32 model;
+	int idx;
+
+	idx = acpi_match_platform_list(pmcg_plat_info);
+	if (idx >= 0)
+		model = pmcg_plat_info[idx].data;
+	else
+		model = IORT_SMMU_V3_PMCG_GENERIC;
+
+	return platform_device_add_data(pdev, &model, sizeof(model));
 }
 
 struct iort_dev_config {
 	const char *name;
 	int (*dev_init)(struct acpi_iort_node *node);
-	bool (*dev_is_coherent)(struct acpi_iort_node *node);
+	void (*dev_dma_configure)(struct device *dev,
+				  struct acpi_iort_node *node);
 	int (*dev_count_resources)(struct acpi_iort_node *node);
 	void (*dev_init_resources)(struct resource *res,
 				     struct acpi_iort_node *node);
-	void (*dev_set_proximity)(struct device *dev,
+	int (*dev_set_proximity)(struct device *dev,
 				    struct acpi_iort_node *node);
+	int (*dev_add_platdata)(struct platform_device *pdev);
 };
 
 static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 	.name = "arm-smmu-v3",
-	.dev_is_coherent = arm_smmu_v3_is_coherent,
+	.dev_dma_configure = arm_smmu_v3_dma_configure,
 	.dev_count_resources = arm_smmu_v3_count_resources,
 	.dev_init_resources = arm_smmu_v3_init_resources,
 	.dev_set_proximity = arm_smmu_v3_set_proximity,
@@ -1332,9 +1416,16 @@ static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 
 static const struct iort_dev_config iort_arm_smmu_cfg __initconst = {
 	.name = "arm-smmu",
-	.dev_is_coherent = arm_smmu_is_coherent,
+	.dev_dma_configure = arm_smmu_dma_configure,
 	.dev_count_resources = arm_smmu_count_resources,
-	.dev_init_resources = arm_smmu_init_resources
+	.dev_init_resources = arm_smmu_init_resources,
+};
+
+static const struct iort_dev_config iort_arm_smmu_v3_pmcg_cfg __initconst = {
+	.name = "arm-smmu-v3-pmcg",
+	.dev_count_resources = arm_smmu_v3_pmcg_count_resources,
+	.dev_init_resources = arm_smmu_v3_pmcg_init_resources,
+	.dev_add_platdata = arm_smmu_v3_pmcg_add_platdata,
 };
 
 static __init const struct iort_dev_config *iort_get_dev_cfg(
@@ -1345,6 +1436,8 @@ static __init const struct iort_dev_config *iort_get_dev_cfg(
 		return &iort_arm_smmu_v3_cfg;
 	case ACPI_IORT_NODE_SMMU:
 		return &iort_arm_smmu_cfg;
+	case ACPI_IORT_NODE_PMCG:
+		return &iort_arm_smmu_v3_pmcg_cfg;
 	default:
 		return NULL;
 	}
@@ -1362,15 +1455,17 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 	struct fwnode_handle *fwnode;
 	struct platform_device *pdev;
 	struct resource *r;
-	enum dev_dma_attr attr;
 	int ret, count;
 
 	pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
 	if (!pdev)
 		return -ENOMEM;
 
-	if (ops->dev_set_proximity)
-		ops->dev_set_proximity(&pdev->dev, node);
+	if (ops->dev_set_proximity) {
+		ret = ops->dev_set_proximity(&pdev->dev, node);
+		if (ret)
+			goto dev_put;
+	}
 
 	count = ops->dev_count_resources(node);
 
@@ -1393,19 +1488,19 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 		goto dev_put;
 
 	/*
-	 * Add a copy of IORT node pointer to platform_data to
-	 * be used to retrieve IORT data information.
+	 * Platform devices based on PMCG nodes uses platform_data to
+	 * pass the hardware model info to the driver. For others, add
+	 * a copy of IORT node pointer to platform_data to be used to
+	 * retrieve IORT data information.
 	 */
-	ret = platform_device_add_data(pdev, &node, sizeof(node));
+	if (ops->dev_add_platdata)
+		ret = ops->dev_add_platdata(pdev);
+	else
+		ret = platform_device_add_data(pdev, &node, sizeof(node));
+
 	if (ret)
 		goto dev_put;
 
-	/*
-	 * We expect the dma masks to be equivalent for
-	 * all SMMUs set-ups
-	 */
-	pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
-
 	fwnode = iort_get_fwnode(node);
 
 	if (!fwnode) {
@@ -1415,11 +1510,8 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 
 	pdev->dev.fwnode = fwnode;
 
-	attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ?
-			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
-
-	/* Configure DMA for the page table walker */
-	acpi_dma_configure(&pdev->dev, attr);
+	if (ops->dev_dma_configure)
+		ops->dev_dma_configure(&pdev->dev, node);
 
 	iort_set_device_domain(&pdev->dev, node);
 
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index a19ff3977ac4..623998a8d722 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -456,8 +456,11 @@ static int acpi_button_resume(struct device *dev)
 	struct acpi_button *button = acpi_driver_data(device);
 
 	button->suspended = false;
-	if (button->type == ACPI_BUTTON_TYPE_LID && button->input->users)
+	if (button->type == ACPI_BUTTON_TYPE_LID && button->input->users) {
+		button->last_state = !!acpi_lid_evaluate_state(device);
+		button->last_time = ktime_get();
 		acpi_lid_initialize_state(device);
+	}
 	return 0;
 }
 #endif
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index d4244e7d0e38..653642a4cbdd 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -81,9 +81,9 @@ struct cppc_pcc_data {
 	int refcount;
 };
 
-/* Array  to represent the PCC channel per subspace id */
+/* Array to represent the PCC channel per subspace ID */
 static struct cppc_pcc_data *pcc_data[MAX_PCC_SUBSPACES];
-/* The cpu_pcc_subspace_idx containsper CPU subspace id */
+/* The cpu_pcc_subspace_idx contains per CPU subspace ID */
 static DEFINE_PER_CPU(int, cpu_pcc_subspace_idx);
 
 /*
@@ -436,7 +436,7 @@ int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data)
 		return -ENOMEM;
 
 	/*
-	 * Now that we have _PSD data from all CPUs, lets setup P-state
+	 * Now that we have _PSD data from all CPUs, let's setup P-state
 	 * domain info.
 	 */
 	for_each_possible_cpu(i) {
@@ -588,7 +588,7 @@ static int register_pcc_channel(int pcc_ss_idx)
 			return -ENOMEM;
 		}
 
-		/* Set flag so that we dont come here for each CPU. */
+		/* Set flag so that we don't come here for each CPU. */
 		pcc_data[pcc_ss_idx]->pcc_channel_acquired = true;
 	}
 
@@ -613,7 +613,7 @@ bool __weak cpc_ffh_supported(void)
  *
  * Check and allocate the cppc_pcc_data memory.
  * In some processor configurations it is possible that same subspace
- * is shared between multiple CPU's. This is seen especially in CPU's
+ * is shared between multiple CPUs. This is seen especially in CPUs
  * with hardware multi-threading support.
  *
  * Return: 0 for success, errno for failure
@@ -711,7 +711,7 @@ static bool is_cppc_supported(int revision, int num_ent)
 
 /**
  * acpi_cppc_processor_probe - Search for per CPU _CPC objects.
- * @pr: Ptr to acpi_processor containing this CPUs logical Id.
+ * @pr: Ptr to acpi_processor containing this CPU's logical ID.
  *
  *	Return: 0 for success or negative value for err.
  */
@@ -728,7 +728,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 	acpi_status status;
 	int ret = -EFAULT;
 
-	/* Parse the ACPI _CPC table for this cpu. */
+	/* Parse the ACPI _CPC table for this CPU. */
 	status = acpi_evaluate_object_typed(handle, "_CPC", NULL, &output,
 			ACPI_TYPE_PACKAGE);
 	if (ACPI_FAILURE(status)) {
@@ -840,7 +840,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 	if (ret)
 		goto out_free;
 
-	/* Register PCC channel once for all PCC subspace id. */
+	/* Register PCC channel once for all PCC subspace ID. */
 	if (pcc_subspace_id >= 0 && !pcc_data[pcc_subspace_id]->pcc_channel_acquired) {
 		ret = register_pcc_channel(pcc_subspace_id);
 		if (ret)
@@ -860,7 +860,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 		goto out_free;
 	}
 
-	/* Plug PSD data into this CPUs CPC descriptor. */
+	/* Plug PSD data into this CPU's CPC descriptor. */
 	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
 
 	ret = kobject_init_and_add(&cpc_ptr->kobj, &cppc_ktype, &cpu_dev->kobj,
@@ -891,7 +891,7 @@ EXPORT_SYMBOL_GPL(acpi_cppc_processor_probe);
 
 /**
  * acpi_cppc_processor_exit - Cleanup CPC structs.
- * @pr: Ptr to acpi_processor containing this CPUs logical Id.
+ * @pr: Ptr to acpi_processor containing this CPU's logical ID.
  *
  * Return: Void
  */
@@ -931,7 +931,7 @@ EXPORT_SYMBOL_GPL(acpi_cppc_processor_exit);
 
 /**
  * cpc_read_ffh() - Read FFH register
- * @cpunum:	cpu number to read
+ * @cpunum:	CPU number to read
  * @reg:	cppc register information
  * @val:	place holder for return value
  *
@@ -946,7 +946,7 @@ int __weak cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
 
 /**
  * cpc_write_ffh() - Write FFH register
- * @cpunum:	cpu number to write
+ * @cpunum:	CPU number to write
  * @reg:	cppc register information
  * @val:	value to write
  *
@@ -1093,7 +1093,7 @@ int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
 
 /**
- * cppc_get_perf_caps - Get a CPUs performance capabilities.
+ * cppc_get_perf_caps - Get a CPU's performance capabilities.
  * @cpunum: CPU from which to get capabilities info.
  * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
  *
@@ -1183,7 +1183,7 @@ out_err:
 EXPORT_SYMBOL_GPL(cppc_get_perf_caps);
 
 /**
- * cppc_get_perf_ctrs - Read a CPUs performance feedback counters.
+ * cppc_get_perf_ctrs - Read a CPU's performance feedback counters.
  * @cpunum: CPU from which to read counters.
  * @perf_fb_ctrs: ptr to cppc_perf_fb_ctrs. See cppc_acpi.h
  *
@@ -1210,7 +1210,7 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	ctr_wrap_reg = &cpc_desc->cpc_regs[CTR_WRAP_TIME];
 
 	/*
-	 * If refernce perf register is not supported then we should
+	 * If reference perf register is not supported then we should
 	 * use the nominal perf value
 	 */
 	if (!CPC_SUPPORTED(ref_perf_reg))
@@ -1263,7 +1263,7 @@ out_err:
 EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs);
 
 /**
- * cppc_set_perf - Set a CPUs performance controls.
+ * cppc_set_perf - Set a CPU's performance controls.
  * @cpu: CPU for which to set performance controls.
  * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h
  *
@@ -1344,7 +1344,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * executing the Phase-II.
 	 *     2. Some other CPU has beaten this CPU to successfully execute the
 	 * write_trylock and has already acquired the write_lock. We know for a
-	 * fact it(other CPU acquiring the write_lock) couldn't have happened
+	 * fact it (other CPU acquiring the write_lock) couldn't have happened
 	 * before this CPU's Phase-I as we held the read_lock.
 	 *     3. Some other CPU executing pcc CMD_READ has stolen the
 	 * down_write, in which case, send_pcc_cmd will check for pending
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 824ae985ad93..5b50f884712c 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -728,6 +728,9 @@ static int __acpi_device_wakeup_enable(struct acpi_device *adev,
 		goto out;
 	}
 
+	acpi_handle_debug(adev->handle, "GPE%2X enabled for wakeup\n",
+			  (unsigned int)wakeup->gpe_number);
+
 inc:
 	wakeup->enable_count++;
 
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index e1c242568341..0c081390930a 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -31,8 +31,7 @@ static ssize_t name##_show(struct device *dev,\
 			   struct device_attribute *attr,\
 			   char *buf)\
 {\
-	struct platform_device *pdev = to_platform_device(dev);\
-	struct acpi_device *acpi_dev = platform_get_drvdata(pdev);\
+	struct acpi_device *acpi_dev = dev_get_drvdata(dev);\
 	unsigned long long val;\
 	acpi_status status;\
 \
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 5a127f3f2d5c..47f21599f2ab 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -131,8 +131,8 @@ int acpi_bus_generate_netlink_event(const char *device_class,
 	event = nla_data(attr);
 	memset(event, 0, sizeof(struct acpi_genl_event));
 
-	strcpy(event->device_class, device_class);
-	strcpy(event->bus_id, bus_id);
+	strscpy(event->device_class, device_class, sizeof(event->device_class));
+	strscpy(event->bus_id, bus_id, sizeof(event->bus_id));
 	event->type = type;
 	event->data = data;
 
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 665e93ca0b40..87db3e124725 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -535,12 +535,12 @@ int acpi_device_sleep_wake(struct acpi_device *dev,
 	/*
 	 * Try to execute _DSW first.
 	 *
-	 * Three agruments are needed for the _DSW object:
+	 * Three arguments are needed for the _DSW object:
 	 * Argument 0: enable/disable the wake capabilities
 	 * Argument 1: target system state
 	 * Argument 2: target device state
 	 * When _DSW object is called to disable the wake capabilities, maybe
-	 * the first argument is filled. The values of the other two agruments
+	 * the first argument is filled. The values of the other two arguments
 	 * are meaningless.
 	 */
 	in_arg[0].type = ACPI_TYPE_INTEGER;
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index 065c4fc245d1..b72e6afaa8fb 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -164,7 +164,7 @@ static struct acpi_pptt_cache *acpi_find_cache_level(struct acpi_table_header *t
 }
 
 /**
- * acpi_count_levels() - Given a PPTT table, and a cpu node, count the caches
+ * acpi_count_levels() - Given a PPTT table, and a CPU node, count the caches
  * @table_hdr: Pointer to the head of the PPTT table
  * @cpu_node: processor node we wish to count caches for
  *
@@ -235,7 +235,7 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
 /**
  * acpi_find_processor_node() - Given a PPTT table find the requested processor
  * @table_hdr:  Pointer to the head of the PPTT table
- * @acpi_cpu_id: cpu we are searching for
+ * @acpi_cpu_id: CPU we are searching for
  *
  * Find the subtable entry describing the provided processor.
  * This is done by iterating the PPTT table looking for processor nodes
@@ -456,21 +456,21 @@ static struct acpi_pptt_processor *acpi_find_processor_package_id(struct acpi_ta
 
 static void acpi_pptt_warn_missing(void)
 {
-	pr_warn_once("No PPTT table found, cpu and cache topology may be inaccurate\n");
+	pr_warn_once("No PPTT table found, CPU and cache topology may be inaccurate\n");
 }
 
 /**
  * topology_get_acpi_cpu_tag() - Find a unique topology value for a feature
  * @table: Pointer to the head of the PPTT table
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  * @level: A level that terminates the search
  * @flag: A flag which terminates the search
  *
- * Get a unique value given a cpu, and a topology level, that can be
+ * Get a unique value given a CPU, and a topology level, that can be
  * matched to determine which cpus share common topological features
  * at that level.
  *
- * Return: Unique value, or -ENOENT if unable to locate cpu
+ * Return: Unique value, or -ENOENT if unable to locate CPU
  */
 static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
 				     unsigned int cpu, int level, int flag)
@@ -510,7 +510,7 @@ static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
 		return -ENOENT;
 	}
 	retval = topology_get_acpi_cpu_tag(table, cpu, level, flag);
-	pr_debug("Topology Setup ACPI cpu %d, level %d ret = %d\n",
+	pr_debug("Topology Setup ACPI CPU %d, level %d ret = %d\n",
 		 cpu, level, retval);
 	acpi_put_table(table);
 
@@ -519,9 +519,9 @@ static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
 
 /**
  * acpi_find_last_cache_level() - Determines the number of cache levels for a PE
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  *
- * Given a logical cpu number, returns the number of levels of cache represented
+ * Given a logical CPU number, returns the number of levels of cache represented
  * in the PPTT. Errors caused by lack of a PPTT table, or otherwise, return 0
  * indicating we didn't find any cache levels.
  *
@@ -534,7 +534,7 @@ int acpi_find_last_cache_level(unsigned int cpu)
 	int number_of_levels = 0;
 	acpi_status status;
 
-	pr_debug("Cache Setup find last level cpu=%d\n", cpu);
+	pr_debug("Cache Setup find last level CPU=%d\n", cpu);
 
 	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
 	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
@@ -551,14 +551,14 @@ int acpi_find_last_cache_level(unsigned int cpu)
 
 /**
  * cache_setup_acpi() - Override CPU cache topology with data from the PPTT
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  *
  * Updates the global cache info provided by cpu_get_cacheinfo()
  * when there are valid properties in the acpi_pptt_cache nodes. A
  * successful parse may not result in any updates if none of the
- * cache levels have any valid flags set.  Futher, a unique value is
+ * cache levels have any valid flags set.  Further, a unique value is
  * associated with each known CPU cache entry. This unique value
- * can be used to determine whether caches are shared between cpus.
+ * can be used to determine whether caches are shared between CPUs.
  *
  * Return: -ENOENT on failure to find table, or 0 on success
  */
@@ -567,7 +567,7 @@ int cache_setup_acpi(unsigned int cpu)
 	struct acpi_table_header *table;
 	acpi_status status;
 
-	pr_debug("Cache Setup ACPI cpu %d\n", cpu);
+	pr_debug("Cache Setup ACPI CPU %d\n", cpu);
 
 	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
 	if (ACPI_FAILURE(status)) {
@@ -582,8 +582,8 @@ int cache_setup_acpi(unsigned int cpu)
 }
 
 /**
- * find_acpi_cpu_topology() - Determine a unique topology value for a given cpu
- * @cpu: Kernel logical cpu number
+ * find_acpi_cpu_topology() - Determine a unique topology value for a given CPU
+ * @cpu: Kernel logical CPU number
  * @level: The topological level for which we would like a unique ID
  *
  * Determine a topology unique ID for each thread/core/cluster/mc_grouping
@@ -596,7 +596,7 @@ int cache_setup_acpi(unsigned int cpu)
  * other levels beyond this use a generated value to uniquely identify
  * a topological feature.
  *
- * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
  * Otherwise returns a value which represents a unique topological feature.
  */
 int find_acpi_cpu_topology(unsigned int cpu, int level)
@@ -606,12 +606,12 @@ int find_acpi_cpu_topology(unsigned int cpu, int level)
 
 /**
  * find_acpi_cpu_cache_topology() - Determine a unique cache topology value
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  * @level: The cache level for which we would like a unique ID
  *
  * Determine a unique ID for each unified cache in the system
  *
- * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
  * Otherwise returns a value which represents a unique topological feature.
  */
 int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
@@ -643,17 +643,17 @@ int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
 
 
 /**
- * find_acpi_cpu_topology_package() - Determine a unique cpu package value
- * @cpu: Kernel logical cpu number
+ * find_acpi_cpu_topology_package() - Determine a unique CPU package value
+ * @cpu: Kernel logical CPU number
  *
- * Determine a topology unique package ID for the given cpu.
+ * Determine a topology unique package ID for the given CPU.
  * This ID can then be used to group peers, which will have matching ids.
  *
  * The search terminates when either a level is found with the PHYSICAL_PACKAGE
  * flag set or we reach a root node.
  *
- * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
- * Otherwise returns a value which represents the package for this cpu.
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
+ * Otherwise returns a value which represents the package for this CPU.
  */
 int find_acpi_cpu_topology_package(unsigned int cpu)
 {
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 446c959a8f08..b845dc3e0ba9 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -763,18 +763,16 @@ acpi_bus_get_ejd(acpi_handle handle, acpi_handle *ejd)
 }
 EXPORT_SYMBOL_GPL(acpi_bus_get_ejd);
 
-static int acpi_bus_extract_wakeup_device_power_package(acpi_handle handle,
-					struct acpi_device_wakeup *wakeup)
+static int acpi_bus_extract_wakeup_device_power_package(struct acpi_device *dev)
 {
+	acpi_handle handle = dev->handle;
+	struct acpi_device_wakeup *wakeup = &dev->wakeup;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *package = NULL;
 	union acpi_object *element = NULL;
 	acpi_status status;
 	int err = -ENODATA;
 
-	if (!wakeup)
-		return -EINVAL;
-
 	INIT_LIST_HEAD(&wakeup->resources);
 
 	/* _PRW */
@@ -848,9 +846,9 @@ static int acpi_bus_extract_wakeup_device_power_package(acpi_handle handle,
 static bool acpi_wakeup_gpe_init(struct acpi_device *device)
 {
 	static const struct acpi_device_id button_device_ids[] = {
-		{"PNP0C0C", 0},
-		{"PNP0C0D", 0},
-		{"PNP0C0E", 0},
+		{"PNP0C0C", 0},		/* Power button */
+		{"PNP0C0D", 0},		/* Lid */
+		{"PNP0C0E", 0},		/* Sleep button */
 		{"", 0},
 	};
 	struct acpi_device_wakeup *wakeup = &device->wakeup;
@@ -883,8 +881,7 @@ static void acpi_bus_get_wakeup_device_flags(struct acpi_device *device)
 	if (!acpi_has_method(device->handle, "_PRW"))
 		return;
 
-	err = acpi_bus_extract_wakeup_device_power_package(device->handle,
-							   &device->wakeup);
+	err = acpi_bus_extract_wakeup_device_power_package(device);
 	if (err) {
 		dev_err(&device->dev, "_PRW evaluation error: %d\n", err);
 		return;
@@ -895,7 +892,7 @@ static void acpi_bus_get_wakeup_device_flags(struct acpi_device *device)
 	/*
 	 * Call _PSW/_DSW object to disable its ability to wake the sleeping
 	 * system for the ACPI device with the _PRW object.
-	 * The _PSW object is depreciated in ACPI 3.0 and is replaced by _DSW.
+	 * The _PSW object is deprecated in ACPI 3.0 and is replaced by _DSW.
 	 * So it is necessary to call _DSW object first. Only when it is not
 	 * present will the _PSW object used.
 	 */
@@ -2260,7 +2257,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 
 	mutex_lock(&acpi_probe_mutex);
 	for (ape = ap_head; nr; ape++, nr--) {
-		if (ACPI_COMPARE_NAME(ACPI_SIG_MADT, ape->id)) {
+		if (ACPI_COMPARE_NAMESEG(ACPI_SIG_MADT, ape->id)) {
 			acpi_probe_count = 0;
 			acpi_table_parse_madt(ape->type, acpi_match_madt, 0);
 			count += acpi_probe_count;
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index c336784d0bcb..b34d05e365b7 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -28,7 +28,7 @@ EXPORT_SYMBOL(qdf2400_e44_present);
 
 /*
  * Some Qualcomm Datacenter Technologies SoCs have a defective UART BUSY bit.
- * Detect them by examining the OEM fields in the SPCR header, similiar to PCI
+ * Detect them by examining the OEM fields in the SPCR header, similar to PCI
  * quirk detection in pci_mcfg.c.
  */
 static bool qdf2400_erratum_44_present(struct acpi_table_header *h)
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index fa76f5e41b5c..75948a3f1a20 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -327,9 +327,9 @@ static struct kobject *hotplug_kobj;
 
 struct acpi_table_attr {
 	struct bin_attribute attr;
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	int instance;
-	char filename[ACPI_NAME_SIZE+ACPI_INST_SIZE];
+	char filename[ACPI_NAMESEG_SIZE+ACPI_INST_SIZE];
 	struct list_head node;
 };
 
@@ -368,10 +368,10 @@ static int acpi_table_attr_init(struct kobject *tables_obj,
 	char instance_str[ACPI_INST_SIZE];
 
 	sysfs_attr_init(&table_attr->attr.attr);
-	ACPI_MOVE_NAME(table_attr->name, table_header->signature);
+	ACPI_COPY_NAMESEG(table_attr->name, table_header->signature);
 
 	list_for_each_entry(attr, &acpi_table_attr_list, node) {
-		if (ACPI_COMPARE_NAME(table_attr->name, attr->name))
+		if (ACPI_COMPARE_NAMESEG(table_attr->name, attr->name))
 			if (table_attr->instance < attr->instance)
 				table_attr->instance = attr->instance;
 	}
@@ -382,8 +382,8 @@ static int acpi_table_attr_init(struct kobject *tables_obj,
 		return -ERANGE;
 	}
 
-	ACPI_MOVE_NAME(table_attr->filename, table_header->signature);
-	table_attr->filename[ACPI_NAME_SIZE] = '\0';
+	ACPI_COPY_NAMESEG(table_attr->filename, table_header->signature);
+	table_attr->filename[ACPI_NAMESEG_SIZE] = '\0';
 	if (table_attr->instance > 1 || (table_attr->instance == 1 &&
 					 !acpi_get_table
 					 (table_header->signature, 2, &header))) {
@@ -484,7 +484,7 @@ static int acpi_table_data_init(struct acpi_table_header *th)
 	int i;
 
 	for (i = 0; i < NUM_ACPI_DATA_OBJS; i++) {
-		if (ACPI_COMPARE_NAME(th->signature, acpi_data_objs[i].name)) {
+		if (ACPI_COMPARE_NAMESEG(th->signature, acpi_data_objs[i].name)) {
 			data_attr = kzalloc(sizeof(*data_attr), GFP_KERNEL);
 			if (!data_attr)
 				return -ENOMEM;
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 8fccbe49612a..d7bf936b1646 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -240,8 +240,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
  * On success returns sum of all matching entries for all proc handlers.
  * Otherwise, -ENODEV or -EINVAL is returned.
  */
-static int __init
-acpi_parse_entries_array(char *id, unsigned long table_size,
+static int __init acpi_parse_entries_array(char *id, unsigned long table_size,
 		struct acpi_table_header *table_header,
 		struct acpi_subtable_proc *proc, int proc_num,
 		unsigned int max_entries)
@@ -314,8 +313,7 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 	return errs ? -EINVAL : count;
 }
 
-int __init
-acpi_table_parse_entries_array(char *id,
+int __init acpi_table_parse_entries_array(char *id,
 			 unsigned long table_size,
 			 struct acpi_subtable_proc *proc, int proc_num,
 			 unsigned int max_entries)
@@ -346,8 +344,7 @@ acpi_table_parse_entries_array(char *id,
 	return count;
 }
 
-int __init
-acpi_table_parse_entries(char *id,
+int __init acpi_table_parse_entries(char *id,
 			unsigned long table_size,
 			int entry_id,
 			acpi_tbl_entry_handler handler,
@@ -362,8 +359,7 @@ acpi_table_parse_entries(char *id,
 						max_entries);
 }
 
-int __init
-acpi_table_parse_madt(enum acpi_madt_type id,
+int __init acpi_table_parse_madt(enum acpi_madt_type id,
 		      acpi_tbl_entry_handler handler, unsigned int max_entries)
 {
 	return acpi_table_parse_entries(ACPI_SIG_MADT,
@@ -670,8 +666,8 @@ static void __init acpi_table_initrd_scan(void)
 		table_length = table->length;
 
 		/* Skip RSDT/XSDT which should only be used for override */
-		if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_RSDT) ||
-		    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_XSDT)) {
+		if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_RSDT) ||
+		    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_XSDT)) {
 			acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
 			goto next_table;
 		}
@@ -725,8 +721,7 @@ static void *amlcode __attribute__ ((weakref("AmlCode")));
 static void *dsdt_amlcode __attribute__ ((weakref("dsdt_aml_code")));
 #endif
 
-acpi_status
-acpi_os_table_override(struct acpi_table_header *existing_table,
+acpi_status acpi_os_table_override(struct acpi_table_header *existing_table,
 		       struct acpi_table_header **new_table)
 {
 	if (!existing_table || !new_table)
@@ -788,7 +783,6 @@ static int __init acpi_parse_apic_instance(char *str)
 
 	return 0;
 }
-
 early_param("acpi_apic_instance", acpi_parse_apic_instance);
 
 static int __init acpi_force_table_verification_setup(char *s)
@@ -797,7 +791,6 @@ static int __init acpi_force_table_verification_setup(char *s)
 
 	return 0;
 }
-
 early_param("acpi_force_table_verification", acpi_force_table_verification_setup);
 
 static int __init acpi_force_32bit_fadt_addr(char *s)
@@ -807,5 +800,4 @@ static int __init acpi_force_32bit_fadt_addr(char *s)
 
 	return 0;
 }
-
 early_param("acpi_force_32bit_fadt_addr", acpi_force_32bit_fadt_addr);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index c4b06cc075f9..89363b245489 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -739,6 +739,7 @@ EXPORT_SYMBOL(acpi_dev_found);
 
 struct acpi_dev_match_info {
 	const char *dev_name;
+	struct acpi_device *adev;
 	struct acpi_device_id hid[2];
 	const char *uid;
 	s64 hrv;
@@ -759,6 +760,7 @@ static int acpi_dev_match_cb(struct device *dev, void *data)
 		return 0;
 
 	match->dev_name = acpi_dev_name(adev);
+	match->adev = adev;
 
 	if (match->hrv == -1)
 		return 1;
@@ -806,18 +808,20 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 EXPORT_SYMBOL(acpi_dev_present);
 
 /**
- * acpi_dev_get_first_match_name - Return name of first match of ACPI device
+ * acpi_dev_get_first_match_dev - Return the first match of ACPI device
  * @hid: Hardware ID of the device.
  * @uid: Unique ID of the device, pass NULL to not check _UID
  * @hrv: Hardware Revision of the device, pass -1 to not check _HRV
  *
- * Return device name if a matching device was present
+ * Return the first match of ACPI device if a matching device was present
  * at the moment of invocation, or NULL otherwise.
  *
+ * The caller is responsible to call put_device() on the returned device.
+ *
  * See additional information in acpi_dev_present() as well.
  */
-const char *
-acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
+struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv)
 {
 	struct acpi_dev_match_info match = {};
 	struct device *dev;
@@ -827,9 +831,9 @@ acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
 	match.hrv = hrv;
 
 	dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb);
-	return dev ? match.dev_name : NULL;
+	return dev ? match.adev : NULL;
 }
-EXPORT_SYMBOL(acpi_dev_get_first_match_name);
+EXPORT_SYMBOL(acpi_dev_get_first_match_dev);
 
 /*
  * acpi_backlight= handling, this is done here rather then in video_detect.c
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 43587ac680e4..31014c7d3793 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -112,7 +112,7 @@ static int video_detect_force_none(const struct dmi_system_id *d)
 static const struct dmi_system_id video_detect_dmi_table[] = {
 	/* On Samsung X360, the BIOS will set a flag (VDRV) if generic
 	 * ACPI backlight device is used. This flag will definitively break
-	 * the backlight interface (even the vendor interface) untill next
+	 * the backlight interface (even the vendor interface) until next
 	 * reboot. It's why we should prevent video.ko from being used here
 	 * and we can't rely on a later call to acpi_video_unregister().
 	 */
@@ -141,6 +141,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
 		},
 	},
+	{
+	.callback = video_detect_force_vendor,
+	.ident = "Sony VPCEH3U1E",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "VPCEH3U1E"),
+		},
+	},
 
 	/*
 	 * These models have a working acpi_video backlight control, and using
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 8c4435c53f09..6e787cc9e5b9 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -46,6 +46,8 @@ static struct clk_lookup *clk_find(const char *dev_id, const char *con_id)
 	if (con_id)
 		best_possible += 1;
 
+	lockdep_assert_held(&clocks_mutex);
+
 	list_for_each_entry(p, &clocks, node) {
 		match = 0;
 		if (p->dev_id) {
@@ -402,7 +404,10 @@ void devm_clk_release_clkdev(struct device *dev, const char *con_id,
 	struct clk_lookup *cl;
 	int rval;
 
+	mutex_lock(&clocks_mutex);
 	cl = clk_find(dev_id, con_id);
+	mutex_unlock(&clocks_mutex);
+
 	WARN_ON(!cl);
 	rval = devres_release(dev, devm_clkdev_release,
 			      devm_clk_match_clkdev, cl);
diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.c b/drivers/clk/sunxi-ng/ccu_nkmp.c
index 9b49adb20d07..cbcdf664f336 100644
--- a/drivers/clk/sunxi-ng/ccu_nkmp.c
+++ b/drivers/clk/sunxi-ng/ccu_nkmp.c
@@ -167,7 +167,7 @@ static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate,
 			   unsigned long parent_rate)
 {
 	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
-	u32 n_mask, k_mask, m_mask, p_mask;
+	u32 n_mask = 0, k_mask = 0, m_mask = 0, p_mask = 0;
 	struct _ccu_nkmp _nkmp;
 	unsigned long flags;
 	u32 reg;
@@ -186,10 +186,24 @@ static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	ccu_nkmp_find_best(parent_rate, rate, &_nkmp);
 
-	n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1, nkmp->n.shift);
-	k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1, nkmp->k.shift);
-	m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1, nkmp->m.shift);
-	p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1, nkmp->p.shift);
+	/*
+	 * If width is 0, GENMASK() macro may not generate expected mask (0)
+	 * as it falls under undefined behaviour by C standard due to shifts
+	 * which are equal or greater than width of left operand. This can
+	 * be easily avoided by explicitly checking if width is 0.
+	 */
+	if (nkmp->n.width)
+		n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1,
+				 nkmp->n.shift);
+	if (nkmp->k.width)
+		k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1,
+				 nkmp->k.shift);
+	if (nkmp->m.width)
+		m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1,
+				 nkmp->m.shift);
+	if (nkmp->p.width)
+		p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1,
+				 nkmp->p.shift);
 
 	spin_lock_irqsave(nkmp->common.lock, flags);
 
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index ea373cfbcecb..b2a951a798e2 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -149,6 +149,26 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
 	return val;
 }
 
+static u64 arch_counter_get_cntpct_stable(void)
+{
+	return __arch_counter_get_cntpct_stable();
+}
+
+static u64 arch_counter_get_cntpct(void)
+{
+	return __arch_counter_get_cntpct();
+}
+
+static u64 arch_counter_get_cntvct_stable(void)
+{
+	return __arch_counter_get_cntvct_stable();
+}
+
+static u64 arch_counter_get_cntvct(void)
+{
+	return __arch_counter_get_cntvct();
+}
+
 /*
  * Default to cp15 based access because arm64 uses this function for
  * sched_clock() before DT is probed and the cp15 method is guaranteed
@@ -316,13 +336,6 @@ static u64 notrace arm64_858921_read_cntvct_el0(void)
 }
 #endif
 
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-static u64 notrace arm64_1188873_read_cntvct_el0(void)
-{
-	return read_sysreg(cntvct_el0);
-}
-#endif
-
 #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
 /*
  * The low bits of the counter registers are indeterminate while bit 10 or
@@ -369,8 +382,7 @@ static u32 notrace sun50i_a64_read_cntv_tval_el0(void)
 DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround);
 EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
 
-DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
-EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
 
 static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
 						struct clock_event_device *clk)
@@ -454,14 +466,6 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.read_cntvct_el0 = arm64_858921_read_cntvct_el0,
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-	{
-		.match_type = ate_match_local_cap_id,
-		.id = (void *)ARM64_WORKAROUND_1188873,
-		.desc = "ARM erratum 1188873",
-		.read_cntvct_el0 = arm64_1188873_read_cntvct_el0,
-	},
-#endif
 #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
 	{
 		.match_type = ate_match_dt,
@@ -549,11 +553,8 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 			per_cpu(timer_unstable_counter_workaround, i) = wa;
 	}
 
-	/*
-	 * Use the locked version, as we're called from the CPU
-	 * hotplug framework. Otherwise, we end-up in deadlock-land.
-	 */
-	static_branch_enable_cpuslocked(&arch_timer_read_ool_enabled);
+	if (wa->read_cntvct_el0 || wa->read_cntpct_el0)
+		atomic_set(&timer_unstable_counter_workaround_in_use, 1);
 
 	/*
 	 * Don't use the vdso fastpath if errata require using the
@@ -570,7 +571,7 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type,
 					    void *arg)
 {
-	const struct arch_timer_erratum_workaround *wa;
+	const struct arch_timer_erratum_workaround *wa, *__wa;
 	ate_match_fn_t match_fn = NULL;
 	bool local = false;
 
@@ -594,53 +595,32 @@ static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type t
 	if (!wa)
 		return;
 
-	if (needs_unstable_timer_counter_workaround()) {
-		const struct arch_timer_erratum_workaround *__wa;
-		__wa = __this_cpu_read(timer_unstable_counter_workaround);
-		if (__wa && wa != __wa)
-			pr_warn("Can't enable workaround for %s (clashes with %s\n)",
-				wa->desc, __wa->desc);
+	__wa = __this_cpu_read(timer_unstable_counter_workaround);
+	if (__wa && wa != __wa)
+		pr_warn("Can't enable workaround for %s (clashes with %s\n)",
+			wa->desc, __wa->desc);
 
-		if (__wa)
-			return;
-	}
+	if (__wa)
+		return;
 
 	arch_timer_enable_workaround(wa, local);
 	pr_info("Enabling %s workaround for %s\n",
 		local ? "local" : "global", wa->desc);
 }
 
-#define erratum_handler(fn, r, ...)					\
-({									\
-	bool __val;							\
-	if (needs_unstable_timer_counter_workaround()) {		\
-		const struct arch_timer_erratum_workaround *__wa;	\
-		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		if (__wa && __wa->fn) {					\
-			r = __wa->fn(__VA_ARGS__);			\
-			__val = true;					\
-		} else {						\
-			__val = false;					\
-		}							\
-	} else {							\
-		__val = false;						\
-	}								\
-	__val;								\
-})
-
 static bool arch_timer_this_cpu_has_cntvct_wa(void)
 {
-	const struct arch_timer_erratum_workaround *wa;
+	return has_erratum_handler(read_cntvct_el0);
+}
 
-	wa = __this_cpu_read(timer_unstable_counter_workaround);
-	return wa && wa->read_cntvct_el0;
+static bool arch_timer_counter_has_wa(void)
+{
+	return atomic_read(&timer_unstable_counter_workaround_in_use);
 }
 #else
 #define arch_timer_check_ool_workaround(t,a)		do { } while(0)
-#define erratum_set_next_event_tval_virt(...)		({BUG(); 0;})
-#define erratum_set_next_event_tval_phys(...)		({BUG(); 0;})
-#define erratum_handler(fn, r, ...)			({false;})
 #define arch_timer_this_cpu_has_cntvct_wa()		({false;})
+#define arch_timer_counter_has_wa()			({false;})
 #endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
 
 static __always_inline irqreturn_t timer_handler(const int access,
@@ -733,11 +713,6 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
 {
-	int ret;
-
-	if (erratum_handler(set_next_event_virt, ret, evt, clk))
-		return ret;
-
 	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
@@ -745,11 +720,6 @@ static int arch_timer_set_next_event_virt(unsigned long evt,
 static int arch_timer_set_next_event_phys(unsigned long evt,
 					  struct clock_event_device *clk)
 {
-	int ret;
-
-	if (erratum_handler(set_next_event_phys, ret, evt, clk))
-		return ret;
-
 	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
@@ -774,6 +744,10 @@ static void __arch_timer_setup(unsigned type,
 	clk->features = CLOCK_EVT_FEAT_ONESHOT;
 
 	if (type == ARCH_TIMER_TYPE_CP15) {
+		typeof(clk->set_next_event) sne;
+
+		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+
 		if (arch_timer_c3stop)
 			clk->features |= CLOCK_EVT_FEAT_C3STOP;
 		clk->name = "arch_sys_timer";
@@ -784,20 +758,20 @@ static void __arch_timer_setup(unsigned type,
 		case ARCH_TIMER_VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
-			clk->set_next_event = arch_timer_set_next_event_virt;
+			sne = erratum_handler(set_next_event_virt);
 			break;
 		case ARCH_TIMER_PHYS_SECURE_PPI:
 		case ARCH_TIMER_PHYS_NONSECURE_PPI:
 		case ARCH_TIMER_HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
-			clk->set_next_event = arch_timer_set_next_event_phys;
+			sne = erratum_handler(set_next_event_phys);
 			break;
 		default:
 			BUG();
 		}
 
-		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+		clk->set_next_event = sne;
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -830,7 +804,11 @@ static void arch_timer_evtstrm_enable(int divider)
 	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
 			| ARCH_TIMER_VIRT_EVT_EN;
 	arch_timer_set_cntkctl(cntkctl);
+#ifdef CONFIG_ARM64
+	cpu_set_named_feature(EVTSTRM);
+#else
 	elf_hwcap |= HWCAP_EVTSTRM;
+#endif
 #ifdef CONFIG_COMPAT
 	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
 #endif
@@ -995,12 +973,22 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_TIMER_TYPE_CP15) {
+		u64 (*rd)(void);
+
 		if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
-		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
-			arch_timer_read_counter = arch_counter_get_cntvct;
-		else
-			arch_timer_read_counter = arch_counter_get_cntpct;
+		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) {
+			if (arch_timer_counter_has_wa())
+				rd = arch_counter_get_cntvct_stable;
+			else
+				rd = arch_counter_get_cntvct;
+		} else {
+			if (arch_timer_counter_has_wa())
+				rd = arch_counter_get_cntpct_stable;
+			else
+				rd = arch_counter_get_cntpct;
+		}
 
+		arch_timer_read_counter = rd;
 		clocksource_counter.archdata.vdso_direct = vdso_default;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
@@ -1052,7 +1040,11 @@ static int arch_timer_cpu_pm_notify(struct notifier_block *self,
 	} else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) {
 		arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
 
+#ifdef CONFIG_ARM64
+		if (cpu_have_named_feature(EVTSTRM))
+#else
 		if (elf_hwcap & HWCAP_EVTSTRM)
+#endif
 			cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
 	}
 	return NOTIFY_OK;
diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
index 4c97478d44bd..5826c2c98a50 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
@@ -303,8 +303,6 @@ static void post_se_instr(struct nitrox_softreq *sr,
 
 	/* Ring doorbell with count 1 */
 	writeq(1, cmdq->dbell_csr_addr);
-	/* orders the doorbell rings */
-	mmiowb();
 
 	cmdq->write_idx = incr_index(idx, 1, ndev->qlen);
 
@@ -599,8 +597,6 @@ void pkt_slc_resp_tasklet(unsigned long data)
 	 * MSI-X interrupt generates if Completion count > Threshold
 	 */
 	writeq(slc_cnts.value, cmdq->compl_cnt_csr_addr);
-	/* order the writes */
-	mmiowb();
 
 	if (atomic_read(&cmdq->backlog_count))
 		schedule_work(&cmdq->backlog_qflush);
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index eb45af71d3a3..e8d0881b64d8 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -327,7 +327,6 @@ static void txx9dmac_reset_chan(struct txx9dmac_chan *dc)
 	channel_writel(dc, SAIR, 0);
 	channel_writel(dc, DAIR, 0);
 	channel_writel(dc, CCR, 0);
-	mmiowb();
 }
 
 /* Called with dc->lock held and bh disabled */
@@ -954,7 +953,6 @@ static void txx9dmac_chain_dynamic(struct txx9dmac_chan *dc,
 	dma_sync_single_for_device(chan2parent(&dc->chan),
 				   prev->txd.phys, ddev->descsize,
 				   DMA_TO_DEVICE);
-	mmiowb();
 	if (!(channel_readl(dc, CSR) & TXX9_DMA_CSR_CHNEN) &&
 	    channel_read_CHAR(dc) == prev->txd.phys)
 		/* Restart chain DMA */
@@ -1080,7 +1078,6 @@ static void txx9dmac_free_chan_resources(struct dma_chan *chan)
 static void txx9dmac_off(struct txx9dmac_dev *ddev)
 {
 	dma_writel(ddev, MCR, 0);
-	mmiowb();
 }
 
 static int __init txx9dmac_chan_probe(struct platform_device *pdev)
diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index a983708b77a6..50f9402fb325 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -333,7 +333,7 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 	struct axp288_extcon_info *info;
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
 	struct device *dev = &pdev->dev;
-	const char *name;
+	struct acpi_device *adev;
 	int ret, i, pirq;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
@@ -357,9 +357,10 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 
-		name = acpi_dev_get_first_match_name("INT3496", NULL, -1);
-		if (name) {
-			info->id_extcon = extcon_get_extcon_dev(name);
+		adev = acpi_dev_get_first_match_dev("INT3496", NULL, -1);
+		if (adev) {
+			info->id_extcon = extcon_get_extcon_dev(acpi_dev_name(adev));
+			put_device(&adev->dev);
 			if (!info->id_extcon)
 				return -EPROBE_DEFER;
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 45c048751f3b..7183ab34269e 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2939,7 +2939,6 @@ static void set_multichannel_mask(struct fw_ohci *ohci, u64 channels)
 	reg_write(ohci, OHCI1394_IRMultiChanMaskLoClear, ~lo);
 	reg_write(ohci, OHCI1394_IRMultiChanMaskHiSet, hi);
 	reg_write(ohci, OHCI1394_IRMultiChanMaskLoSet, lo);
-	mmiowb();
 	ohci->mc_channels = channels;
 }
 
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index e6376f985ef7..9cd70d1a5622 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -165,6 +165,7 @@ static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
 
 	return err;
 }
+NOKPROBE_SYMBOL(invoke_sdei_fn);
 
 static struct sdei_event *sdei_event_find(u32 event_num)
 {
@@ -879,6 +880,7 @@ static void sdei_smccc_smc(unsigned long function_id,
 {
 	arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
 }
+NOKPROBE_SYMBOL(sdei_smccc_smc);
 
 static void sdei_smccc_hvc(unsigned long function_id,
 			   unsigned long arg0, unsigned long arg1,
@@ -887,6 +889,7 @@ static void sdei_smccc_hvc(unsigned long function_id,
 {
 	arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
 }
+NOKPROBE_SYMBOL(sdei_smccc_hvc);
 
 int sdei_register_ghes(struct ghes *ghes, sdei_event_callback *normal_cb,
 		       sdei_event_callback *critical_cb)
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 099d83e4e910..fae2d5c43314 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -416,11 +416,8 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v)
 	nr++;
 }
 
-void __init dmi_memdev_walk(void)
+static void __init dmi_memdev_walk(void)
 {
-	if (!dmi_available)
-		return;
-
 	if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) {
 		dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr);
 		if (dmi_memdev)
@@ -614,7 +611,7 @@ static int __init dmi_smbios3_present(const u8 *buf)
 	return 1;
 }
 
-void __init dmi_scan_machine(void)
+static void __init dmi_scan_machine(void)
 {
 	char __iomem *p, *q;
 	char buf[32];
@@ -769,15 +766,20 @@ static int __init dmi_init(void)
 subsys_initcall(dmi_init);
 
 /**
- * dmi_set_dump_stack_arch_desc - set arch description for dump_stack()
+ *	dmi_setup - scan and setup DMI system information
  *
- * Invoke dump_stack_set_arch_desc() with DMI system information so that
- * DMI identifiers are printed out on task dumps.  Arch boot code should
- * call this function after dmi_scan_machine() if it wants to print out DMI
- * identifiers on task dumps.
+ *	Scan the DMI system information. This setups DMI identifiers
+ *	(dmi_system_id) for printing it out on task dumps and prepares
+ *	DIMM entry information (dmi_memdev_info) from the SMBIOS table
+ *	for using this when reporting memory errors.
  */
-void __init dmi_set_dump_stack_arch_desc(void)
+void __init dmi_setup(void)
 {
+	dmi_scan_machine();
+	if (!dmi_available)
+		return;
+
+	dmi_memdev_walk();
 	dump_stack_set_arch_desc("%s", dmi_ids_string);
 }
 
@@ -841,7 +843,7 @@ static bool dmi_is_end_of_table(const struct dmi_system_id *dmi)
  *	returns non zero or we hit the end. Callback function is called for
  *	each successful match. Returns the number of matches.
  *
- *	dmi_scan_machine must be called before this function is called.
+ *	dmi_setup must be called before this function is called.
  */
 int dmi_check_system(const struct dmi_system_id *list)
 {
@@ -871,7 +873,7 @@ EXPORT_SYMBOL(dmi_check_system);
  *	Walk the blacklist table until the first match is found.  Return the
  *	pointer to the matching entry or NULL if there's no match.
  *
- *	dmi_scan_machine must be called before this function is called.
+ *	dmi_setup must be called before this function is called.
  */
 const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list)
 {
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 0c1af675c338..e2ac5fa5531b 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -162,13 +162,11 @@ void efi_virtmap_unload(void)
 static int __init arm_dmi_init(void)
 {
 	/*
-	 * On arm64/ARM, DMI depends on UEFI, and dmi_scan_machine() needs to
+	 * On arm64/ARM, DMI depends on UEFI, and dmi_setup() needs to
 	 * be called early because dmi_id_init(), which is an arch_initcall
 	 * itself, depends on dmi_scan_machine() having been called already.
 	 */
-	dmi_scan_machine();
-	if (dmi_available)
-		dmi_set_dump_stack_arch_desc();
+	dmi_setup();
 	return 0;
 }
 core_initcall(arm_dmi_init);
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index b0103e16fc1b..0460c7581220 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -16,9 +16,9 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 
 # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
 # disable the stackleak plugin
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
-				   $(DISABLE_STACKLEAK_PLUGIN)
-cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM64)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
+				   -fpie $(DISABLE_STACKLEAK_PLUGIN)
+cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
 
@@ -71,7 +71,6 @@ CFLAGS_arm64-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 extra-$(CONFIG_EFI_ARMSTUB)	:= $(lib-y)
 lib-$(CONFIG_EFI_ARMSTUB)	:= $(patsubst %.o,%.stub.o,$(lib-y))
 
-STUBCOPY_RM-y			:= -R *ksymtab* -R *kcrctab*
 STUBCOPY_FLAGS-$(CONFIG_ARM64)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
 STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
@@ -86,12 +85,13 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 # this time, use objcopy and leave all sections in place.
 #
 quiet_cmd_stubcopy = STUBCPY $@
-      cmd_stubcopy = if $(STRIP) --strip-debug $(STUBCOPY_RM-y) -o $@ $<; \
-		     then if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); \
-		     then (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
-			   rm -f $@; /bin/false);			  \
-		     else $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; fi	  \
-		     else /bin/false; fi
+      cmd_stubcopy =							\
+	$(STRIP) --strip-debug -o $@ $<;				\
+	if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); then		\
+		echo "$@: absolute symbol references not allowed in the EFI stub" >&2; \
+		/bin/false;						\
+	fi;								\
+	$(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@
 
 #
 # ARM discards the .data section because it disallows r/w data in the
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index c51462f5aa1e..a5dc0629f225 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -425,7 +425,7 @@ static ssize_t ibft_attr_show_acpitbl(void *data, int type, char *buf)
 
 	switch (type) {
 	case ISCSI_BOOT_ACPITBL_SIGNATURE:
-		str += sprintf_string(str, ACPI_NAME_SIZE,
+		str += sprintf_string(str, ACPI_NAMESEG_SIZE,
 				      entry->header->header.signature);
 		break;
 	case ISCSI_BOOT_ACPITBL_OEM_ID:
diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 7c659fdaa6d5..3302125e5265 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -377,10 +377,20 @@ static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
 	}
 }
 
-static const char *mrfld_gpio_get_pinctrl_dev_name(void)
+static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv)
 {
-	const char *dev_name = acpi_dev_get_first_match_name("INTC1002", NULL, -1);
-	return dev_name ? dev_name : "pinctrl-merrifield";
+	struct acpi_device *adev;
+	const char *name;
+
+	adev = acpi_dev_get_first_match_dev("INTC1002", NULL, -1);
+	if (adev) {
+		name = devm_kstrdup(priv->dev, acpi_dev_name(adev), GFP_KERNEL);
+		acpi_dev_put(adev);
+	} else {
+		name = "pinctrl-merrifield";
+	}
+
+	return name;
 }
 
 static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -441,7 +451,7 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		return retval;
 	}
 
-	pinctrl_dev_name = mrfld_gpio_get_pinctrl_dev_name();
+	pinctrl_dev_name = mrfld_gpio_get_pinctrl_dev_name(priv);
 	for (i = 0; i < ARRAY_SIZE(mrfld_gpio_ranges); i++) {
 		range = &mrfld_gpio_ranges[i];
 		retval = gpiochip_add_pin_range(&priv->chip,
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 2b4f373736c7..8b4cd31ce7bd 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -106,25 +106,19 @@
 static noinline void save_stack(struct drm_mm_node *node)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = STACKDEPTH,
-		.skip = 1
-	};
+	unsigned int n;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
 
 	/* May be called under spinlock, so avoid sleeping */
-	node->stack = depot_save_stack(&trace, GFP_NOWAIT);
+	node->stack = stack_depot_save(entries, n, GFP_NOWAIT);
 }
 
 static void show_leaks(struct drm_mm *mm)
 {
 	struct drm_mm_node *node;
-	unsigned long entries[STACKDEPTH];
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char *buf;
 
 	buf = kmalloc(BUFSZ, GFP_KERNEL);
@@ -132,19 +126,14 @@ static void show_leaks(struct drm_mm *mm)
 		return;
 
 	list_for_each_entry(node, drm_mm_nodes(mm), node_list) {
-		struct stack_trace trace = {
-			.entries = entries,
-			.max_entries = STACKDEPTH
-		};
-
 		if (!node->stack) {
 			DRM_ERROR("node [%08llx + %08llx]: unknown owner\n",
 				  node->start, node->size);
 			continue;
 		}
 
-		depot_fetch_stack(node->stack, &trace);
-		snprint_stack_trace(buf, BUFSZ, &trace, 0);
+		nr_entries = stack_depot_fetch(node->stack, &entries);
+		stack_trace_snprint(buf, BUFSZ, entries, nr_entries, 0);
 		DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s",
 			  node->start, node->size, buf);
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 02adcaf6ebea..16f80a448820 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1667,6 +1667,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 					     len)) {
 end_user:
 				user_access_end();
+end:
 				kvfree(relocs);
 				err = -EFAULT;
 				goto err;
@@ -1686,7 +1687,7 @@ end_user:
 		 * relocations were valid.
 		 */
 		if (!user_access_begin(urelocs, size))
-			goto end_user;
+			goto end;
 
 		for (copied = 0; copied < nreloc; copied++)
 			unsafe_put_user(-1,
@@ -2695,7 +2696,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		 * when we did the "copy_from_user()" above.
 		 */
 		if (!user_access_begin(user_exec_list, count * sizeof(*user_exec_list)))
-			goto end_user;
+			goto end;
 
 		for (i = 0; i < args->buffer_count; i++) {
 			if (!(exec2_list[i].offset & UPDATE))
@@ -2709,6 +2710,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		}
 end_user:
 		user_access_end();
+end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index b713bed20c38..41b5bcb803cb 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -36,11 +36,8 @@
 
 static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 {
-	unsigned long entries[12];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char buf[512];
 
 	if (!vma->node.stack) {
@@ -49,8 +46,8 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 		return;
 	}
 
-	depot_fetch_stack(vma->node.stack, &trace);
-	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	nr_entries = stack_depot_fetch(vma->node.stack, &entries);
+	stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0);
 	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
 			 vma->node.start, vma->node.size, reason, buf);
 }
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index f125a62eba8c..a46bffe2b288 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -182,7 +182,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(VIDEO_DIP_CTL, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VIDEO_DIP_DATA, *data);
 		data++;
@@ -190,7 +189,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VIDEO_DIP_DATA, 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -237,7 +235,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -245,7 +242,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -298,7 +294,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -306,7 +301,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -352,7 +346,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -360,7 +353,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -406,7 +398,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), *data);
@@ -416,7 +407,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	for (; i < data_size; i += 4)
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), 0);
-	mmiowb();
 
 	val |= hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index a017a4232c0f..20c4434474e3 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -60,31 +60,20 @@
 static noinline depot_stack_handle_t __save_depot_stack(void)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-		.skip = 1,
-	};
+	unsigned int n;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries &&
-	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
-		trace.nr_entries--;
-
-	return depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
 }
 
 static void __print_depot_stack(depot_stack_handle_t stack,
 				char *buf, int sz, int indent)
 {
-	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 
-	depot_fetch_stack(stack, &trace);
-	snprint_stack_trace(buf, sz, &trace, indent);
+	nr_entries = stack_depot_fetch(stack, &entries);
+	stack_trace_snprint(buf, sz, entries, nr_entries, indent);
 }
 
 static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 578d867a81d5..f33e349c4ec5 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -255,10 +255,14 @@ static struct drm_driver qxl_driver = {
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = qxl_debugfs_init,
 #endif
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_pin = qxl_gem_prime_pin,
 	.gem_prime_unpin = qxl_gem_prime_unpin,
+	.gem_prime_get_sg_table = qxl_gem_prime_get_sg_table,
+	.gem_prime_import_sg_table = qxl_gem_prime_import_sg_table,
 	.gem_prime_vmap = qxl_gem_prime_vmap,
 	.gem_prime_vunmap = qxl_gem_prime_vunmap,
 	.gem_prime_mmap = qxl_gem_prime_mmap,
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index 8b448eca1cd9..114653b471c6 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -42,6 +42,18 @@ void qxl_gem_prime_unpin(struct drm_gem_object *obj)
 	qxl_bo_unpin(bo);
 }
 
+struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+struct drm_gem_object *qxl_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *table)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 void *qxl_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct qxl_bo *bo = gem_to_qxl_bo(obj);
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index bb8e3f149979..d464799e40a3 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -426,8 +426,7 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 
 	pm_runtime_get_sync(dev->dev);
 
-	if (dev->suspended) {
-		dev_err(dev->dev, "Error %s call while suspended\n", __func__);
+	if (dev_WARN_ONCE(dev->dev, dev->suspended, "Transfer while suspended\n")) {
 		ret = -ESHUTDOWN;
 		goto done_nolock;
 	}
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index c0c3043b5d61..fd70b110e8f4 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -515,9 +515,9 @@ static int i2c_imx_clk_notifier_call(struct notifier_block *nb,
 				     unsigned long action, void *data)
 {
 	struct clk_notifier_data *ndata = data;
-	struct imx_i2c_struct *i2c_imx = container_of(&ndata->clk,
+	struct imx_i2c_struct *i2c_imx = container_of(nb,
 						      struct imx_i2c_struct,
-						      clk);
+						      clk_change_nb);
 
 	if (action & POST_RATE_CHANGE)
 		i2c_imx_set_clk(i2c_imx, ndata->new_rate);
diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c
index d18b0941b71a..f14d4b3fab44 100644
--- a/drivers/i2c/busses/i2c-synquacer.c
+++ b/drivers/i2c/busses/i2c-synquacer.c
@@ -597,6 +597,8 @@ static int synquacer_i2c_probe(struct platform_device *pdev)
 	i2c->adapter = synquacer_i2c_ops;
 	i2c_set_adapdata(&i2c->adapter, i2c);
 	i2c->adapter.dev.parent = &pdev->dev;
+	i2c->adapter.dev.of_node = pdev->dev.of_node;
+	ACPI_COMPANION_SET(&i2c->adapter.dev, ACPI_COMPANION(&pdev->dev));
 	i2c->adapter.nr = pdev->id;
 	init_completion(&i2c->completion);
 
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 38af18645133..688aa3b5f3ac 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -185,7 +185,7 @@ static int i2c_generic_bus_free(struct i2c_adapter *adap)
 int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 {
 	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
-	int i = 0, scl = 1, ret;
+	int i = 0, scl = 1, ret = 0;
 
 	if (bri->prepare_recovery)
 		bri->prepare_recovery(adap);
@@ -327,6 +327,8 @@ static int i2c_device_probe(struct device *dev)
 
 		if (client->flags & I2C_CLIENT_HOST_NOTIFY) {
 			dev_dbg(dev, "Using Host Notify IRQ\n");
+			/* Keep adapter active when Host Notify is required */
+			pm_runtime_get_sync(&client->adapter->dev);
 			irq = i2c_smbus_host_notify_to_irq(client);
 		} else if (dev->of_node) {
 			irq = of_irq_get_byname(dev->of_node, "irq");
@@ -431,6 +433,8 @@ static int i2c_device_remove(struct device *dev)
 	device_init_wakeup(&client->dev, false);
 
 	client->irq = client->init_irq;
+	if (client->flags & I2C_CLIENT_HOST_NOTIFY)
+		pm_runtime_put(&client->adapter->dev);
 
 	return status;
 }
diff --git a/drivers/ide/tx4939ide.c b/drivers/ide/tx4939ide.c
index 67d4a7d4acc8..88d132edc4e3 100644
--- a/drivers/ide/tx4939ide.c
+++ b/drivers/ide/tx4939ide.c
@@ -156,7 +156,6 @@ static u16 tx4939ide_check_error_ints(ide_hwif_t *hwif)
 		u16 sysctl = tx4939ide_readw(base, TX4939IDE_Sys_Ctl);
 
 		tx4939ide_writew(sysctl | 0x4000, base, TX4939IDE_Sys_Ctl);
-		mmiowb();
 		/* wait 12GBUSCLK (typ. 60ns @ GBUS200MHz, max 270ns) */
 		ndelay(270);
 		tx4939ide_writew(sysctl, base, TX4939IDE_Sys_Ctl);
@@ -396,7 +395,6 @@ static void tx4939ide_init_hwif(ide_hwif_t *hwif)
 
 	/* Soft Reset */
 	tx4939ide_writew(0x8000, base, TX4939IDE_Sys_Ctl);
-	mmiowb();
 	/* at least 20 GBUSCLK (typ. 100ns @ GBUS200MHz, max 450ns) */
 	ndelay(450);
 	tx4939ide_writew(0x0000, base, TX4939IDE_Sys_Ctl);
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 7843e89235c3..c489f545baae 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -895,7 +895,7 @@ static vm_fault_t rdma_umap_fault(struct vm_fault *vmf)
 
 	/* Read only pages can just use the system zero page. */
 	if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) {
-		vmf->page = ZERO_PAGE(vmf->vm_start);
+		vmf->page = ZERO_PAGE(vmf->address);
 		get_page(vmf->page);
 		return 0;
 	}
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9784c6c0d2ec..addefae16c9c 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -8365,7 +8365,6 @@ static inline void clear_recv_intr(struct hfi1_ctxtdata *rcd)
 	struct hfi1_devdata *dd = rcd->dd;
 	u32 addr = CCE_INT_CLEAR + (8 * rcd->ireg);
 
-	mmiowb();	/* make sure everything before is written */
 	write_csr(dd, addr, rcd->imask);
 	/* force the above write on the chip and get a value back */
 	(void)read_csr(dd, addr);
@@ -11803,12 +11802,10 @@ void update_usrhead(struct hfi1_ctxtdata *rcd, u32 hd, u32 updegr, u32 egrhd,
 			<< RCV_EGR_INDEX_HEAD_HEAD_SHIFT;
 		write_uctxt_csr(dd, ctxt, RCV_EGR_INDEX_HEAD, reg);
 	}
-	mmiowb();
 	reg = ((u64)rcv_intr_count << RCV_HDR_HEAD_COUNTER_SHIFT) |
 		(((u64)hd & RCV_HDR_HEAD_HEAD_MASK)
 			<< RCV_HDR_HEAD_HEAD_SHIFT);
 	write_uctxt_csr(dd, ctxt, RCV_HDR_HEAD, reg);
-	mmiowb();
 }
 
 u32 hdrqempty(struct hfi1_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index a1de566fe95e..16ba9d52e1b9 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -1578,7 +1578,6 @@ void hfi1_sc_wantpiobuf_intr(struct send_context *sc, u32 needint)
 		sc_del_credit_return_intr(sc);
 	trace_hfi1_wantpiointr(sc, needint, sc->credit_ctrl);
 	if (needint) {
-		mmiowb();
 		sc_return_credits(sc);
 	}
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 97515c340134..c8555f7704d8 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1750,8 +1750,6 @@ static int hns_roce_v1_post_mbox(struct hns_roce_dev *hr_dev, u64 in_param,
 
 	writel(val, hcr + 5);
 
-	mmiowb();
-
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_osdep.h b/drivers/infiniband/hw/i40iw/i40iw_osdep.h
index f27be3e7830b..d474aad62a81 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_osdep.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_osdep.h
@@ -211,7 +211,7 @@ enum i40iw_status_code i40iw_hw_manage_vf_pble_bp(struct i40iw_device *iwdev,
 struct i40iw_sc_vsi;
 void i40iw_hw_stats_start_timer(struct i40iw_sc_vsi *vsi);
 void i40iw_hw_stats_stop_timer(struct i40iw_sc_vsi *vsi);
-#define i40iw_mmiowb() mmiowb()
+#define i40iw_mmiowb() do { } while (0)
 void i40iw_wr32(struct i40iw_hw *hw, u32 reg, u32 value);
 u32  i40iw_rd32(struct i40iw_hw *hw, u32 reg);
 #endif				/* _I40IW_OSDEP_H_ */
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 429a59c5801c..9426936460f8 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -3744,12 +3744,6 @@ out:
 		writel_relaxed(qp->doorbell_qpn,
 			to_mdev(ibqp->device)->uar_map + MLX4_SEND_DOORBELL);
 
-		/*
-		 * Make sure doorbells don't leak out of SQ spinlock
-		 * and reach the HCA out of order.
-		 */
-		mmiowb();
-
 		stamp_send_wqe(qp, ind + qp->sq_spare_wqes - 1);
 
 		qp->sq_next_wqe = ind;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8870c350fda0..8aafb2208899 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -5126,7 +5126,6 @@ out:
 		/* Make sure doorbells don't leak out of SQ spinlock
 		 * and reach the HCA out of order.
 		 */
-		mmiowb();
 		bf->offset ^= bf->buf_size;
 	}
 
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 83aa47eb81a9..bdf5ed38de22 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -292,12 +292,6 @@ static int mthca_cmd_post(struct mthca_dev *dev,
 		err = mthca_cmd_post_hcr(dev, in_param, out_param, in_modifier,
 					 op_modifier, op, token, event);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	mutex_unlock(&dev->cmd.hcr_mutex);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c
index a6531ffe29a6..877a6daffa98 100644
--- a/drivers/infiniband/hw/mthca/mthca_cq.c
+++ b/drivers/infiniband/hw/mthca/mthca_cq.c
@@ -211,11 +211,6 @@ static inline void update_cons_index(struct mthca_dev *dev, struct mthca_cq *cq,
 		mthca_write64(MTHCA_TAVOR_CQ_DB_INC_CI | cq->cqn, incr - 1,
 			      dev->kar + MTHCA_CQ_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-		/*
-		 * Make sure doorbells don't leak out of CQ spinlock
-		 * and reach the HCA out of order:
-		 */
-		mmiowb();
 	}
 }
 
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 7a5b25d13faa..d65b189f20ea 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -1809,11 +1809,6 @@ out:
 			      (qp->qpn << 8) | size0,
 			      dev->kar + MTHCA_SEND_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-		/*
-		 * Make sure doorbells don't leak out of SQ spinlock
-		 * and reach the HCA out of order:
-		 */
-		mmiowb();
 	}
 
 	qp->sq.next_ind = ind;
@@ -1924,12 +1919,6 @@ out:
 	qp->rq.next_ind = ind;
 	qp->rq.head    += nreq;
 
-	/*
-	 * Make sure doorbells don't leak out of RQ spinlock and reach
-	 * the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->rq.lock, flags);
 	return err;
 }
@@ -2164,12 +2153,6 @@ out:
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
-	/*
-	 * Make sure doorbells don't leak out of SQ spinlock and reach
-	 * the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c
index 06b920385512..a85935ccce88 100644
--- a/drivers/infiniband/hw/mthca/mthca_srq.c
+++ b/drivers/infiniband/hw/mthca/mthca_srq.c
@@ -570,12 +570,6 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
-	/*
-	 * Make sure doorbells don't leak out of SRQ spinlock and
-	 * reach the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&srq->lock, flags);
 	return err;
 }
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 59ad4202422c..8686a98e113d 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -773,9 +773,6 @@ static void doorbell_cq(struct qedr_cq *cq, u32 cons, u8 flags)
 	cq->db.data.agg_flags = flags;
 	cq->db.data.value = cpu_to_le32(cons);
 	writeq(cq->db.raw, cq->db_addr);
-
-	/* Make sure write would stick */
-	mmiowb();
 }
 
 int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
@@ -2084,8 +2081,6 @@ static int qedr_update_qp_state(struct qedr_dev *dev,
 
 			if (rdma_protocol_roce(&dev->ibdev, 1)) {
 				writel(qp->rq.db_data.raw, qp->rq.db);
-				/* Make sure write takes effect */
-				mmiowb();
 			}
 			break;
 		case QED_ROCE_QP_STATE_ERR:
@@ -3502,9 +3497,6 @@ int qedr_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 	smp_wmb();
 	writel(qp->sq.db_data.raw, qp->sq.db);
 
-	/* Make sure write sticks */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->q_lock, flags);
 
 	return rc;
@@ -3695,12 +3687,8 @@ int qedr_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 		writel(qp->rq.db_data.raw, qp->rq.db);
 
-		/* Make sure write sticks */
-		mmiowb();
-
 		if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
 			writel(qp->rq.iwarp_db2_data.raw, qp->rq.iwarp_db2);
-			mmiowb();	/* for second doorbell */
 		}
 
 		wr = wr->next;
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index cdbf707fa267..531d8a1db2c3 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -1884,7 +1884,6 @@ static void qib_6120_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 	qib_write_kreg(dd, kr_scratch, 0xfeeddeaf);
 	writel(pa, tidp32);
 	qib_write_kreg(dd, kr_scratch, 0xdeadbeef);
-	mmiowb();
 	spin_unlock_irqrestore(tidlockp, flags);
 }
 
@@ -1928,7 +1927,6 @@ static void qib_6120_put_tid_2(struct qib_devdata *dd, u64 __iomem *tidptr,
 			pa |= 2 << 29;
 	}
 	writel(pa, tidp32);
-	mmiowb();
 }
 
 
@@ -2053,9 +2051,7 @@ static void qib_update_6120_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 {
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_6120_hdrqempty(struct qib_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index 9fde45538f6e..ea3ddb05cbad 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -2175,7 +2175,6 @@ static void qib_7220_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 		pa = chippa;
 	}
 	writeq(pa, tidptr);
-	mmiowb();
 }
 
 /**
@@ -2704,9 +2703,7 @@ static void qib_update_7220_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 {
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_7220_hdrqempty(struct qib_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 17d6b24b3473..ac6a84f11ad0 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -3793,7 +3793,6 @@ static void qib_7322_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 		pa = chippa;
 	}
 	writeq(pa, tidptr);
-	mmiowb();
 }
 
 /**
@@ -4440,10 +4439,8 @@ static void qib_update_7322_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 		adjust_rcv_timeout(rcd, npkts);
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_7322_hdrqempty(struct qib_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/qib/qib_sd7220.c b/drivers/infiniband/hw/qib/qib_sd7220.c
index 12caf3db8c34..4f4a09c2dbcd 100644
--- a/drivers/infiniband/hw/qib/qib_sd7220.c
+++ b/drivers/infiniband/hw/qib/qib_sd7220.c
@@ -1068,7 +1068,6 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 	for (idx = 0; idx < NUM_DDS_REGS; ++idx) {
 		data = ((dds_reg_map & 0xF) << 4) | TX_FAST_ELT;
 		writeq(data, iaddr + idx);
-		mmiowb();
 		qib_read_kreg32(dd, kr_scratch);
 		dds_reg_map >>= 4;
 		for (midx = 0; midx < DDS_ROWS; ++midx) {
@@ -1076,7 +1075,6 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 
 			data = dds_init_vals[midx].reg_vals[idx];
 			writeq(data, daddr);
-			mmiowb();
 			qib_read_kreg32(dd, kr_scratch);
 		} /* End inner for (vals for this reg, each row) */
 	} /* end outer for (regs to be stored) */
@@ -1098,13 +1096,11 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 		didx = idx + min_idx;
 		/* Store the next RXEQ register address */
 		writeq(rxeq_init_vals[idx].rdesc, iaddr + didx);
-		mmiowb();
 		qib_read_kreg32(dd, kr_scratch);
 		/* Iterate through RXEQ values */
 		for (vidx = 0; vidx < 4; vidx++) {
 			data = rxeq_init_vals[idx].rdata[vidx];
 			writeq(data, taddr + (vidx << 6) + idx);
-			mmiowb();
 			qib_read_kreg32(dd, kr_scratch);
 		}
 	} /* end outer for (Reg-writes for RXEQ) */
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 1ecef76225a1..2a48ea3f1b30 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -150,7 +150,7 @@ struct dm_buffer {
 	void (*end_io)(struct dm_buffer *, blk_status_t);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 #define MAX_STACK 10
-	struct stack_trace stack_trace;
+	unsigned int stack_len;
 	unsigned long stack_entries[MAX_STACK];
 #endif
 };
@@ -232,11 +232,7 @@ static DEFINE_MUTEX(dm_bufio_clients_lock);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 static void buffer_record_stack(struct dm_buffer *b)
 {
-	b->stack_trace.nr_entries = 0;
-	b->stack_trace.max_entries = MAX_STACK;
-	b->stack_trace.entries = b->stack_entries;
-	b->stack_trace.skip = 2;
-	save_stack_trace(&b->stack_trace);
+	b->stack_len = stack_trace_save(b->stack_entries, MAX_STACK, 2);
 }
 #endif
 
@@ -438,7 +434,7 @@ static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask)
 	adjust_total_allocated(b->data_mode, (long)c->block_size);
 
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	memset(&b->stack_trace, 0, sizeof(b->stack_trace));
+	b->stack_len = 0;
 #endif
 	return b;
 }
@@ -1520,8 +1516,9 @@ static void drop_buffers(struct dm_bufio_client *c)
 			DMERR("leaked buffer %llx, hold count %u, list %d",
 			      (unsigned long long)b->block, b->hold_count, i);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-			print_stack_trace(&b->stack_trace, 1);
-			b->hold_count = 0; /* mark unclaimed to avoid BUG_ON below */
+			stack_trace_print(b->stack_entries, b->stack_len, 1);
+			/* mark unclaimed to avoid BUG_ON below */
+			b->hold_count = 0;
 #endif
 		}
 
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 3972232b8037..749ec268d957 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -35,7 +35,10 @@
 #define MAX_HOLDERS 4
 #define MAX_STACK 10
 
-typedef unsigned long stack_entries[MAX_STACK];
+struct stack_store {
+	unsigned int	nr_entries;
+	unsigned long	entries[MAX_STACK];
+};
 
 struct block_lock {
 	spinlock_t lock;
@@ -44,8 +47,7 @@ struct block_lock {
 	struct task_struct *holders[MAX_HOLDERS];
 
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	struct stack_trace traces[MAX_HOLDERS];
-	stack_entries entries[MAX_HOLDERS];
+	struct stack_store traces[MAX_HOLDERS];
 #endif
 };
 
@@ -73,7 +75,7 @@ static void __add_holder(struct block_lock *lock, struct task_struct *task)
 {
 	unsigned h = __find_holder(lock, NULL);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	struct stack_trace *t;
+	struct stack_store *t;
 #endif
 
 	get_task_struct(task);
@@ -81,11 +83,7 @@ static void __add_holder(struct block_lock *lock, struct task_struct *task)
 
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 	t = lock->traces + h;
-	t->nr_entries = 0;
-	t->max_entries = MAX_STACK;
-	t->entries = lock->entries[h];
-	t->skip = 2;
-	save_stack_trace(t);
+	t->nr_entries = stack_trace_save(t->entries, MAX_STACK, 2);
 #endif
 }
 
@@ -106,7 +104,8 @@ static int __check_holder(struct block_lock *lock)
 			DMERR("recursive lock detected in metadata");
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 			DMERR("previously held here:");
-			print_stack_trace(lock->traces + i, 4);
+			stack_trace_print(lock->traces[i].entries,
+					  lock->traces[i].nr_entries, 4);
 
 			DMERR("subsequent acquisition attempted here:");
 			dump_stack();
diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c
index 17d69bd5d7f1..49677ee889e3 100644
--- a/drivers/media/pci/dt3155/dt3155.c
+++ b/drivers/media/pci/dt3155/dt3155.c
@@ -46,7 +46,6 @@ static int read_i2c_reg(void __iomem *addr, u8 index, u8 *data)
 	u32 tmp = index;
 
 	iowrite32((tmp << 17) | IIC_READ, addr + IIC_CSR2);
-	mmiowb();
 	udelay(45); /* wait at least 43 usec for NEW_CYCLE to clear */
 	if (ioread32(addr + IIC_CSR2) & NEW_CYCLE)
 		return -EIO; /* error: NEW_CYCLE not cleared */
@@ -77,7 +76,6 @@ static int write_i2c_reg(void __iomem *addr, u8 index, u8 data)
 	u32 tmp = index;
 
 	iowrite32((tmp << 17) | IIC_WRITE | data, addr + IIC_CSR2);
-	mmiowb();
 	udelay(65); /* wait at least 63 usec for NEW_CYCLE to clear */
 	if (ioread32(addr + IIC_CSR2) & NEW_CYCLE)
 		return -EIO; /* error: NEW_CYCLE not cleared */
@@ -104,7 +102,6 @@ static void write_i2c_reg_nowait(void __iomem *addr, u8 index, u8 data)
 	u32 tmp = index;
 
 	iowrite32((tmp << 17) | IIC_WRITE | data, addr + IIC_CSR2);
-	mmiowb();
 }
 
 /**
@@ -264,7 +261,6 @@ static irqreturn_t dt3155_irq_handler_even(int irq, void *dev_id)
 						FLD_DN_ODD | FLD_DN_EVEN |
 						CAP_CONT_EVEN | CAP_CONT_ODD,
 							ipd->regs + CSR1);
-		mmiowb();
 	}
 
 	spin_lock(&ipd->lock);
@@ -282,7 +278,6 @@ static irqreturn_t dt3155_irq_handler_even(int irq, void *dev_id)
 		iowrite32(dma_addr + ipd->width, ipd->regs + ODD_DMA_START);
 		iowrite32(ipd->width, ipd->regs + EVEN_DMA_STRIDE);
 		iowrite32(ipd->width, ipd->regs + ODD_DMA_STRIDE);
-		mmiowb();
 	}
 
 	/* enable interrupts, clear all irq flags */
@@ -437,12 +432,10 @@ static int dt3155_init_board(struct dt3155_priv *pd)
 	/*  resetting the adapter  */
 	iowrite32(ADDR_ERR_ODD | ADDR_ERR_EVEN | FLD_CRPT_ODD | FLD_CRPT_EVEN |
 			FLD_DN_ODD | FLD_DN_EVEN, pd->regs + CSR1);
-	mmiowb();
 	msleep(20);
 
 	/*  initializing adapter registers  */
 	iowrite32(FIFO_EN | SRST, pd->regs + CSR1);
-	mmiowb();
 	iowrite32(0xEEEEEE01, pd->regs + EVEN_PIXEL_FMT);
 	iowrite32(0xEEEEEE01, pd->regs + ODD_PIXEL_FMT);
 	iowrite32(0x00000020, pd->regs + FIFO_TRIGER);
@@ -454,7 +447,6 @@ static int dt3155_init_board(struct dt3155_priv *pd)
 	iowrite32(0, pd->regs + MASK_LENGTH);
 	iowrite32(0x0005007C, pd->regs + FIFO_FLAG_CNT);
 	iowrite32(0x01010101, pd->regs + IIC_CLK_DUR);
-	mmiowb();
 
 	/* verifying that we have a DT3155 board (not just a SAA7116 chip) */
 	read_i2c_reg(pd->regs, DT_ID, &tmp);
diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c
index bcdca9fbef51..e3a5af65dbce 100644
--- a/drivers/memstick/host/jmb38x_ms.c
+++ b/drivers/memstick/host/jmb38x_ms.c
@@ -644,7 +644,6 @@ static int jmb38x_ms_reset(struct jmb38x_ms_host *host)
 	writel(HOST_CONTROL_RESET_REQ | HOST_CONTROL_CLOCK_EN
 	       | readl(host->addr + HOST_CONTROL),
 	       host->addr + HOST_CONTROL);
-	mmiowb();
 
 	for (cnt = 0; cnt < 20; ++cnt) {
 		if (!(HOST_CONTROL_RESET_REQ
@@ -659,7 +658,6 @@ reset_next:
 	writel(HOST_CONTROL_RESET | HOST_CONTROL_CLOCK_EN
 	       | readl(host->addr + HOST_CONTROL),
 	       host->addr + HOST_CONTROL);
-	mmiowb();
 
 	for (cnt = 0; cnt < 20; ++cnt) {
 		if (!(HOST_CONTROL_RESET
@@ -672,7 +670,6 @@ reset_next:
 	return -EIO;
 
 reset_ok:
-	mmiowb();
 	writel(INT_STATUS_ALL, host->addr + INT_SIGNAL_ENABLE);
 	writel(INT_STATUS_ALL, host->addr + INT_STATUS_ENABLE);
 	return 0;
@@ -1009,7 +1006,6 @@ static void jmb38x_ms_remove(struct pci_dev *dev)
 		tasklet_kill(&host->notify);
 		writel(0, host->addr + INT_SIGNAL_ENABLE);
 		writel(0, host->addr + INT_STATUS_ENABLE);
-		mmiowb();
 		dev_dbg(&jm->pdev->dev, "interrupts off\n");
 		spin_lock_irqsave(&host->lock, flags);
 		if (host->req) {
diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c
index ec0832278170..9d0445a567db 100644
--- a/drivers/misc/ioc4.c
+++ b/drivers/misc/ioc4.c
@@ -156,7 +156,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd)
 
 	/* Reset to power-on state */
 	writel(0, &idd->idd_misc_regs->int_out.raw);
-	mmiowb();
 
 	/* Set up square wave */
 	int_out.raw = 0;
@@ -164,7 +163,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd)
 	int_out.fields.mode = IOC4_INT_OUT_MODE_TOGGLE;
 	int_out.fields.diag = 0;
 	writel(int_out.raw, &idd->idd_misc_regs->int_out.raw);
-	mmiowb();
 
 	/* Check square wave period averaged over some number of cycles */
 	start = ktime_get_ns();
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 3fbbadfa2ae1..8a47a6fc3fc7 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -350,9 +350,6 @@ static void mei_me_hw_reset_release(struct mei_device *dev)
 	hcsr |= H_IG;
 	hcsr &= ~H_RST;
 	mei_hcsr_set(dev, hcsr);
-
-	/* complete this write before we set host ready on another CPU */
-	mmiowb();
 }
 
 /**
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 242dcee14689..6736f72cc14a 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -4,7 +4,7 @@ comment "Intel MIC Bus Driver"
 
 config INTEL_MIC_BUS
 	tristate "Intel MIC Bus Driver"
-	depends on 64BIT && PCI && X86 && X86_DEV_DMA_OPS
+	depends on 64BIT && PCI && X86
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
@@ -21,7 +21,7 @@ comment "SCIF Bus Driver"
 
 config SCIF_BUS
 	tristate "SCIF Bus Driver"
-	depends on 64BIT && PCI && X86 && X86_DEV_DMA_OPS
+	depends on 64BIT && PCI && X86
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c
index 9ac95b48ef92..cc729f7ab32e 100644
--- a/drivers/misc/tifm_7xx1.c
+++ b/drivers/misc/tifm_7xx1.c
@@ -403,7 +403,6 @@ static void tifm_7xx1_remove(struct pci_dev *dev)
 	fm->eject = tifm_7xx1_dummy_eject;
 	fm->has_ms_pif = tifm_7xx1_dummy_has_ms_pif;
 	writel(TIFM_IRQ_SETALL, fm->addr + FM_CLEAR_INTERRUPT_ENABLE);
-	mmiowb();
 	free_irq(dev->irq, fm);
 
 	tifm_remove_adapter(fm);
diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index 7c8f203f9a24..6e6b7ade4b60 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -959,7 +959,6 @@ static void alcor_timeout_timer(struct work_struct *work)
 		alcor_request_complete(host, 0);
 	}
 
-	mmiowb();
 	mutex_unlock(&host->cmd_mutex);
 }
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index a8141ff9be03..42e1bad024f4 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1807,7 +1807,6 @@ void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 			sdhci_send_command(host, mrq->cmd);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 EXPORT_SYMBOL_GPL(sdhci_request);
@@ -2010,8 +2009,6 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	 */
 	if (host->quirks & SDHCI_QUIRK_RESET_CMD_DATA_ON_IOS)
 		sdhci_do_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
-
-	mmiowb();
 }
 EXPORT_SYMBOL_GPL(sdhci_set_ios);
 
@@ -2105,7 +2102,6 @@ static void sdhci_enable_sdio_irq_nolock(struct sdhci_host *host, int enable)
 
 		sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 		sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
-		mmiowb();
 	}
 }
 
@@ -2353,7 +2349,6 @@ void sdhci_send_tuning(struct sdhci_host *host, u32 opcode)
 
 	host->tuning_done = 0;
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	/* Wait for Buffer Read Ready interrupt */
@@ -2705,7 +2700,6 @@ static bool sdhci_request_done(struct sdhci_host *host)
 
 	host->mrqs_done[i] = NULL;
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	mmc_request_done(host->mmc, mrq);
@@ -2739,7 +2733,6 @@ static void sdhci_timeout_timer(struct timer_list *t)
 		sdhci_finish_mrq(host, host->cmd->mrq);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -2770,7 +2763,6 @@ static void sdhci_timeout_data_timer(struct timer_list *t)
 		}
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -3251,7 +3243,6 @@ int sdhci_resume_host(struct sdhci_host *host)
 		mmc->ops->set_ios(mmc, &mmc->ios);
 	} else {
 		sdhci_init(host, (host->mmc->pm_flags & MMC_PM_KEEP_POWER));
-		mmiowb();
 	}
 
 	if (host->irq_wake_enabled) {
@@ -3391,7 +3382,6 @@ void sdhci_cqe_enable(struct mmc_host *mmc)
 		 mmc_hostname(mmc), host->ier,
 		 sdhci_readl(host, SDHCI_INT_STATUS));
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 EXPORT_SYMBOL_GPL(sdhci_cqe_enable);
@@ -3416,7 +3406,6 @@ void sdhci_cqe_disable(struct mmc_host *mmc, bool recovery)
 		 mmc_hostname(mmc), host->ier,
 		 sdhci_readl(host, SDHCI_INT_STATUS));
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 EXPORT_SYMBOL_GPL(sdhci_cqe_disable);
@@ -4255,8 +4244,6 @@ int __sdhci_add_host(struct sdhci_host *host)
 		goto unirq;
 	}
 
-	mmiowb();
-
 	ret = mmc_add_host(mmc);
 	if (ret)
 		goto unled;
diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c
index b6644ce296b2..35dd34b82a4d 100644
--- a/drivers/mmc/host/tifm_sd.c
+++ b/drivers/mmc/host/tifm_sd.c
@@ -889,7 +889,6 @@ static int tifm_sd_initialize_host(struct tifm_sd *host)
 	struct tifm_dev *sock = host->dev;
 
 	writel(0, sock->addr + SOCK_MMCSD_INT_ENABLE);
-	mmiowb();
 	host->clk_div = 61;
 	host->clk_freq = 20000000;
 	writel(TIFM_MMCSD_RESET, sock->addr + SOCK_MMCSD_SYSTEM_CONTROL);
@@ -940,7 +939,6 @@ static int tifm_sd_initialize_host(struct tifm_sd *host)
 	writel(TIFM_MMCSD_CERR | TIFM_MMCSD_BRS | TIFM_MMCSD_EOC
 	       | TIFM_MMCSD_ERRMASK,
 	       sock->addr + SOCK_MMCSD_INT_ENABLE);
-	mmiowb();
 
 	return 0;
 }
@@ -1005,7 +1003,6 @@ static void tifm_sd_remove(struct tifm_dev *sock)
 	spin_lock_irqsave(&sock->lock, flags);
 	host->eject = 1;
 	writel(0, sock->addr + SOCK_MMCSD_INT_ENABLE);
-	mmiowb();
 	spin_unlock_irqrestore(&sock->lock, flags);
 
 	tasklet_kill(&host->finish_tasklet);
diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c
index 32c4211506fc..412395ac2935 100644
--- a/drivers/mmc/host/via-sdmmc.c
+++ b/drivers/mmc/host/via-sdmmc.c
@@ -686,7 +686,6 @@ static void via_sdc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		via_sdc_send_command(host, mrq->cmd);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -711,7 +710,6 @@ static void via_sdc_set_power(struct via_crdr_mmc_host *host,
 		gatt &= ~VIA_CRDR_PCICLKGATT_PAD_PWRON;
 	writeb(gatt, host->pcictrl_mmiobase + VIA_CRDR_PCICLKGATT);
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	via_pwron_sleep(host);
@@ -770,7 +768,6 @@ static void via_sdc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (readb(addrbase + VIA_CRDR_PCISDCCLK) != clock)
 		writeb(clock, addrbase + VIA_CRDR_PCISDCCLK);
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	if (ios->power_mode != MMC_POWER_OFF)
@@ -830,7 +827,6 @@ static void via_reset_pcictrl(struct via_crdr_mmc_host *host)
 	via_restore_pcictrlreg(host);
 	via_restore_sdcreg(host);
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -925,7 +921,6 @@ static irqreturn_t via_sdc_isr(int irq, void *dev_id)
 
 	result = IRQ_HANDLED;
 
-	mmiowb();
 out:
 	spin_unlock(&sdhost->lock);
 
@@ -960,7 +955,6 @@ static void via_sdc_timeout(struct timer_list *t)
 		}
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&sdhost->lock, flags);
 }
 
@@ -1012,7 +1006,6 @@ static void via_sdc_card_detect(struct work_struct *work)
 			tasklet_schedule(&host->finish_tasklet);
 		}
 
-		mmiowb();
 		spin_unlock_irqrestore(&host->lock, flags);
 
 		via_reset_pcictrl(host);
@@ -1020,7 +1013,6 @@ static void via_sdc_card_detect(struct work_struct *work)
 		spin_lock_irqsave(&host->lock, flags);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	via_print_pcictrl(host);
@@ -1188,7 +1180,6 @@ static void via_sd_remove(struct pci_dev *pcidev)
 
 	/* Disable generating further interrupts */
 	writeb(0x0, sdhost->pcictrl_mmiobase + VIA_CRDR_PCIINTCTRL);
-	mmiowb();
 
 	if (sdhost->mrq) {
 		pr_err("%s: Controller removed during "
@@ -1197,7 +1188,6 @@ static void via_sd_remove(struct pci_dev *pcidev)
 		/* make sure all DMA is stopped */
 		writel(VIA_CRDR_DMACTRL_SFTRST,
 			sdhost->ddma_mmiobase + VIA_CRDR_DMACTRL);
-		mmiowb();
 		sdhost->mrq->cmd->error = -ENOMEDIUM;
 		if (sdhost->mrq->stop)
 			sdhost->mrq->stop->error = -ENOMEDIUM;
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index f38e5c1b87e4..d984538980e2 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -722,12 +722,6 @@ static void marvell_nfc_select_target(struct nand_chip *chip,
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
 	u32 ndcr_generic;
 
-	if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die)
-		return;
-
-	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
-	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
-
 	/*
 	 * Reset the NDCR register to a clean state for this particular chip,
 	 * also clear ND_RUN bit.
@@ -739,6 +733,12 @@ static void marvell_nfc_select_target(struct nand_chip *chip,
 	/* Also reset the interrupt status register */
 	marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
 
+	if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die)
+		return;
+
+	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
+	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
+
 	nfc->selected_chip = chip;
 	marvell_nand->selected_die = die_nr;
 }
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index 86456216fb93..7b99831aa046 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -45,7 +45,6 @@ static inline void r852_write_reg(struct r852_device *dev,
 						int address, uint8_t value)
 {
 	writeb(value, dev->mmio + address);
-	mmiowb();
 }
 
 
@@ -61,7 +60,6 @@ static inline void r852_write_reg_dword(struct r852_device *dev,
 							int address, uint32_t value)
 {
 	writel(cpu_to_le32(value), dev->mmio + address);
-	mmiowb();
 }
 
 /* returns pointer to our private structure */
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index ddf0420c0997..97978227aa55 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -159,7 +159,6 @@ static void txx9ndfmc_cmd_ctrl(struct nand_chip *chip, int cmd,
 		if ((ctrl & NAND_CTRL_CHANGE) && cmd == NAND_CMD_NONE)
 			txx9ndfmc_write(dev, 0, TXX9_NDFDTR);
 	}
-	mmiowb();
 }
 
 static int txx9ndfmc_dev_ready(struct nand_chip *chip)
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index e6234d209787..4212bc4a5f31 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -886,6 +886,9 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	     fs->m_ext.data[1]))
 		return -EINVAL;
 
+	if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	if (fs->location != RX_CLS_LOC_ANY &&
 	    test_bit(fs->location, priv->cfp.used))
 		return -EBUSY;
@@ -974,6 +977,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc)
 	struct cfp_rule *rule;
 	int ret;
 
+	if (loc >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	/* Refuse deleting unused rules, and those that are not unique since
 	 * that could leave IPv6 rules with one of the chained rule in the
 	 * table.
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 47e5984f16fb..3155f7fa83eb 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -613,7 +613,6 @@ static irqreturn_t greth_interrupt(int irq, void *dev_id)
 		napi_schedule(&greth->napi);
 	}
 
-	mmiowb();
 	spin_unlock(&greth->devlock);
 
 	return retval;
diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 16477aa6d61f..4f7e792e50e9 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -345,8 +345,6 @@ static void slic_set_rx_mode(struct net_device *dev)
 	if (sdev->promisc != set_promisc) {
 		sdev->promisc = set_promisc;
 		slic_configure_rcv(sdev);
-		/* make sure writes to receiver cant leak out of the lock */
-		mmiowb();
 	}
 	spin_unlock_bh(&sdev->link_lock);
 }
@@ -1461,8 +1459,6 @@ static netdev_tx_t slic_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (slic_get_free_tx_descs(txq) < SLIC_MAX_REQ_TX_DESCS)
 		netif_stop_queue(dev);
-	/* make sure writes to io-memory cant leak out of tx queue lock */
-	mmiowb();
 
 	return NETDEV_TX_OK;
 drop_skb:
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index b17d435de09f..05798aa5bb73 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2016,7 +2016,6 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 	mb();
 	writel_relaxed((u32)aenq->head,
 		       dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
-	mmiowb();
 }
 
 int ena_com_dev_reset(struct ena_com_dev *ena_dev,
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 156fbc5601ca..f35c9a75be50 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -2439,7 +2439,6 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	atl1_tx_map(adapter, skb, ptpd);
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
-	mmiowb();
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 98da0fa27192..dd81c5863111 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -908,7 +908,6 @@ static netdev_tx_t atl2_xmit_frame(struct sk_buff *skb,
 	ATL2_WRITE_REGW(&adapter->hw, REG_MB_TXD_WR_IDX,
 		(adapter->txd_write_ptr >> 2));
 
-	mmiowb();
 	dev_consume_skb_any(skb);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index d63371d70bce..dfdd14eadd57 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -3305,8 +3305,6 @@ next_rx:
 
 	BNX2_WR(bp, rxr->rx_bseq_addr, rxr->rx_prod_bseq);
 
-	mmiowb();
-
 	return rx_pkt;
 
 }
@@ -6723,8 +6721,6 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	BNX2_WR16(bp, txr->tx_bidx_addr, prod);
 	BNX2_WR(bp, txr->tx_bseq_addr, txr->tx_prod_bseq);
 
-	mmiowb();
-
 	txr->tx_prod = prod;
 
 	if (unlikely(bnx2_tx_avail(bp, txr) <= MAX_SKB_FRAGS)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ecb1bd7eb508..0c8f5b546c6f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4166,8 +4166,6 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
-	mmiowb();
-
 	txdata->tx_bd_prod += nbd;
 
 	if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_DESC_PER_TX_PKT)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 2462e7aa0c5d..2d57af9c061c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -527,8 +527,6 @@ static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 		REG_WR_RELAXED(bp, fp->ustorm_rx_prods_offset + i * 4,
 			       ((u32 *)&rx_prods)[i]);
 
-	mmiowb(); /* keep prod updates ordered */
-
 	DP(NETIF_MSG_RX_STATUS,
 	   "queue[%d]:  wrote  bd_prod %u  cqe_prod %u  sge_prod %u\n",
 	   fp->index, bd_prod, rx_comp_prod, rx_sge_prod);
@@ -653,7 +651,6 @@ static inline void bnx2x_igu_ack_sb_gen(struct bnx2x *bp, u8 igu_sb_id,
 	REG_WR(bp, igu_addr, cmd_data.sb_id_and_flags);
 
 	/* Make sure that ACK is written */
-	mmiowb();
 	barrier();
 }
 
@@ -674,7 +671,6 @@ static inline void bnx2x_hc_ack_sb(struct bnx2x *bp, u8 sb_id,
 	REG_WR(bp, hc_addr, (*(u32 *)&igu_ack));
 
 	/* Make sure that ACK is written */
-	mmiowb();
 	barrier();
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 749d0ef44371..0745cccd416d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2623,7 +2623,6 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	wmb();
 	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
-	mmiowb();
 	barrier();
 
 	num_pkts++;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 626b491f7674..3716c828ff5d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -869,9 +869,6 @@ static void bnx2x_hc_int_disable(struct bnx2x *bp)
 	   "write %x to HC %d (addr 0x%x)\n",
 	   val, port, addr);
 
-	/* flush all outstanding writes */
-	mmiowb();
-
 	REG_WR(bp, addr, val);
 	if (REG_RD(bp, addr) != val)
 		BNX2X_ERR("BUG! Proper val not read from IGU!\n");
@@ -887,9 +884,6 @@ static void bnx2x_igu_int_disable(struct bnx2x *bp)
 
 	DP(NETIF_MSG_IFDOWN, "write %x to IGU\n", val);
 
-	/* flush all outstanding writes */
-	mmiowb();
-
 	REG_WR(bp, IGU_REG_PF_CONFIGURATION, val);
 	if (REG_RD(bp, IGU_REG_PF_CONFIGURATION) != val)
 		BNX2X_ERR("BUG! Proper val not read from IGU!\n");
@@ -1595,7 +1589,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp)
 	/*
 	 * Ensure that HC_CONFIG is written before leading/trailing edge config
 	 */
-	mmiowb();
 	barrier();
 
 	if (!CHIP_IS_E1(bp)) {
@@ -1611,9 +1604,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp)
 		REG_WR(bp, HC_REG_TRAILING_EDGE_0 + port*8, val);
 		REG_WR(bp, HC_REG_LEADING_EDGE_0 + port*8, val);
 	}
-
-	/* Make sure that interrupts are indeed enabled from here on */
-	mmiowb();
 }
 
 static void bnx2x_igu_int_enable(struct bnx2x *bp)
@@ -1674,9 +1664,6 @@ static void bnx2x_igu_int_enable(struct bnx2x *bp)
 
 	REG_WR(bp, IGU_REG_TRAILING_EDGE_LATCH, val);
 	REG_WR(bp, IGU_REG_LEADING_EDGE_LATCH, val);
-
-	/* Make sure that interrupts are indeed enabled from here on */
-	mmiowb();
 }
 
 void bnx2x_int_enable(struct bnx2x *bp)
@@ -3833,7 +3820,6 @@ static void bnx2x_sp_prod_update(struct bnx2x *bp)
 
 	REG_WR16_RELAXED(bp, BAR_XSTRORM_INTMEM + XSTORM_SPQ_PROD_OFFSET(func),
 			 bp->spq_prod_idx);
-	mmiowb();
 }
 
 /**
@@ -5244,7 +5230,6 @@ static void bnx2x_update_eq_prod(struct bnx2x *bp, u16 prod)
 {
 	/* No memory barriers */
 	storm_memset_eq_prod(bp, prod, BP_FUNC(bp));
-	mmiowb(); /* keep prod updates ordered */
 }
 
 static int  bnx2x_cnic_handle_cfc_del(struct bnx2x *bp, u32 cid,
@@ -6513,7 +6498,6 @@ void bnx2x_nic_init_cnic(struct bnx2x *bp)
 
 	/* flush all */
 	mb();
-	mmiowb();
 }
 
 void bnx2x_pre_irq_nic_init(struct bnx2x *bp)
@@ -6553,7 +6537,6 @@ void bnx2x_post_irq_nic_init(struct bnx2x *bp, u32 load_code)
 
 	/* flush all before enabling interrupts */
 	mb();
-	mmiowb();
 
 	bnx2x_int_enable(bp);
 
@@ -7775,12 +7758,10 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, bool is_pf)
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 			 data, igu_addr_data);
 	REG_WR(bp, igu_addr_data, data);
-	mmiowb();
 	barrier();
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 			  ctl, igu_addr_ctl);
 	REG_WR(bp, igu_addr_ctl, ctl);
-	mmiowb();
 	barrier();
 
 	/* wait for clean up to finish */
@@ -9550,7 +9531,6 @@ static void bnx2x_set_234_gates(struct bnx2x *bp, bool close)
 
 	DP(NETIF_MSG_HW | NETIF_MSG_IFUP, "%s gates #2, #3 and #4\n",
 		close ? "closing" : "opening");
-	mmiowb();
 }
 
 #define SHARED_MF_CLP_MAGIC  0x80000000 /* `magic' bit */
@@ -9674,7 +9654,6 @@ static void bnx2x_pxp_prep(struct bnx2x *bp)
 	if (!CHIP_IS_E1(bp)) {
 		REG_WR(bp, PXP2_REG_RD_START_INIT, 0);
 		REG_WR(bp, PXP2_REG_RQ_RBC_DONE, 0);
-		mmiowb();
 	}
 }
 
@@ -9774,16 +9753,13 @@ static void bnx2x_process_kill_chip_reset(struct bnx2x *bp, bool global)
 	       reset_mask1 & (~not_reset_mask1));
 
 	barrier();
-	mmiowb();
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET,
 	       reset_mask2 & (~stay_reset2));
 
 	barrier();
-	mmiowb();
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_1_SET, reset_mask1);
-	mmiowb();
 }
 
 /**
@@ -9867,9 +9843,6 @@ static int bnx2x_process_kill(struct bnx2x *bp, bool global)
 	REG_WR(bp, MISC_REG_UNPREPARED, 0);
 	barrier();
 
-	/* Make sure all is written to the chip before the reset */
-	mmiowb();
-
 	/* Wait for 1ms to empty GLUE and PCI-E core queues,
 	 * PSWHST, GRC and PSWRD Tetris buffer.
 	 */
@@ -14828,7 +14801,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		if (rc)
 			break;
 
-		mmiowb();
 		barrier();
 
 		/* Start accepting on iSCSI L2 ring */
@@ -14863,7 +14835,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		if (!bnx2x_wait_sp_comp(bp, sp_bits))
 			BNX2X_ERR("rx_mode completion timed out!\n");
 
-		mmiowb();
 		barrier();
 
 		/* Unset iSCSI L2 MAC */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 7b22a6d8514c..80d250a6d048 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -5039,7 +5039,6 @@ static inline int bnx2x_q_init(struct bnx2x *bp,
 	/* As no ramrod is sent, complete the command immediately  */
 	o->complete_cmd(bp, o, BNX2X_Q_CMD_INIT);
 
-	mmiowb();
 	smp_mb();
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index c97b642e6537..0edbb0a76847 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -100,13 +100,11 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   cmd_data.sb_id_and_flags, igu_addr_data);
 	REG_WR(bp, igu_addr_data, cmd_data.sb_id_and_flags);
-	mmiowb();
 	barrier();
 
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   ctl, igu_addr_ctl);
 	REG_WR(bp, igu_addr_ctl, ctl);
-	mmiowb();
 	barrier();
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 10ff37d6dc78..0752b7fa4d9c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -172,8 +172,6 @@ static int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping)
 	/* Trigger the PF FW */
 	writeb_relaxed(1, &zone_data->trigger.vf_pf_channel.addr_valid);
 
-	mmiowb();
-
 	/* Wait for PF to complete */
 	while ((tout >= 0) && (!*done)) {
 		msleep(interval);
@@ -1179,7 +1177,6 @@ static void bnx2x_vf_mbx_resp_send_msg(struct bnx2x *bp,
 
 	/* ack the FW */
 	storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
-	mmiowb();
 
 	/* copy the response header including status-done field,
 	 * must be last dmae, must be after FW is acked
@@ -2174,7 +2171,6 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		 */
 		storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
 		/* Firmware ack should be written before unlocking channel */
-		mmiowb();
 		bnx2x_unlock_vf_pf_channel(bp, vf, mbx->first_tlv.tl.type);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4c586ba4364b..2a4341708c0f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -556,8 +556,6 @@ normal_tx:
 
 tx_done:
 
-	mmiowb();
-
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
 		if (skb->xmit_more && !tx_buf->is_push)
 			bnxt_db_write(bp, &txr->tx_db, prod);
@@ -1625,7 +1623,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
 			bnxt_sched_reset(bp, rxr);
 		}
-		goto next_rx;
+		goto next_rx_no_len;
 	}
 
 	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
@@ -1706,12 +1704,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	rc = 1;
 
 next_rx:
-	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
-
 	cpr->rx_packets += 1;
 	cpr->rx_bytes += len;
 
+next_rx_no_len:
+	rxr->rx_prod = NEXT_RX(prod);
+	rxr->rx_next_cons = NEXT_RX(cons);
+
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
@@ -2133,7 +2132,6 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 			       &dim_sample);
 		net_dim(&cpr->dim, dim_sample);
 	}
-	mmiowb();
 	return work_done;
 }
 
@@ -5135,10 +5133,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_TX,
 						close_path ? cmpl_ring_id :
@@ -5151,10 +5149,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_RX,
 						close_path ? cmpl_ring_id :
@@ -5173,10 +5171,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring, type,
 						close_path ? cmpl_ring_id :
 						INVALID_HW_RING_ID);
@@ -5315,17 +5313,16 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= rx_rings ?
 				FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 		} else {
 			enables |= cp_rings ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS |
 				   FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
@@ -5365,14 +5362,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 	enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		enables |= tx_rings + ring_grps ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
 		enables |= cp_rings ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 		enables |= ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0;
 	}
@@ -6753,6 +6749,7 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
 	struct hwrm_port_qstats_ext_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	u32 tx_stat_size;
 	int rc;
 
 	if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
@@ -6762,13 +6759,16 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	req.port_id = cpu_to_le16(pf->port_id);
 	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
 	req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
-	req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext));
+	tx_stat_size = bp->hw_tx_port_stats_ext ?
+		       sizeof(*bp->hw_tx_port_stats_ext) : 0;
+	req.tx_stat_size = cpu_to_le16(tx_stat_size);
 	req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
-		bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8;
+		bp->fw_tx_stats_ext_size = tx_stat_size ?
+			le16_to_cpu(resp->tx_stat_size) / 8 : 0;
 	} else {
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
@@ -8961,8 +8961,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 
 skip_uc:
 	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	if (rc && vnic->mc_list_count) {
+		netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	}
 	if (rc)
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
 			   rc);
 
 	return rc;
@@ -10685,6 +10692,7 @@ init_err_cleanup_tc:
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 060a6f386104..2aebd4bbb67d 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1073,7 +1073,6 @@ static void tg3_int_reenable(struct tg3_napi *tnapi)
 	struct tg3 *tp = tnapi->tp;
 
 	tw32_mailbox(tnapi->int_mbox, tnapi->last_tag << 24);
-	mmiowb();
 
 	/* When doing tagged status, this work check is unnecessary.
 	 * The last_tag we write above tells the chip which piece of
@@ -6999,7 +6998,6 @@ next_pkt_nopost:
 			tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
 				     tpr->rx_jmb_prod_idx);
 		}
-		mmiowb();
 	} else if (work_mask) {
 		/* rx_std_buffers[] and rx_jmb_buffers[] entries must be
 		 * updated before the producer indices can be updated.
@@ -7210,8 +7208,6 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
 			tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
 				     dpr->rx_jmb_prod_idx);
 
-		mmiowb();
-
 		if (err)
 			tw32_f(HOSTCC_MODE, tp->coal_now);
 	}
@@ -7278,7 +7274,6 @@ static int tg3_poll_msix(struct napi_struct *napi, int budget)
 						  HOSTCC_MODE_ENABLE |
 						  tnapi->coal_now);
 			}
-			mmiowb();
 			break;
 		}
 	}
@@ -8159,7 +8154,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!skb->xmit_more || netif_xmit_stopped(txq)) {
 		/* Packets are ready, update Tx producer idx on card. */
 		tw32_tx_mbox(tnapi->prodmbox, entry);
-		mmiowb();
 	}
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index 2df7440f58df..39643be8c30a 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -38,9 +38,6 @@ int lio_cn6xxx_soft_reset(struct octeon_device *oct)
 	lio_pci_readq(oct, CN6XXX_CIU_SOFT_RST);
 	lio_pci_writeq(oct, 1, CN6XXX_CIU_SOFT_RST);
 
-	/* make sure that the reset is written before starting timer */
-	mmiowb();
-
 	/* Wait for 10ms as Octeon resets. */
 	mdelay(100);
 
@@ -487,9 +484,6 @@ void lio_cn6xxx_disable_interrupt(struct octeon_device *oct,
 
 	/* Disable Interrupts */
 	writeq(0, cn6xxx->intr_enb_reg64);
-
-	/* make sure interrupts are really disabled */
-	mmiowb();
 }
 
 static void lio_cn6xxx_get_pcie_qlmport(struct octeon_device *oct)
@@ -555,10 +549,6 @@ static int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 				value &= ~(1 << oq_no);
 				octeon_write_csr(oct, reg, value);
 
-				/* Ensure that the enable register is written.
-				 */
-				mmiowb();
-
 				spin_unlock(&cn6xxx->lock_for_droq_int_enb_reg);
 			}
 		}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index ce8c3f818666..934115d18488 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1449,7 +1449,6 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 		iq->pkt_in_done -= iq->pkts_processed;
 		iq->pkts_processed = 0;
 		/* this write needs to be flushed before we release the lock */
-		mmiowb();
 		spin_unlock_bh(&iq->lock);
 		oct = iq->oct_dev;
 	}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index a0c099f71524..017169023cca 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -513,8 +513,6 @@ int octeon_retry_droq_refill(struct octeon_droq *droq)
 		 */
 		wmb();
 		writel(desc_refilled, droq->pkts_credit_reg);
-		/* make sure mmio write completes */
-		mmiowb();
 
 		if (pkts_credit + desc_refilled >= CN23XX_SLI_DEF_BP)
 			reschedule = 0;
@@ -712,8 +710,6 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 				 */
 				wmb();
 				writel(desc_refilled, droq->pkts_credit_reg);
-				/* make sure mmio write completes */
-				mmiowb();
 			}
 		}
 	}                       /* for (each packet)... */
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index c6f4cbda040f..fcf20a8f92d9 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -278,7 +278,6 @@ ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq)
 	if (atomic_read(&oct->status) == OCT_DEV_RUNNING) {
 		writel(iq->fill_cnt, iq->doorbell_reg);
 		/* make sure doorbell write goes through */
-		mmiowb();
 		iq->fill_cnt = 0;
 		iq->last_db_time = jiffies;
 		return;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 8fe9af0e2ab7..466bf1ea186d 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3270,11 +3270,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		if (!skb->xmit_more ||
 		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
 			writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
-			/* we need this if more than one processor can write to
-			 * our tail at a time, it synchronizes IO on IA64/Altix
-			 * systems
-			 */
-			mmiowb();
 		}
 	} else {
 		dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 7acc61e4f645..022c3ac0e40f 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3816,7 +3816,6 @@ static void e1000_flush_tx_ring(struct e1000_adapter *adapter)
 	if (tx_ring->next_to_use == tx_ring->count)
 		tx_ring->next_to_use = 0;
 	ew32(TDT(0), tx_ring->next_to_use);
-	mmiowb();
 	usleep_range(200, 250);
 }
 
@@ -5904,12 +5903,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 						     tx_ring->next_to_use);
 			else
 				writel(tx_ring->next_to_use, tx_ring->tail);
-
-			/* we need this if more than one processor can write
-			 * to our tail at a time, it synchronizes IO on
-			 *IA64/Altix systems
-			 */
-			mmiowb();
 		}
 	} else {
 		dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index 5d4f1761dc0c..8de77155f2e7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -321,8 +321,6 @@ static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask);
 	err_mask |= PCI_ERR_UNC_COMP_ABORT;
 	pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask);
-
-	mmiowb();
 }
 
 int fm10k_iov_resume(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index ecef949f3baa..cbf76a96e94e 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1039,11 +1039,6 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 6c97667d20ef..ffb611bbedfa 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3471,11 +3471,6 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 9b4d7cec2e18..6bfef82e7607 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -2360,11 +2360,6 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index c289d97f477d..1af21bbe180e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1356,11 +1356,6 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 3269d8e94744..1d71ec360b1c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6028,11 +6028,6 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 	return 0;
 
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 4eab83faec62..34cd30d7162f 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2279,10 +2279,6 @@ static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter,
 	tx_ring->buffer_info[first].next_to_watch = tx_desc;
 	tx_ring->next_to_use = i;
 	writel(i, adapter->hw.hw_addr + tx_ring->tail);
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
 }
 
 static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 87a11879bf2d..f8d692f6aa4f 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -892,11 +892,6 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e100054a3765..99e23cf6a73a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8299,11 +8299,6 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 8b3495ee2b6e..49486c10ef81 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1139,9 +1139,6 @@ static inline void sky2_put_idx(struct sky2_hw *hw, unsigned q, u16 idx)
 	/* Make sure write' to descriptors are complete before we tell hardware */
 	wmb();
 	sky2_write16(hw, Y2_QADDR(q, PREF_UNIT_PUT_IDX), idx);
-
-	/* Synchronize I/O on since next processor may write to tail */
-	mmiowb();
 }
 
 
@@ -1354,7 +1351,6 @@ stopped:
 
 	/* reset the Rx prefetch unit */
 	sky2_write32(hw, Y2_QADDR(rxq, PREF_UNIT_CTRL), PREF_UNIT_RST_SET);
-	mmiowb();
 }
 
 /* Clean out receive buffer area, assumes receiver hardware stopped */
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c81d15bf259c..87e90b5d4d7d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -129,10 +129,6 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
 	comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET;
 	__raw_writel((__force u32)cpu_to_be32(comm_flags),
 		     (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS);
-	/* Make sure that our comm channel write doesn't
-	 * get mixed in with writes from another CPU.
-	 */
-	mmiowb();
 
 	end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies;
 	while (time_before(jiffies, end)) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index a5d5d6fc1da0..c678344d22a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -281,7 +281,6 @@ static int mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param)
 	val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31);
 	__raw_writel((__force u32) cpu_to_be32(val),
 		     &priv->mfunc.comm->slave_write);
-	mmiowb();
 	mutex_unlock(&dev->persist->device_state_mutex);
 	return 0;
 }
@@ -496,12 +495,6 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 					       (op_modifier << HCR_OPMOD_SHIFT) |
 					       op), hcr + 6);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	cmd->toggle = cmd->toggle ^ 1;
 
 	ret = 0;
@@ -2206,7 +2199,6 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 	}
 	__raw_writel((__force u32) cpu_to_be32(reply),
 		     &priv->mfunc.comm[slave].slave_read);
-	mmiowb();
 
 	return;
 
@@ -2410,7 +2402,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 				     &priv->mfunc.comm[i].slave_write);
 			__raw_writel((__force u32) 0,
 				     &priv->mfunc.comm[i].slave_read);
-			mmiowb();
 			for (port = 1; port <= MLX4_MAX_PORTS; port++) {
 				struct mlx4_vport_state *admin_vport;
 				struct mlx4_vport_state *oper_vport;
@@ -2576,10 +2567,6 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
 		slave_read |= (u32)COMM_CHAN_EVENT_INTERNAL_ERR;
 		__raw_writel((__force u32)cpu_to_be32(slave_read),
 			     &priv->mfunc.comm[slave].slave_read);
-		/* Make sure that our comm channel write doesn't
-		 * get mixed in with writes from another CPU.
-		 */
-		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index be48c6440251..c087d1014b09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -917,7 +917,6 @@ static void cmd_work_handler(struct work_struct *work)
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
-	mmiowb();
 	/* if not in polling don't use ent after this point */
 	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index e0340f778d8f..d8b7fba96d58 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -1439,7 +1439,6 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index)
 			tx->queue_active = 0;
 			put_be32(htonl(1), tx->send_stop);
 			mb();
-			mmiowb();
 		}
 		__netif_tx_unlock(dev_queue);
 	}
@@ -2861,7 +2860,6 @@ again:
 		tx->queue_active = 1;
 		put_be32(htonl(1), tx->send_go);
 		mb();
-		mmiowb();
 	}
 	tx->pkt_start++;
 	if ((avail - count) < MXGEFW_MAX_SEND_DESC) {
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index feda9644289d..3b2ae1a21678 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4153,8 +4153,6 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	writeq(val64, &tx_fifo->List_Control);
 
-	mmiowb();
-
 	put_off++;
 	if (put_off == fifo->tx_curr_put_info.fifo_len + 1)
 		put_off = 0;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index b877acec5cde..1d334f2e0a56 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -1826,7 +1826,6 @@ static int vxge_poll_msix(struct napi_struct *napi, int budget)
 		vxge_hw_channel_msix_unmask(
 				(struct __vxge_hw_channel *)ring->handle,
 				ring->rx_vector_no);
-		mmiowb();
 	}
 
 	/* We are copying and returning the local variable, in case if after
@@ -2234,8 +2233,6 @@ static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id)
 	vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle,
 				    fifo->tx_vector_no);
 
-	mmiowb();
-
 	return IRQ_HANDLED;
 }
 
@@ -2272,14 +2269,12 @@ vxge_alarm_msix_handle(int irq, void *dev_id)
 		 */
 		vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id);
 		vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id);
-		mmiowb();
 
 		status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle,
 			vdev->exec_mode);
 		if (status == VXGE_HW_OK) {
 			vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle,
 						  msix_id);
-			mmiowb();
 			continue;
 		}
 		vxge_debug_intr(VXGE_ERR,
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index 59e77e3086bb..709d20d9938f 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1399,11 +1399,7 @@ static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo,
 		VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop),
 		&fifo->nofl_db->control_0);
 
-	mmiowb();
-
 	writeq(txdl_ptr, &fifo->nofl_db->txdl_ptr);
-
-	mmiowb();
 }
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 8848d5bed6e5..fdfedbc8e431 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -814,18 +814,12 @@ static inline u16 qed_attn_update_idx(struct qed_hwfn *p_hwfn,
 {
 	u16 rc = 0, index;
 
-	/* Make certain HW write took affect */
-	mmiowb();
-
 	index = le16_to_cpu(p_sb_desc->sb_attn->sb_index);
 	if (p_sb_desc->index != index) {
 		p_sb_desc->index	= index;
 		rc		      = QED_SB_ATT_IDX;
 	}
 
-	/* Make certain we got a consistent view with HW */
-	mmiowb();
-
 	return rc;
 }
 
@@ -1213,7 +1207,6 @@ static void qed_sb_ack_attn(struct qed_hwfn *p_hwfn,
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
 	 */
-	mmiowb();
 	barrier();
 }
 
@@ -1848,9 +1841,6 @@ static void qed_int_igu_enable_attn(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff);
 	qed_wr(p_hwfn, p_ptt, IGU_REG_ATTENTION_ENABLE, 0xfff);
 
-	/* Flush the writes to IGU */
-	mmiowb();
-
 	/* Unmask AEU signals toward IGU */
 	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff);
 }
@@ -1914,9 +1904,6 @@ static void qed_int_igu_cleanup_sb(struct qed_hwfn *p_hwfn,
 
 	qed_wr(p_hwfn, p_ptt, IGU_REG_COMMAND_REG_CTRL, cmd_ctrl);
 
-	/* Flush the write to IGU */
-	mmiowb();
-
 	/* calculate where to read the status bit from */
 	sb_bit = 1 << (igu_sb_id % 32);
 	sb_bit_addr = igu_sb_id / 32 * sizeof(u32);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 79b311b86f66..f5f3c03b9dd2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -341,9 +341,6 @@ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod)
 		   USTORM_EQE_CONS_OFFSET(p_hwfn->rel_pf_id);
 
 	REG_WR16(p_hwfn, addr, prod);
-
-	/* keep prod updates ordered */
-	mmiowb();
 }
 
 int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b4c8949933f1..4555c0b161ef 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1526,14 +1526,6 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	barrier();
 	writel(txq->tx_db.raw, txq->doorbell_addr);
 
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the queue lock is released and another start_xmit is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
-
 	for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
 		if (qede_txq_has_work(txq))
 			break;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 31b046e24565..6f7e3622c6b4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -580,14 +580,6 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
 
 	internal_ram_wr(rxq->hw_rxq_prod_addr, sizeof(rx_prods),
 			(u32 *)&rx_prods);
-
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the napi lock is released and another qede_poll is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
 }
 
 static void qede_get_rxhash(struct sk_buff *skb, u8 bitfields, __le32 rss_hash)
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index b61b88cbc0c7..457444894d80 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1858,7 +1858,6 @@ static void ql_update_small_bufq_prod_index(struct ql3_adapter *qdev)
 		wmb();
 		writel_relaxed(qdev->small_buf_q_producer_index,
 			       &port_regs->CommonRegs.rxSmallQProducerIndex);
-		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 3e71b65a9546..ad7c5eb8a3b6 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -2181,7 +2181,6 @@ static inline void ql_write32(const struct ql_adapter *qdev, int reg, u32 val)
 static inline void ql_write_db_reg(u32 val, void __iomem *addr)
 {
 	writel(val, addr);
-	mmiowb();
 }
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 07e1c623048e..6cae33072496 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2695,7 +2695,6 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 
 	ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg);
-	mmiowb();
 	netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev,
 		     "tx queued, slot %d, len %d\n",
 		     tx_ring->prod_idx, skb->len);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 8154b38c08f7..316b47741d3f 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -728,7 +728,6 @@ static irqreturn_t ravb_emac_interrupt(int irq, void *dev_id)
 
 	spin_lock(&priv->lock);
 	ravb_emac_interrupt_unlocked(ndev);
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return IRQ_HANDLED;
 }
@@ -848,7 +847,6 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id)
 		result = IRQ_HANDLED;
 	}
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -881,7 +879,6 @@ static irqreturn_t ravb_multi_interrupt(int irq, void *dev_id)
 		result = IRQ_HANDLED;
 	}
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -898,7 +895,6 @@ static irqreturn_t ravb_dma_interrupt(int irq, void *dev_id, int q)
 	if (ravb_queue_interrupt(ndev, q))
 		result = IRQ_HANDLED;
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -943,7 +939,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 			ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
 			ravb_tx_free(ndev, q, true);
 			netif_wake_subqueue(ndev, q);
-			mmiowb();
 			spin_unlock_irqrestore(&priv->lock, flags);
 		}
 	}
@@ -959,7 +954,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 		ravb_write(ndev, mask, RIE0);
 		ravb_write(ndev, mask, TIE);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	/* Receive error message handling */
@@ -1008,7 +1002,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 	if (priv->no_avb_link && phydev->link)
 		ravb_rcv_snd_enable(ndev);
 
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	if (new_state && netif_msg_link(priv))
@@ -1601,7 +1594,6 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		netif_stop_subqueue(ndev, q);
 
 exit:
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 	return NETDEV_TX_OK;
 
@@ -1673,7 +1665,6 @@ static void ravb_set_rx_mode(struct net_device *ndev)
 	spin_lock_irqsave(&priv->lock, flags);
 	ravb_modify(ndev, ECMR, ECMR_PRM,
 		    ndev->flags & IFF_PROMISC ? ECMR_PRM : 0);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index dce2a40a31e3..9a42580693cb 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -196,7 +196,6 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 		ravb_write(ndev, GIE_PTCS, GIE);
 	else
 		ravb_write(ndev, GID_PTCD, GID);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
@@ -259,7 +258,6 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 		else
 			ravb_write(ndev, GID_PTMD0, GID);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return error;
@@ -331,7 +329,6 @@ void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev)
 	spin_lock_irqsave(&priv->lock, flags);
 	ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
 	ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index e33af371b169..ed30aebdb941 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2010,7 +2010,6 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 	if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link)
 		sh_eth_rcv_snd_enable(ndev);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mdp->lock, flags);
 
 	if (new_state && netif_msg_link(mdp))
diff --git a/drivers/net/ethernet/sfc/falcon/io.h b/drivers/net/ethernet/sfc/falcon/io.h
index 7085ee1d5e2b..c3577643fbda 100644
--- a/drivers/net/ethernet/sfc/falcon/io.h
+++ b/drivers/net/ethernet/sfc/falcon/io.h
@@ -108,7 +108,6 @@ static inline void ef4_writeo(struct ef4_nic *efx, const ef4_oword_t *value,
 	_ef4_writed(efx, value->u32[2], reg + 8);
 	_ef4_writed(efx, value->u32[3], reg + 12);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
@@ -130,7 +129,6 @@ static inline void ef4_sram_writeq(struct ef4_nic *efx, void __iomem *membase,
 	__raw_writel((__force u32)value->u32[0], membase + addr);
 	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 89563170af52..2774a10f44e9 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -120,7 +120,6 @@ static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value,
 	_efx_writed(efx, value->u32[2], reg + 8);
 	_efx_writed(efx, value->u32[3], reg + 12);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
@@ -142,7 +141,6 @@ static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
 	__raw_writel((__force u32)value->u32[0], membase + addr);
 	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
index c07fd594fe71..02b3962b0e63 100644
--- a/drivers/net/ethernet/silan/sc92031.c
+++ b/drivers/net/ethernet/silan/sc92031.c
@@ -251,7 +251,6 @@ enum PMConfigBits {
  * use of mdelay() at _sc92031_reset.
  * Functions prefixed with _sc92031_ must be called with the lock held;
  * functions prefixed with sc92031_ must be called without the lock held.
- * Use mmiowb() before unlocking if the hardware was written to.
  */
 
 /* Locking rules for the interrupt:
@@ -361,7 +360,6 @@ static void sc92031_disable_interrupts(struct net_device *dev)
 	/* stop interrupts */
 	iowrite32(0, port_base + IntrMask);
 	_sc92031_dummy_read(port_base);
-	mmiowb();
 
 	/* wait for any concurrent interrupt/tasklet to finish */
 	synchronize_irq(priv->pdev->irq);
@@ -379,7 +377,6 @@ static void sc92031_enable_interrupts(struct net_device *dev)
 	wmb();
 
 	iowrite32(IntrBits, port_base + IntrMask);
-	mmiowb();
 }
 
 static void _sc92031_disable_tx_rx(struct net_device *dev)
@@ -867,7 +864,6 @@ out:
 	rmb();
 
 	iowrite32(intr_mask, port_base + IntrMask);
-	mmiowb();
 
 	spin_unlock(&priv->lock);
 }
@@ -901,7 +897,6 @@ out_none:
 	rmb();
 
 	iowrite32(intr_mask, port_base + IntrMask);
-	mmiowb();
 
 	return IRQ_NONE;
 }
@@ -978,7 +973,6 @@ static netdev_tx_t sc92031_start_xmit(struct sk_buff *skb,
 	iowrite32(priv->tx_bufs_dma_addr + entry * TX_BUF_SIZE,
 			port_base + TxAddr0 + entry * 4);
 	iowrite32(tx_status, port_base + TxStatus0 + entry * 4);
-	mmiowb();
 
 	if (priv->tx_head - priv->tx_tail >= NUM_TX_DESC)
 		netif_stop_queue(dev);
@@ -1024,7 +1018,6 @@ static int sc92031_open(struct net_device *dev)
 	spin_lock_bh(&priv->lock);
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 	sc92031_enable_interrupts(dev);
@@ -1060,7 +1053,6 @@ static int sc92031_stop(struct net_device *dev)
 
 	_sc92031_disable_tx_rx(dev);
 	_sc92031_tx_clear(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1081,7 +1073,6 @@ static void sc92031_set_multicast_list(struct net_device *dev)
 
 	_sc92031_set_mar(dev);
 	_sc92031_set_rx_config(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 }
@@ -1098,7 +1089,6 @@ static void sc92031_tx_timeout(struct net_device *dev)
 	priv->tx_timeouts++;
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock(&priv->lock);
 
@@ -1140,7 +1130,6 @@ sc92031_ethtool_get_link_ksettings(struct net_device *dev,
 
 	output_status = _sc92031_mii_read(port_base, MII_OutputStatus);
 	_sc92031_mii_scan(port_base);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1311,7 +1300,6 @@ static int sc92031_ethtool_set_wol(struct net_device *dev,
 
 	priv->pm_config = pm_config;
 	iowrite32(pm_config, port_base + PMConfig);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1337,7 +1325,6 @@ static int sc92031_ethtool_nway_reset(struct net_device *dev)
 
 out:
 	_sc92031_mii_scan(port_base);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1530,7 +1517,6 @@ static int sc92031_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	_sc92031_disable_tx_rx(dev);
 	_sc92031_tx_clear(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1555,7 +1541,6 @@ static int sc92031_resume(struct pci_dev *pdev)
 	spin_lock_bh(&priv->lock);
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 	sc92031_enable_interrupts(dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 062a600fa5a7..21428537e231 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -333,6 +333,9 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 	 */
 	dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev,
 							"stm32_pwr_wakeup");
+	if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
 	if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) {
 		err = device_init_wakeup(&pdev->dev, true);
 		if (err) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index cc1e887e47b5..26db6aa002d1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -160,7 +160,7 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 		.driver_data = (void *)&galileo_stmmac_dmi_data,
 	},
 	/*
-	 * There are 2 types of SIMATIC IOT2000: IOT20202 and IOT2040.
+	 * There are 2 types of SIMATIC IOT2000: IOT2020 and IOT2040.
 	 * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
 	 * has only one pci network device while other asset tags are
 	 * for IOT2040 which has two.
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 33949248c829..ab55416a10fa 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -571,7 +571,6 @@ static void rhine_ack_events(struct rhine_private *rp, u32 mask)
 	if (rp->quirks & rqStatusWBRace)
 		iowrite8(mask >> 16, ioaddr + IntrStatus2);
 	iowrite16(mask, ioaddr + IntrStatus);
-	mmiowb();
 }
 
 /*
@@ -863,7 +862,6 @@ static int rhine_napipoll(struct napi_struct *napi, int budget)
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
 		iowrite16(enable_mask, ioaddr + IntrEnable);
-		mmiowb();
 	}
 	return work_done;
 }
@@ -1893,7 +1891,6 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 static void rhine_irq_disable(struct rhine_private *rp)
 {
 	iowrite16(0x0000, rp->base + IntrEnable);
-	mmiowb();
 }
 
 /* The interrupt handler does all of the Rx thread work and cleans up
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index d8ba512f166a..1713c2d2dccf 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -219,7 +219,6 @@ static inline int __w5100_write_direct(struct net_device *ndev, u32 addr,
 static inline int w5100_write_direct(struct net_device *ndev, u32 addr, u8 data)
 {
 	__w5100_write_direct(ndev, addr, data);
-	mmiowb();
 
 	return 0;
 }
@@ -236,7 +235,6 @@ static int w5100_write16_direct(struct net_device *ndev, u32 addr, u16 data)
 {
 	__w5100_write_direct(ndev, addr, data >> 8);
 	__w5100_write_direct(ndev, addr + 1, data);
-	mmiowb();
 
 	return 0;
 }
@@ -260,8 +258,6 @@ static int w5100_writebulk_direct(struct net_device *ndev, u32 addr,
 	for (i = 0; i < len; i++, addr++)
 		__w5100_write_direct(ndev, addr, *buf++);
 
-	mmiowb();
-
 	return 0;
 }
 
@@ -375,7 +371,6 @@ static int w5100_readbulk_indirect(struct net_device *ndev, u32 addr, u8 *buf,
 	for (i = 0; i < len; i++)
 		*buf++ = w5100_read_direct(ndev, W5100_IDM_DR);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mmio_priv->reg_lock, flags);
 
 	return 0;
@@ -394,7 +389,6 @@ static int w5100_writebulk_indirect(struct net_device *ndev, u32 addr,
 	for (i = 0; i < len; i++)
 		__w5100_write_direct(ndev, W5100_IDM_DR, *buf++);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mmio_priv->reg_lock, flags);
 
 	return 0;
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index f9da5d6172e3..3f03eecc0479 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -141,7 +141,6 @@ static u16 w5300_read_indirect(struct w5300_priv *priv, u16 addr)
 
 	spin_lock_irqsave(&priv->reg_lock, flags);
 	w5300_write_direct(priv, W5300_IDM_AR, addr);
-	mmiowb();
 	data = w5300_read_direct(priv, W5300_IDM_DR);
 	spin_unlock_irqrestore(&priv->reg_lock, flags);
 
@@ -154,9 +153,7 @@ static void w5300_write_indirect(struct w5300_priv *priv, u16 addr, u16 data)
 
 	spin_lock_irqsave(&priv->reg_lock, flags);
 	w5300_write_direct(priv, W5300_IDM_AR, addr);
-	mmiowb();
 	w5300_write_direct(priv, W5300_IDM_DR, data);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->reg_lock, flags);
 }
 
@@ -192,7 +189,6 @@ static int w5300_command(struct w5300_priv *priv, u16 cmd)
 	unsigned long timeout = jiffies + msecs_to_jiffies(100);
 
 	w5300_write(priv, W5300_S0_CR, cmd);
-	mmiowb();
 
 	while (w5300_read(priv, W5300_S0_CR) != 0) {
 		if (time_after(jiffies, timeout))
@@ -241,18 +237,15 @@ static void w5300_write_macaddr(struct w5300_priv *priv)
 	w5300_write(priv, W5300_SHARH,
 		      ndev->dev_addr[4] << 8 |
 		      ndev->dev_addr[5]);
-	mmiowb();
 }
 
 static void w5300_hw_reset(struct w5300_priv *priv)
 {
 	w5300_write_direct(priv, W5300_MR, MR_RST);
-	mmiowb();
 	mdelay(5);
 	w5300_write_direct(priv, W5300_MR, priv->indirect ?
 				 MR_WDF(7) | MR_PB | MR_IND :
 				 MR_WDF(7) | MR_PB);
-	mmiowb();
 	w5300_write(priv, W5300_IMR, 0);
 	w5300_write_macaddr(priv);
 
@@ -264,24 +257,20 @@ static void w5300_hw_reset(struct w5300_priv *priv)
 	w5300_write32(priv, W5300_TMSRL, 64 << 24);
 	w5300_write32(priv, W5300_TMSRH, 0);
 	w5300_write(priv, W5300_MTYPE, 0x00ff);
-	mmiowb();
 }
 
 static void w5300_hw_start(struct w5300_priv *priv)
 {
 	w5300_write(priv, W5300_S0_MR, priv->promisc ?
 			  S0_MR_MACRAW : S0_MR_MACRAW_MF);
-	mmiowb();
 	w5300_command(priv, S0_CR_OPEN);
 	w5300_write(priv, W5300_S0_IMR, S0_IR_RECV | S0_IR_SENDOK);
 	w5300_write(priv, W5300_IMR, IR_S0);
-	mmiowb();
 }
 
 static void w5300_hw_close(struct w5300_priv *priv)
 {
 	w5300_write(priv, W5300_IMR, 0);
-	mmiowb();
 	w5300_command(priv, S0_CR_CLOSE);
 }
 
@@ -372,7 +361,6 @@ static netdev_tx_t w5300_start_tx(struct sk_buff *skb, struct net_device *ndev)
 	netif_stop_queue(ndev);
 
 	w5300_write_frame(priv, skb->data, skb->len);
-	mmiowb();
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += skb->len;
 	dev_kfree_skb(skb);
@@ -419,7 +407,6 @@ static int w5300_napi_poll(struct napi_struct *napi, int budget)
 	if (rx_count < budget) {
 		napi_complete_done(napi, rx_count);
 		w5300_write(priv, W5300_IMR, IR_S0);
-		mmiowb();
 	}
 
 	return rx_count;
@@ -434,7 +421,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
 	if (!ir)
 		return IRQ_NONE;
 	w5300_write(priv, W5300_S0_IR, ir);
-	mmiowb();
 
 	if (ir & S0_IR_SENDOK) {
 		netif_dbg(priv, tx_done, ndev, "tx done\n");
@@ -444,7 +430,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
 	if (ir & S0_IR_RECV) {
 		if (napi_schedule_prep(&priv->napi)) {
 			w5300_write(priv, W5300_IMR, 0);
-			mmiowb();
 			__napi_schedule(&priv->napi);
 		}
 	}
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index c589f5ae75bb..8bb53ec8d9cf 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -533,6 +533,8 @@ mcr20a_start(struct ieee802154_hw *hw)
 	dev_dbg(printdev(lp), "no slotted operation\n");
 	ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1,
 				 DAR_PHY_CTRL1_SLOTTED, 0x0);
+	if (ret < 0)
+		return ret;
 
 	/* enable irq */
 	enable_irq(lp->spi->irq);
@@ -540,11 +542,15 @@ mcr20a_start(struct ieee802154_hw *hw)
 	/* Unmask SEQ interrupt */
 	ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL2,
 				 DAR_PHY_CTRL2_SEQMSK, 0x0);
+	if (ret < 0)
+		return ret;
 
 	/* Start the RX sequence */
 	dev_dbg(printdev(lp), "start the RX sequence\n");
 	ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1,
 				 DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 3ccba37bd6dd..f76c4048b978 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1489,9 +1489,10 @@ static int marvell_get_sset_count(struct phy_device *phydev)
 
 static void marvell_get_strings(struct phy_device *phydev, u8 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) {
+	for (i = 0; i < count; i++) {
 		strlcpy(data + i * ETH_GSTRING_LEN,
 			marvell_hw_stats[i].string, ETH_GSTRING_LEN);
 	}
@@ -1519,9 +1520,10 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i)
 static void marvell_get_stats(struct phy_device *phydev,
 			      struct ethtool_stats *stats, u64 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++)
+	for (i = 0; i < count; i++)
 		data[i] = marvell_get_stat(phydev, i);
 }
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 9195f3476b1d..679e404a5224 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1122,9 +1122,16 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x0846, 0x68d3, 8)},	/* Netgear Aircard 779S */
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)},	/* Huawei E1820 */
+	{QMI_FIXED_INTF(0x1435, 0x0918, 3)},	/* Wistron NeWeb D16Q1 */
+	{QMI_FIXED_INTF(0x1435, 0x0918, 4)},	/* Wistron NeWeb D16Q1 */
+	{QMI_FIXED_INTF(0x1435, 0x0918, 5)},	/* Wistron NeWeb D16Q1 */
+	{QMI_FIXED_INTF(0x1435, 0x3185, 4)},	/* Wistron NeWeb M18Q5 */
+	{QMI_FIXED_INTF(0x1435, 0xd111, 4)},	/* M9615A DM11-1 D51QC */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 3)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 4)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 5)},	/* Wistron NeWeb D18Q1 */
+	{QMI_FIXED_INTF(0x1435, 0xd182, 4)},	/* Wistron NeWeb D18 */
+	{QMI_FIXED_INTF(0x1435, 0xd182, 5)},	/* Wistron NeWeb D18 */
 	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)},	/* Fibocom NL668 series */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
@@ -1180,6 +1187,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x0265, 4)},	/* ONDA MT8205 4G LTE */
 	{QMI_FIXED_INTF(0x19d2, 0x0284, 4)},	/* ZTE MF880 */
 	{QMI_FIXED_INTF(0x19d2, 0x0326, 4)},	/* ZTE MF821D */
+	{QMI_FIXED_INTF(0x19d2, 0x0396, 3)},	/* ZTE ZM8620 */
 	{QMI_FIXED_INTF(0x19d2, 0x0412, 4)},	/* Telewell TW-LTE 4G */
 	{QMI_FIXED_INTF(0x19d2, 0x1008, 4)},	/* ZTE (Vodafone) K3570-Z */
 	{QMI_FIXED_INTF(0x19d2, 0x1010, 4)},	/* ZTE (Vodafone) K3571-Z */
@@ -1200,7 +1208,9 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
 	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
+	{QMI_FIXED_INTF(0x19d2, 0x1432, 3)},	/* ZTE ME3620 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
+	{QMI_FIXED_INTF(0x2001, 0x7e16, 3)},	/* D-Link DWM-221 */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
 	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index 24b983edb357..eca87f7c5b6c 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -1855,7 +1855,7 @@ void ath10k_ce_dump_registers(struct ath10k *ar,
 	struct ath10k_ce_crash_data ce_data;
 	u32 addr, id;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	ath10k_err(ar, "Copy Engine register dump:\n");
 
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 835b8de92d55..aff585658fc0 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -3119,6 +3119,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 		goto err_free_wq;
 
 	mutex_init(&ar->conf_mutex);
+	mutex_init(&ar->dump_mutex);
 	spin_lock_init(&ar->data_lock);
 
 	INIT_LIST_HEAD(&ar->peers);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index e08a17b01e03..e35aae5146f1 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1063,6 +1063,9 @@ struct ath10k {
 	/* prevents concurrent FW reconfiguration */
 	struct mutex conf_mutex;
 
+	/* protects coredump data */
+	struct mutex dump_mutex;
+
 	/* protects shared structure data */
 	spinlock_t data_lock;
 
diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c
index 33838d9c1cb6..45a355fb62b9 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.c
+++ b/drivers/net/wireless/ath/ath10k/coredump.c
@@ -1102,7 +1102,7 @@ struct ath10k_fw_crash_data *ath10k_coredump_new(struct ath10k *ar)
 {
 	struct ath10k_fw_crash_data *crash_data = ar->coredump.fw_crash_data;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	if (ath10k_coredump_mask == 0)
 		/* coredump disabled */
@@ -1146,7 +1146,7 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar)
 	if (!buf)
 		return NULL;
 
-	spin_lock_bh(&ar->data_lock);
+	mutex_lock(&ar->dump_mutex);
 
 	dump_data = (struct ath10k_dump_file_data *)(buf);
 	strlcpy(dump_data->df_magic, "ATH10K-FW-DUMP",
@@ -1213,7 +1213,7 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar)
 		sofar += sizeof(*dump_tlv) + crash_data->ramdump_buf_len;
 	}
 
-	spin_unlock_bh(&ar->data_lock);
+	mutex_unlock(&ar->dump_mutex);
 
 	return dump_data;
 }
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 41e89db244d2..9c703d287333 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -5774,7 +5774,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_MCAST_RATE &&
-	    !WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def))) {
+	    !ath10k_mac_vif_chan(arvif->vif, &def)) {
 		band = def.chan->band;
 		rateidx = vif->bss_conf.mcast_rate[band] - 1;
 
@@ -5812,7 +5812,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_BASIC_RATES) {
-		if (WARN_ON(ath10k_mac_vif_chan(vif, &def))) {
+		if (ath10k_mac_vif_chan(vif, &def)) {
 			mutex_unlock(&ar->conf_mutex);
 			return;
 		}
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 271f92c24d44..2c27f407a851 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -1441,7 +1441,7 @@ static void ath10k_pci_dump_registers(struct ath10k *ar,
 	__le32 reg_dump_values[REG_DUMP_COUNT_QCA988X] = {};
 	int i, ret;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	ret = ath10k_pci_diag_read_hi(ar, &reg_dump_values[0],
 				      hi_failure_state,
@@ -1656,7 +1656,7 @@ static void ath10k_pci_dump_memory(struct ath10k *ar,
 	int ret, i;
 	u8 *buf;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	if (!crash_data)
 		return;
@@ -1734,14 +1734,19 @@ static void ath10k_pci_dump_memory(struct ath10k *ar,
 	}
 }
 
-static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
+static void ath10k_pci_fw_dump_work(struct work_struct *work)
 {
+	struct ath10k_pci *ar_pci = container_of(work, struct ath10k_pci,
+						 dump_work);
 	struct ath10k_fw_crash_data *crash_data;
+	struct ath10k *ar = ar_pci->ar;
 	char guid[UUID_STRING_LEN + 1];
 
-	spin_lock_bh(&ar->data_lock);
+	mutex_lock(&ar->dump_mutex);
 
+	spin_lock_bh(&ar->data_lock);
 	ar->stats.fw_crash_counter++;
+	spin_unlock_bh(&ar->data_lock);
 
 	crash_data = ath10k_coredump_new(ar);
 
@@ -1756,11 +1761,18 @@ static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
 	ath10k_ce_dump_registers(ar, crash_data);
 	ath10k_pci_dump_memory(ar, crash_data);
 
-	spin_unlock_bh(&ar->data_lock);
+	mutex_unlock(&ar->dump_mutex);
 
 	queue_work(ar->workqueue, &ar->restart_work);
 }
 
+static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
+{
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+
+	queue_work(ar->workqueue, &ar_pci->dump_work);
+}
+
 void ath10k_pci_hif_send_complete_check(struct ath10k *ar, u8 pipe,
 					int force)
 {
@@ -3442,6 +3454,8 @@ int ath10k_pci_setup_resource(struct ath10k *ar)
 	spin_lock_init(&ar_pci->ps_lock);
 	mutex_init(&ar_pci->ce_diag_mutex);
 
+	INIT_WORK(&ar_pci->dump_work, ath10k_pci_fw_dump_work);
+
 	timer_setup(&ar_pci->rx_post_retry, ath10k_pci_rx_replenish_retry, 0);
 
 	if (QCA_REV_6174(ar) || QCA_REV_9377(ar))
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index 3773c79f322f..4455ed6c5275 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -121,6 +121,8 @@ struct ath10k_pci {
 	/* For protecting ce_diag */
 	struct mutex ce_diag_mutex;
 
+	struct work_struct dump_work;
+
 	struct ath10k_ce ce;
 	struct timer_list rx_post_retry;
 
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index a2351ef45ae0..65a4c142640d 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -837,7 +837,6 @@ ath5k_txbuf_setup(struct ath5k_hw *ah, struct ath5k_buf *bf,
 
 	txq->link = &ds->ds_link;
 	ath5k_hw_start_tx_dma(ah, txq->qnum);
-	mmiowb();
 	spin_unlock_bh(&txq->lock);
 
 	return 0;
@@ -2174,7 +2173,6 @@ ath5k_beacon_config(struct ath5k_hw *ah)
 	}
 
 	ath5k_hw_set_imr(ah, ah->imask);
-	mmiowb();
 	spin_unlock_bh(&ah->block);
 }
 
@@ -2779,7 +2777,6 @@ int ath5k_start(struct ieee80211_hw *hw)
 
 	ret = 0;
 done:
-	mmiowb();
 	mutex_unlock(&ah->lock);
 
 	set_bit(ATH_STAT_STARTED, ah->status);
@@ -2839,7 +2836,6 @@ void ath5k_stop(struct ieee80211_hw *hw)
 				"putting device to sleep\n");
 	}
 
-	mmiowb();
 	mutex_unlock(&ah->lock);
 
 	ath5k_stop_tasklets(ah);
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index 16e052d02c94..5e866a193ed0 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -263,7 +263,6 @@ ath5k_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		memcpy(common->curbssid, bss_conf->bssid, ETH_ALEN);
 		common->curaid = 0;
 		ath5k_hw_set_bssid(ah);
-		mmiowb();
 	}
 
 	if (changes & BSS_CHANGED_BEACON_INT)
@@ -528,7 +527,6 @@ ath5k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		ret = -EINVAL;
 	}
 
-	mmiowb();
 	mutex_unlock(&ah->lock);
 	return ret;
 }
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 74be3c809225..4c7980f84591 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -485,7 +485,6 @@ static void b43_ram_write(struct b43_wldev *dev, u16 offset, u32 val)
 		val = swab32(val);
 
 	b43_write32(dev, B43_MMIO_RAM_CONTROL, offset);
-	mmiowb();
 	b43_write32(dev, B43_MMIO_RAM_DATA, val);
 }
 
@@ -656,9 +655,7 @@ static void b43_tsf_write_locked(struct b43_wldev *dev, u64 tsf)
 	/* The hardware guarantees us an atomic write, if we
 	 * write the low register first. */
 	b43_write32(dev, B43_MMIO_REV3PLUS_TSF_LOW, low);
-	mmiowb();
 	b43_write32(dev, B43_MMIO_REV3PLUS_TSF_HIGH, high);
-	mmiowb();
 }
 
 void b43_tsf_write(struct b43_wldev *dev, u64 tsf)
@@ -1822,11 +1819,9 @@ static void b43_beacon_update_trigger_work(struct work_struct *work)
 		if (b43_bus_host_is_sdio(dev->dev)) {
 			/* wl->mutex is enough. */
 			b43_do_beacon_update_trigger_work(dev);
-			mmiowb();
 		} else {
 			spin_lock_irq(&wl->hardirq_lock);
 			b43_do_beacon_update_trigger_work(dev);
-			mmiowb();
 			spin_unlock_irq(&wl->hardirq_lock);
 		}
 	}
@@ -2078,7 +2073,6 @@ static irqreturn_t b43_interrupt_thread_handler(int irq, void *dev_id)
 
 	mutex_lock(&dev->wl->mutex);
 	b43_do_interrupt_thread(dev);
-	mmiowb();
 	mutex_unlock(&dev->wl->mutex);
 
 	return IRQ_HANDLED;
@@ -2143,7 +2137,6 @@ static irqreturn_t b43_interrupt_handler(int irq, void *dev_id)
 
 	spin_lock(&dev->wl->hardirq_lock);
 	ret = b43_do_interrupt(dev);
-	mmiowb();
 	spin_unlock(&dev->wl->hardirq_lock);
 
 	return ret;
diff --git a/drivers/net/wireless/broadcom/b43/sysfs.c b/drivers/net/wireless/broadcom/b43/sysfs.c
index 3190493bd07f..93d03b673670 100644
--- a/drivers/net/wireless/broadcom/b43/sysfs.c
+++ b/drivers/net/wireless/broadcom/b43/sysfs.c
@@ -129,7 +129,6 @@ static ssize_t b43_attr_interfmode_store(struct device *dev,
 	} else
 		err = -ENOSYS;
 
-	mmiowb();
 	mutex_unlock(&wldev->wl->mutex);
 
 	return err ? err : count;
diff --git a/drivers/net/wireless/broadcom/b43legacy/ilt.c b/drivers/net/wireless/broadcom/b43legacy/ilt.c
index ee5682e54204..6d15fb4d30c6 100644
--- a/drivers/net/wireless/broadcom/b43legacy/ilt.c
+++ b/drivers/net/wireless/broadcom/b43legacy/ilt.c
@@ -315,14 +315,12 @@ const u16 b43legacy_ilt_sigmasqr2[B43legacy_ILT_SIGMASQR_SIZE] = {
 void b43legacy_ilt_write(struct b43legacy_wldev *dev, u16 offset, u16 val)
 {
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_CTRL, offset);
-	mmiowb();
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA1, val);
 }
 
 void b43legacy_ilt_write32(struct b43legacy_wldev *dev, u16 offset, u32 val)
 {
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_CTRL, offset);
-	mmiowb();
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA2,
 			    (val & 0xFFFF0000) >> 16);
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA1,
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index 55f411925960..c777efc6dc13 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -264,7 +264,6 @@ static void b43legacy_ram_write(struct b43legacy_wldev *dev, u16 offset,
 		val = swab32(val);
 
 	b43legacy_write32(dev, B43legacy_MMIO_RAM_CONTROL, offset);
-	mmiowb();
 	b43legacy_write32(dev, B43legacy_MMIO_RAM_DATA, val);
 }
 
@@ -341,14 +340,11 @@ void b43legacy_shm_write32(struct b43legacy_wldev *dev,
 		if (offset & 0x0003) {
 			/* Unaligned access */
 			b43legacy_shm_control_word(dev, routing, offset >> 2);
-			mmiowb();
 			b43legacy_write16(dev,
 					  B43legacy_MMIO_SHM_DATA_UNALIGNED,
 					  (value >> 16) & 0xffff);
-			mmiowb();
 			b43legacy_shm_control_word(dev, routing,
 						   (offset >> 2) + 1);
-			mmiowb();
 			b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA,
 					  value & 0xffff);
 			return;
@@ -356,7 +352,6 @@ void b43legacy_shm_write32(struct b43legacy_wldev *dev,
 		offset >>= 2;
 	}
 	b43legacy_shm_control_word(dev, routing, offset);
-	mmiowb();
 	b43legacy_write32(dev, B43legacy_MMIO_SHM_DATA, value);
 }
 
@@ -368,7 +363,6 @@ void b43legacy_shm_write16(struct b43legacy_wldev *dev, u16 routing, u16 offset,
 		if (offset & 0x0003) {
 			/* Unaligned access */
 			b43legacy_shm_control_word(dev, routing, offset >> 2);
-			mmiowb();
 			b43legacy_write16(dev,
 					  B43legacy_MMIO_SHM_DATA_UNALIGNED,
 					  value);
@@ -377,7 +371,6 @@ void b43legacy_shm_write16(struct b43legacy_wldev *dev, u16 routing, u16 offset,
 		offset >>= 2;
 	}
 	b43legacy_shm_control_word(dev, routing, offset);
-	mmiowb();
 	b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA, value);
 }
 
@@ -471,7 +464,6 @@ static void b43legacy_time_lock(struct b43legacy_wldev *dev)
 	status = b43legacy_read32(dev, B43legacy_MMIO_MACCTL);
 	status |= B43legacy_MACCTL_TBTTHOLD;
 	b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status);
-	mmiowb();
 }
 
 static void b43legacy_time_unlock(struct b43legacy_wldev *dev)
@@ -494,10 +486,8 @@ static void b43legacy_tsf_write_locked(struct b43legacy_wldev *dev, u64 tsf)
 		u32 hi = (tsf & 0xFFFFFFFF00000000ULL) >> 32;
 
 		b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_LOW, 0);
-		mmiowb();
 		b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_HIGH,
 				    hi);
-		mmiowb();
 		b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_LOW,
 				    lo);
 	} else {
@@ -507,13 +497,9 @@ static void b43legacy_tsf_write_locked(struct b43legacy_wldev *dev, u64 tsf)
 		u16 v3 = (tsf & 0xFFFF000000000000ULL) >> 48;
 
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_0, 0);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_3, v3);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_2, v2);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_1, v1);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_0, v0);
 	}
 }
@@ -1250,7 +1236,6 @@ static void b43legacy_beacon_update_trigger_work(struct work_struct *work)
 		/* The handler might have updated the IRQ mask. */
 		b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK,
 				  dev->irq_mask);
-		mmiowb();
 		spin_unlock_irq(&wl->irq_lock);
 	}
 	mutex_unlock(&wl->mutex);
@@ -1346,7 +1331,6 @@ static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev)
 			       dma_reason[2], dma_reason[3],
 			       dma_reason[4], dma_reason[5]);
 			b43legacy_controller_restart(dev, "DMA error");
-			mmiowb();
 			spin_unlock_irqrestore(&dev->wl->irq_lock, flags);
 			return;
 		}
@@ -1396,7 +1380,6 @@ static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev)
 		handle_irq_transmit_status(dev);
 
 	b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask);
-	mmiowb();
 	spin_unlock_irqrestore(&dev->wl->irq_lock, flags);
 }
 
@@ -1488,7 +1471,6 @@ static irqreturn_t b43legacy_interrupt_handler(int irq, void *dev_id)
 	dev->irq_reason = reason;
 	tasklet_schedule(&dev->isr_tasklet);
 out:
-	mmiowb();
 	spin_unlock(&dev->wl->irq_lock);
 
 	return ret;
@@ -2781,7 +2763,6 @@ static int b43legacy_op_dev_config(struct ieee80211_hw *hw,
 
 	spin_lock_irqsave(&wl->irq_lock, flags);
 	b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask);
-	mmiowb();
 	spin_unlock_irqrestore(&wl->irq_lock, flags);
 out_unlock_mutex:
 	mutex_unlock(&wl->mutex);
@@ -2900,7 +2881,6 @@ static void b43legacy_op_bss_info_changed(struct ieee80211_hw *hw,
 	spin_lock_irqsave(&wl->irq_lock, flags);
 	b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask);
 	/* XXX: why? */
-	mmiowb();
 	spin_unlock_irqrestore(&wl->irq_lock, flags);
  out_unlock_mutex:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/broadcom/b43legacy/phy.c b/drivers/net/wireless/broadcom/b43legacy/phy.c
index 995c7d0c212a..f949766d27ca 100644
--- a/drivers/net/wireless/broadcom/b43legacy/phy.c
+++ b/drivers/net/wireless/broadcom/b43legacy/phy.c
@@ -134,7 +134,6 @@ u16 b43legacy_phy_read(struct b43legacy_wldev *dev, u16 offset)
 void b43legacy_phy_write(struct b43legacy_wldev *dev, u16 offset, u16 val)
 {
 	b43legacy_write16(dev, B43legacy_MMIO_PHY_CONTROL, offset);
-	mmiowb();
 	b43legacy_write16(dev, B43legacy_MMIO_PHY_DATA, val);
 }
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/pio.h b/drivers/net/wireless/broadcom/b43legacy/pio.h
index 1cd1b9ca5e9c..08cd02282beb 100644
--- a/drivers/net/wireless/broadcom/b43legacy/pio.h
+++ b/drivers/net/wireless/broadcom/b43legacy/pio.h
@@ -92,7 +92,6 @@ void b43legacy_pio_write(struct b43legacy_pioqueue *queue,
 		       u16 offset, u16 value)
 {
 	b43legacy_write16(queue->dev, queue->mmio_base + offset, value);
-	mmiowb();
 }
 
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c
index eab1c9387846..c6db444ea07e 100644
--- a/drivers/net/wireless/broadcom/b43legacy/radio.c
+++ b/drivers/net/wireless/broadcom/b43legacy/radio.c
@@ -95,7 +95,6 @@ void b43legacy_radio_lock(struct b43legacy_wldev *dev)
 	B43legacy_WARN_ON(status & B43legacy_MACCTL_RADIOLOCK);
 	status |= B43legacy_MACCTL_RADIOLOCK;
 	b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status);
-	mmiowb();
 	udelay(10);
 }
 
@@ -108,7 +107,6 @@ void b43legacy_radio_unlock(struct b43legacy_wldev *dev)
 	B43legacy_WARN_ON(!(status & B43legacy_MACCTL_RADIOLOCK));
 	status &= ~B43legacy_MACCTL_RADIOLOCK;
 	b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status);
-	mmiowb();
 }
 
 u16 b43legacy_radio_read16(struct b43legacy_wldev *dev, u16 offset)
@@ -141,7 +139,6 @@ u16 b43legacy_radio_read16(struct b43legacy_wldev *dev, u16 offset)
 void b43legacy_radio_write16(struct b43legacy_wldev *dev, u16 offset, u16 val)
 {
 	b43legacy_write16(dev, B43legacy_MMIO_RADIO_CONTROL, offset);
-	mmiowb();
 	b43legacy_write16(dev, B43legacy_MMIO_RADIO_DATA_LOW, val);
 }
 
@@ -333,7 +330,6 @@ u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev)
 void b43legacy_nrssi_hw_write(struct b43legacy_wldev *dev, u16 offset, s16 val)
 {
 	b43legacy_phy_write(dev, B43legacy_PHY_NRSSILT_CTRL, offset);
-	mmiowb();
 	b43legacy_phy_write(dev, B43legacy_PHY_NRSSILT_DATA, (u16)val);
 }
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/sysfs.c b/drivers/net/wireless/broadcom/b43legacy/sysfs.c
index 2a1da15c913b..2db83eec7a11 100644
--- a/drivers/net/wireless/broadcom/b43legacy/sysfs.c
+++ b/drivers/net/wireless/broadcom/b43legacy/sysfs.c
@@ -143,7 +143,6 @@ static ssize_t b43legacy_attr_interfmode_store(struct device *dev,
 	if (err)
 		b43legacyerr(wldev->wl, "Interference Mitigation not "
 		       "supported by device\n");
-	mmiowb();
 	spin_unlock_irqrestore(&wldev->wl->irq_lock, flags);
 	mutex_unlock(&wldev->wl->mutex);
 
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index b079c64ca014..986646af8dfd 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -2030,13 +2030,6 @@ static inline void
 _il_release_nic_access(struct il_priv *il)
 {
 	_il_clear_bit(il, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
-	/*
-	 * In above we are reading CSR_GP_CNTRL register, what will flush any
-	 * previous writes, but still want write, which clear MAC_ACCESS_REQ
-	 * bit, be performed on PCI bus before any other writes scheduled on
-	 * different CPUs (after we drop reg_lock).
-	 */
-	mmiowb();
 }
 
 static inline u32
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index eb6defb6d0cd..0a87d87fbb4f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -201,7 +201,7 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 #define IWL_DEVICE_AX210						\
 	IWL_DEVICE_AX200_COMMON,					\
 	.device_family = IWL_DEVICE_FAMILY_AX210,			\
-	.base_params = &iwl_22000_base_params,				\
+	.base_params = &iwl_22560_base_params,				\
 	.csr = &iwl_csr_v1,						\
 	.min_txq_size = 128
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
index 575a7022d045..3846064d51a5 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
@@ -1,7 +1,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of version 2 of the GNU General Public License as
@@ -136,6 +136,7 @@ const struct iwl_cfg iwl5350_agn_cfg = {
 	.ht_params = &iwl5000_ht_params,
 	.led_mode = IWL_LED_BLINK,
 	.internal_wimax_coex = true,
+	.csr = &iwl_csr_v1,
 };
 
 #define IWL_DEVICE_5150						\
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 641c95d03b15..e06407dc088b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -93,7 +93,7 @@ struct iwl_ucode_header {
 	} u;
 };
 
-#define IWL_UCODE_INI_TLV_GROUP	BIT(24)
+#define IWL_UCODE_INI_TLV_GROUP	0x1000000
 
 /*
  * new TLV uCode file layout
@@ -148,11 +148,14 @@ enum iwl_ucode_tlv_type {
 	IWL_UCODE_TLV_UMAC_DEBUG_ADDRS	= 54,
 	IWL_UCODE_TLV_LMAC_DEBUG_ADDRS	= 55,
 	IWL_UCODE_TLV_FW_RECOVERY_INFO	= 57,
-	IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION	= IWL_UCODE_INI_TLV_GROUP | 0x1,
-	IWL_UCODE_TLV_TYPE_HCMD			= IWL_UCODE_INI_TLV_GROUP | 0x2,
-	IWL_UCODE_TLV_TYPE_REGIONS		= IWL_UCODE_INI_TLV_GROUP | 0x3,
-	IWL_UCODE_TLV_TYPE_TRIGGERS		= IWL_UCODE_INI_TLV_GROUP | 0x4,
-	IWL_UCODE_TLV_TYPE_DEBUG_FLOW		= IWL_UCODE_INI_TLV_GROUP | 0x5,
+
+	IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION	= IWL_UCODE_INI_TLV_GROUP + 0x1,
+	IWL_UCODE_TLV_DEBUG_BASE = IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION,
+	IWL_UCODE_TLV_TYPE_HCMD			= IWL_UCODE_INI_TLV_GROUP + 0x2,
+	IWL_UCODE_TLV_TYPE_REGIONS		= IWL_UCODE_INI_TLV_GROUP + 0x3,
+	IWL_UCODE_TLV_TYPE_TRIGGERS		= IWL_UCODE_INI_TLV_GROUP + 0x4,
+	IWL_UCODE_TLV_TYPE_DEBUG_FLOW		= IWL_UCODE_INI_TLV_GROUP + 0x5,
+	IWL_UCODE_TLV_DEBUG_MAX = IWL_UCODE_TLV_TYPE_DEBUG_FLOW,
 
 	/* TLVs 0x1000-0x2000 are for internal driver usage */
 	IWL_UCODE_TLV_FW_DBG_DUMP_LST	= 0x1000,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 5798f434f68f..c7070760a10a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -126,7 +126,8 @@ void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data,
 		len -= ALIGN(tlv_len, 4);
 		data += sizeof(*tlv) + ALIGN(tlv_len, 4);
 
-		if (!(tlv_type & IWL_UCODE_INI_TLV_GROUP))
+		if (tlv_type < IWL_UCODE_TLV_DEBUG_BASE ||
+		    tlv_type > IWL_UCODE_TLV_DEBUG_MAX)
 			continue;
 
 		hdr = (void *)&tlv->data[0];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index 2453ceabf00d..6925527d8457 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -774,8 +774,7 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		return;
 
 	mvmvif->dbgfs_dir = debugfs_create_dir("iwlmvm", dbgfs_dir);
-
-	if (!mvmvif->dbgfs_dir) {
+	if (IS_ERR_OR_NULL(mvmvif->dbgfs_dir)) {
 		IWL_ERR(mvm, "Failed to create debugfs directory under %pd\n",
 			dbgfs_dir);
 		return;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 00a47f6f1d81..ab68b5d53ec9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1121,7 +1121,9 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	ret = iwl_mvm_load_rt_fw(mvm);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
-		iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
+		if (ret != -ERFKILL)
+			iwl_fw_dbg_error_collect(&mvm->fwrt,
+						 FW_DBG_TRIGGER_DRIVER);
 		goto error;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index ba27dce4c2bb..13681b03c10e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -834,7 +834,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	mutex_lock(&mvm->mutex);
 	iwl_mvm_ref(mvm, IWL_MVM_REF_INIT_UCODE);
 	err = iwl_run_init_mvm_ucode(mvm, true);
-	if (err)
+	if (err && err != -ERFKILL)
 		iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
 	if (!iwlmvm_mod_params.init_dbg || !err)
 		iwl_mvm_stop_device(mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 1e03acf30762..b516fd1867ec 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -169,9 +169,9 @@ static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb,
 }
 
 /* iwl_mvm_create_skb Adds the rxb to a new skb */
-static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
-			       u16 len, u8 crypt_len,
-			       struct iwl_rx_cmd_buffer *rxb)
+static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
+			      struct ieee80211_hdr *hdr, u16 len, u8 crypt_len,
+			      struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
@@ -204,6 +204,20 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
 	 * present before copying packet data.
 	 */
 	hdrlen += crypt_len;
+
+	if (WARN_ONCE(headlen < hdrlen,
+		      "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n",
+		      hdrlen, len, crypt_len)) {
+		/*
+		 * We warn and trace because we want to be able to see
+		 * it in trace-cmd as well.
+		 */
+		IWL_DEBUG_RX(mvm,
+			     "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n",
+			     hdrlen, len, crypt_len);
+		return -EINVAL;
+	}
+
 	skb_put_data(skb, hdr, hdrlen);
 	skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen);
 
@@ -216,6 +230,8 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
 		skb_add_rx_frag(skb, 0, rxb_steal_page(rxb), offset,
 				fraglen, rxb->truesize);
 	}
+
+	return 0;
 }
 
 static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm,
@@ -1671,7 +1687,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			rx_status->boottime_ns = ktime_get_boot_ns();
 	}
 
-	iwl_mvm_create_skb(skb, hdr, len, crypt_len, rxb);
+	if (iwl_mvm_create_skb(mvm, skb, hdr, len, crypt_len, rxb)) {
+		kfree_skb(skb);
+		goto out;
+	}
+
 	if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc))
 		iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue,
 						sta, csi);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 79c1dc05f948..4f5eec7e44bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2067,7 +2067,6 @@ static void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans,
 	 * MAC_ACCESS_REQ bit to be performed before any other writes
 	 * scheduled on different CPUs (after we drop reg_lock).
 	 */
-	mmiowb();
 out:
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, *flags);
 }
@@ -3644,20 +3643,27 @@ out_no_pci:
 
 void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	unsigned long timeout = jiffies + IWL_TRANS_NMI_TIMEOUT;
+	u32 inta_addr, sw_err_bit;
+
+	if (trans_pcie->msix_enabled) {
+		inta_addr = CSR_MSIX_HW_INT_CAUSES_AD;
+		sw_err_bit = MSIX_HW_INT_CAUSES_REG_SW_ERR;
+	} else {
+		inta_addr = CSR_INT;
+		sw_err_bit = CSR_INT_BIT_SW_ERR;
+	}
 
 	iwl_disable_interrupts(trans);
 	iwl_force_nmi(trans);
 	while (time_after(timeout, jiffies)) {
-		u32 inta_hw = iwl_read32(trans,
-					 CSR_MSIX_HW_INT_CAUSES_AD);
+		u32 inta_hw = iwl_read32(trans, inta_addr);
 
 		/* Error detected by uCode */
-		if (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR) {
+		if (inta_hw & sw_err_bit) {
 			/* Clear causes register */
-			iwl_write32(trans, CSR_MSIX_HW_INT_CAUSES_AD,
-				    inta_hw &
-				    MSIX_HW_INT_CAUSES_REG_SW_ERR);
+			iwl_write32(trans, inta_addr, inta_hw & sw_err_bit);
 			break;
 		}
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 524eb5805995..c71adb1f1f41 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -521,7 +521,7 @@ struct mac80211_hwsim_data {
 	unsigned int rx_filter;
 	bool started, idle, scanning;
 	struct mutex mutex;
-	struct tasklet_hrtimer beacon_timer;
+	struct hrtimer beacon_timer;
 	enum ps_mode {
 		PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL
 	} ps;
@@ -1460,7 +1460,7 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
 {
 	struct mac80211_hwsim_data *data = hw->priv;
 	data->started = false;
-	tasklet_hrtimer_cancel(&data->beacon_timer);
+	hrtimer_cancel(&data->beacon_timer);
 	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 }
 
@@ -1583,14 +1583,12 @@ static enum hrtimer_restart
 mac80211_hwsim_beacon(struct hrtimer *timer)
 {
 	struct mac80211_hwsim_data *data =
-		container_of(timer, struct mac80211_hwsim_data,
-			     beacon_timer.timer);
+		container_of(timer, struct mac80211_hwsim_data, beacon_timer);
 	struct ieee80211_hw *hw = data->hw;
 	u64 bcn_int = data->beacon_int;
-	ktime_t next_bcn;
 
 	if (!data->started)
-		goto out;
+		return HRTIMER_NORESTART;
 
 	ieee80211_iterate_active_interfaces_atomic(
 		hw, IEEE80211_IFACE_ITER_NORMAL,
@@ -1601,12 +1599,9 @@ mac80211_hwsim_beacon(struct hrtimer *timer)
 		bcn_int -= data->bcn_delta;
 		data->bcn_delta = 0;
 	}
-
-	next_bcn = ktime_add(hrtimer_get_expires(timer),
-			     ns_to_ktime(bcn_int * 1000));
-	tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS);
-out:
-	return HRTIMER_NORESTART;
+	hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
+			ns_to_ktime(bcn_int * NSEC_PER_USEC));
+	return HRTIMER_RESTART;
 }
 
 static const char * const hwsim_chanwidths[] = {
@@ -1680,15 +1675,15 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
 	mutex_unlock(&data->mutex);
 
 	if (!data->started || !data->beacon_int)
-		tasklet_hrtimer_cancel(&data->beacon_timer);
-	else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
+		hrtimer_cancel(&data->beacon_timer);
+	else if (!hrtimer_is_queued(&data->beacon_timer)) {
 		u64 tsf = mac80211_hwsim_get_tsf(hw, NULL);
 		u32 bcn_int = data->beacon_int;
 		u64 until_tbtt = bcn_int - do_div(tsf, bcn_int);
 
-		tasklet_hrtimer_start(&data->beacon_timer,
-				      ns_to_ktime(until_tbtt * 1000),
-				      HRTIMER_MODE_REL);
+		hrtimer_start(&data->beacon_timer,
+			      ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+			      HRTIMER_MODE_REL_SOFT);
 	}
 
 	return 0;
@@ -1751,7 +1746,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			  info->enable_beacon, info->beacon_int);
 		vp->bcn_en = info->enable_beacon;
 		if (data->started &&
-		    !hrtimer_is_queued(&data->beacon_timer.timer) &&
+		    !hrtimer_is_queued(&data->beacon_timer) &&
 		    info->enable_beacon) {
 			u64 tsf, until_tbtt;
 			u32 bcn_int;
@@ -1759,9 +1754,10 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			tsf = mac80211_hwsim_get_tsf(hw, vif);
 			bcn_int = data->beacon_int;
 			until_tbtt = bcn_int - do_div(tsf, bcn_int);
-			tasklet_hrtimer_start(&data->beacon_timer,
-					      ns_to_ktime(until_tbtt * 1000),
-					      HRTIMER_MODE_REL);
+
+			hrtimer_start(&data->beacon_timer,
+				      ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL_SOFT);
 		} else if (!info->enable_beacon) {
 			unsigned int count = 0;
 			ieee80211_iterate_active_interfaces_atomic(
@@ -1770,7 +1766,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			wiphy_dbg(hw->wiphy, "  beaconing vifs remaining: %u",
 				  count);
 			if (count == 0) {
-				tasklet_hrtimer_cancel(&data->beacon_timer);
+				hrtimer_cancel(&data->beacon_timer);
 				data->beacon_int = 0;
 			}
 		}
@@ -2933,9 +2929,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
-	tasklet_hrtimer_init(&data->beacon_timer,
-			     mac80211_hwsim_beacon,
-			     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_ABS_SOFT);
+	data->beacon_timer.function = mac80211_hwsim_beacon;
 
 	err = ieee80211_register_hw(hw);
 	if (err < 0) {
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index a85648342d15..d5a70340a945 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -181,7 +181,7 @@ static int mwifiex_sdio_resume(struct device *dev)
 
 	adapter = card->adapter;
 
-	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
+	if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, WARN,
 			    "device already resumed\n");
 		return 0;
diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c
index 1dede87dd54f..dcf234680535 100644
--- a/drivers/ntb/hw/idt/ntb_hw_idt.c
+++ b/drivers/ntb/hw/idt/ntb_hw_idt.c
@@ -358,8 +358,6 @@ static void idt_sw_write(struct idt_ntb_dev *ndev,
 	iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR);
 	/* Put the new value of the register */
 	iowrite32(data, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA);
-	/* Make sure the PCIe transactions are executed */
-	mmiowb();
 	/* Unlock GASA registers operations */
 	spin_unlock_irqrestore(&ndev->gasa_lock, irqflags);
 }
@@ -750,7 +748,6 @@ static void idt_ntb_local_link_enable(struct idt_ntb_dev *ndev)
 	spin_lock_irqsave(&ndev->mtbl_lock, irqflags);
 	idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part);
 	idt_nt_write(ndev, IDT_NT_NTMTBLDATA, mtbldata);
-	mmiowb();
 	spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags);
 
 	/* Notify the peers by setting and clearing the global signal bit */
@@ -778,7 +775,6 @@ static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev)
 	spin_lock_irqsave(&ndev->mtbl_lock, irqflags);
 	idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part);
 	idt_nt_write(ndev, IDT_NT_NTMTBLDATA, 0);
-	mmiowb();
 	spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags);
 
 	/* Notify the peers by setting and clearing the global signal bit */
@@ -1339,7 +1335,6 @@ static int idt_ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
 		idt_nt_write(ndev, IDT_NT_LUTLDATA, (u32)addr);
 		idt_nt_write(ndev, IDT_NT_LUTMDATA, (u32)(addr >> 32));
 		idt_nt_write(ndev, IDT_NT_LUTUDATA, data);
-		mmiowb();
 		spin_unlock_irqrestore(&ndev->lut_lock, irqflags);
 		/* Limit address isn't specified since size is fixed for LUT */
 	}
@@ -1393,7 +1388,6 @@ static int idt_ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx,
 		idt_nt_write(ndev, IDT_NT_LUTLDATA, 0);
 		idt_nt_write(ndev, IDT_NT_LUTMDATA, 0);
 		idt_nt_write(ndev, IDT_NT_LUTUDATA, 0);
-		mmiowb();
 		spin_unlock_irqrestore(&ndev->lut_lock, irqflags);
 	}
 
@@ -1812,7 +1806,6 @@ static int idt_ntb_peer_msg_write(struct ntb_dev *ntb, int pidx, int midx,
 	/* Set the route and send the data */
 	idt_sw_write(ndev, partdata_tbl[ndev->part].msgctl[midx], swpmsgctl);
 	idt_nt_write(ndev, ntdata_tbl.msgs[midx].out, msg);
-	mmiowb();
 	/* Unlock the messages routing table */
 	spin_unlock_irqrestore(&ndev->msg_locks[midx], irqflags);
 
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 2a9d6b0d1f19..11a6cd374004 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -284,11 +284,9 @@ static int perf_spad_cmd_send(struct perf_peer *peer, enum perf_cmd cmd,
 		ntb_peer_spad_write(perf->ntb, peer->pidx,
 				    PERF_SPAD_HDATA(perf->gidx),
 				    upper_32_bits(data));
-		mmiowb();
 		ntb_peer_spad_write(perf->ntb, peer->pidx,
 				    PERF_SPAD_CMD(perf->gidx),
 				    cmd);
-		mmiowb();
 		ntb_peer_db_set(perf->ntb, PERF_SPAD_NOTIFY(peer->gidx));
 
 		dev_dbg(&perf->ntb->dev, "DB ring peer %#llx\n",
@@ -379,7 +377,6 @@ static int perf_msg_cmd_send(struct perf_peer *peer, enum perf_cmd cmd,
 
 		ntb_peer_msg_write(perf->ntb, peer->pidx, PERF_MSG_HDATA,
 				   upper_32_bits(data));
-		mmiowb();
 
 		/* This call shall trigger peer message event */
 		ntb_peer_msg_write(perf->ntb, peer->pidx, PERF_MSG_CMD, cmd);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2c43e12b70af..6265d9225ec8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -388,7 +388,7 @@ static void nvme_free_ns_head(struct kref *ref)
 	nvme_mpath_remove_disk(head);
 	ida_simple_remove(&head->subsys->ns_ida, head->instance);
 	list_del_init(&head->entry);
-	cleanup_srcu_struct_quiesced(&head->srcu);
+	cleanup_srcu_struct(&head->srcu);
 	nvme_put_subsystem(head->subsys);
 	kfree(head);
 }
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 6012f3059acd..011c57cae4b0 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -267,6 +267,7 @@ config PCIE_TANGO_SMP8759
 
 config VMD
 	depends on PCI_MSI && X86_64 && SRCU
+	select X86_DEV_DMA_OPS
 	tristate "Intel Volume Management Device Driver"
 	---help---
 	  Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index cf6816b55b5e..999a5509e57e 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -95,10 +95,8 @@ struct vmd_dev {
 	struct irq_domain	*irq_domain;
 	struct pci_bus		*bus;
 
-#ifdef CONFIG_X86_DEV_DMA_OPS
 	struct dma_map_ops	dma_ops;
 	struct dma_domain	dma_domain;
-#endif
 };
 
 static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -293,7 +291,6 @@ static struct msi_domain_info vmd_msi_domain_info = {
 	.chip		= &vmd_msi_controller,
 };
 
-#ifdef CONFIG_X86_DEV_DMA_OPS
 /*
  * VMD replaces the requester ID with its own.  DMA mappings for devices in a
  * VMD domain need to be mapped for the VMD, not the device requiring
@@ -438,10 +435,6 @@ static void vmd_setup_dma_ops(struct vmd_dev *vmd)
 	add_dma_domain(domain);
 }
 #undef ASSIGN_VMD_DMA_OPS
-#else
-static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {}
-static void vmd_setup_dma_ops(struct vmd_dev *vmd) {}
-#endif
 
 static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
 				  unsigned int devfn, int reg, int len)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7c1b362f599a..766f5779db92 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6262,8 +6262,7 @@ static int __init pci_setup(char *str)
 			} else if (!strncmp(str, "pcie_scan_all", 13)) {
 				pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
 			} else if (!strncmp(str, "disable_acs_redir=", 18)) {
-				disable_acs_redir_param =
-					kstrdup(str + 18, GFP_KERNEL);
+				disable_acs_redir_param = str + 18;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);
@@ -6274,3 +6273,19 @@ static int __init pci_setup(char *str)
 	return 0;
 }
 early_param("pci", pci_setup);
+
+/*
+ * 'disable_acs_redir_param' is initialized in pci_setup(), above, to point
+ * to data in the __initdata section which will be freed after the init
+ * sequence is complete. We can't allocate memory in pci_setup() because some
+ * architectures do not have any memory allocation service available during
+ * an early_param() call. So we allocate memory and copy the variable here
+ * before the init section is freed.
+ */
+static int __init pci_realloc_setup_params(void)
+{
+	disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL);
+
+	return 0;
+}
+pure_initcall(pci_realloc_setup_params);
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index 5cbdbca904ac..362eb8cfa53b 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -142,3 +142,11 @@ config PCIE_PTM
 
 	  This is only useful if you have devices that support PTM, but it
 	  is safe to enable even if you don't.
+
+config PCIE_BW
+	bool "PCI Express Bandwidth Change Notification"
+	depends on PCIEPORTBUS
+	help
+	  This enables PCI Express Bandwidth Change Notification.  If
+	  you know link width or rate changes occur only to correct
+	  unreliable links, you may answer Y.
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
index f1d7bc1e5efa..efb9d2e71e9e 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -3,7 +3,6 @@
 # Makefile for PCI Express features and port driver
 
 pcieportdrv-y			:= portdrv_core.o portdrv_pci.o err.o
-pcieportdrv-y			+= bw_notification.o
 
 obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
 
@@ -13,3 +12,4 @@ obj-$(CONFIG_PCIEAER_INJECT)	+= aer_inject.o
 obj-$(CONFIG_PCIE_PME)		+= pme.o
 obj-$(CONFIG_PCIE_DPC)		+= dpc.o
 obj-$(CONFIG_PCIE_PTM)		+= ptm.o
+obj-$(CONFIG_PCIE_BW)		+= bw_notification.o
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 1d50dc58ac40..944827a8c7d3 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -49,7 +49,11 @@ int pcie_dpc_init(void);
 static inline int pcie_dpc_init(void) { return 0; }
 #endif
 
+#ifdef CONFIG_PCIE_BW
 int pcie_bandwidth_notification_init(void);
+#else
+static inline int pcie_bandwidth_notification_init(void) { return 0; }
+#endif
 
 /* Port Type */
 #define PCIE_ANY_PORT			(~0)
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 7d04f9d087a6..1b330129089f 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -55,7 +55,8 @@ static int pcie_message_numbers(struct pci_dev *dev, int mask,
 	 * 7.8.2, 7.10.10, 7.31.2.
 	 */
 
-	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) {
+	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP |
+		    PCIE_PORT_SERVICE_BWNOTIF)) {
 		pcie_capability_read_word(dev, PCI_EXP_FLAGS, &reg16);
 		*pme = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9;
 		nvec = *pme + 1;
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index af9bc178495d..a94e586a58b2 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -52,6 +52,15 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config ARM_SMMU_V3_PMU
+	 tristate "ARM SMMUv3 Performance Monitors Extension"
+	 depends on ARM64 && ACPI && ARM_SMMU_V3
+	   help
+	   Provides support for the ARM SMMUv3 Performance Monitor Counter
+	   Groups (PMCG), which provide monitoring of transactions passing
+	   through the SMMU and allow the resulting information to be filtered
+	   based on the Stream ID of the corresponding master.
+
 config ARM_DSU_PMU
 	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
 	depends on ARM64
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 909f27fd9db3..30489941f3d6 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_ARM_CCN) += arm-ccn.o
 obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
 obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index bfd03e023308..8f8606b9bc9e 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1684,21 +1684,24 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock);
 	mutex_init(&cci_pmu->reserve_mutex);
 	atomic_set(&cci_pmu->active_events, 0);
-	cci_pmu->cpu = get_cpu();
-
-	ret = cci_pmu_init(cci_pmu, pdev);
-	if (ret) {
-		put_cpu();
-		return ret;
-	}
 
+	cci_pmu->cpu = raw_smp_processor_id();
+	g_cci_pmu = cci_pmu;
 	cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
 				  "perf/arm/cci:online", NULL,
 				  cci_pmu_offline_cpu);
-	put_cpu();
-	g_cci_pmu = cci_pmu;
+
+	ret = cci_pmu_init(cci_pmu, pdev);
+	if (ret)
+		goto error_pmu_init;
+
 	pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
 	return 0;
+
+error_pmu_init:
+	cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+	g_cci_pmu = NULL;
+	return ret;
 }
 
 static int cci_pmu_remove(struct platform_device *pdev)
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 2ae76026e947..0bb52d9bdcf7 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -167,7 +167,7 @@ struct arm_ccn_dt {
 
 	struct hrtimer hrtimer;
 
-	cpumask_t cpu;
+	unsigned int cpu;
 	struct hlist_node node;
 
 	struct pmu pmu;
@@ -559,7 +559,7 @@ static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
 {
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &ccn->dt.cpu);
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
 }
 
 static struct device_attribute arm_ccn_pmu_cpumask_attr =
@@ -759,7 +759,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	 * mitigate this, we enforce CPU assignment to one, selected
 	 * processor (the one described in the "cpumask" attribute).
 	 */
-	event->cpu = cpumask_first(&ccn->dt.cpu);
+	event->cpu = ccn->dt.cpu;
 
 	node_xp = CCN_CONFIG_NODE(event->attr.config);
 	type = CCN_CONFIG_TYPE(event->attr.config);
@@ -1215,15 +1215,15 @@ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
 	unsigned int target;
 
-	if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+	if (cpu != dt->cpu)
 		return 0;
 	target = cpumask_any_but(cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 	perf_pmu_migrate_context(&dt->pmu, cpu, target);
-	cpumask_set_cpu(target, &dt->cpu);
+	dt->cpu = target;
 	if (ccn->irq)
-		WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
+		WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
 	return 0;
 }
 
@@ -1299,29 +1299,30 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	}
 
 	/* Pick one CPU which we will use to collect data from CCN... */
-	cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
+	ccn->dt.cpu = raw_smp_processor_id();
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
-		err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
+		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
 		if (err) {
 			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
 			goto error_set_affinity;
 		}
 	}
 
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					 &ccn->dt.node);
+
 	err = perf_pmu_register(&ccn->dt.pmu, name, -1);
 	if (err)
 		goto error_pmu_register;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-					 &ccn->dt.node);
-	put_cpu();
 	return 0;
 
 error_pmu_register:
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					    &ccn->dt.node);
 error_set_affinity:
-	put_cpu();
 error_choose_name:
 	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
 	for (i = 0; i < ccn->num_xps; i++)
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
new file mode 100644
index 000000000000..da71c741cb46
--- /dev/null
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * This driver adds support for perf events to use the Performance
+ * Monitor Counter Groups (PMCG) associated with an SMMUv3 node
+ * to monitor that node.
+ *
+ * SMMUv3 PMCG devices are named as smmuv3_pmcg_<phys_addr_page> where
+ * <phys_addr_page> is the physical page address of the SMMU PMCG wrapped
+ * to 4K boundary. For example, the PMCG at 0xff88840000 is named
+ * smmuv3_pmcg_ff88840
+ *
+ * Filtering by stream id is done by specifying filtering parameters
+ * with the event. options are:
+ *   filter_enable    - 0 = no filtering, 1 = filtering enabled
+ *   filter_span      - 0 = exact match, 1 = pattern match
+ *   filter_stream_id - pattern to filter against
+ *
+ * To match a partial StreamID where the X most-significant bits must match
+ * but the Y least-significant bits might differ, STREAMID is programmed
+ * with a value that contains:
+ *  STREAMID[Y - 1] == 0.
+ *  STREAMID[Y - 2:0] == 1 (where Y > 1).
+ * The remainder of implemented bits of STREAMID (X bits, from bit Y upwards)
+ * contain a value to match from the corresponding bits of event StreamID.
+ *
+ * Example: perf stat -e smmuv3_pmcg_ff88840/transaction,filter_enable=1,
+ *                    filter_span=1,filter_stream_id=0x42/ -a netperf
+ * Applies filter pattern 0x42 to transaction events, which means events
+ * matching stream ids 0x42 and 0x43 are counted. Further filtering
+ * information is available in the SMMU documentation.
+ *
+ * SMMU events are not attributable to a CPU, so task mode and sampling
+ * are not supported.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#define SMMU_PMCG_EVCNTR0               0x0
+#define SMMU_PMCG_EVCNTR(n, stride)     (SMMU_PMCG_EVCNTR0 + (n) * (stride))
+#define SMMU_PMCG_EVTYPER0              0x400
+#define SMMU_PMCG_EVTYPER(n)            (SMMU_PMCG_EVTYPER0 + (n) * 4)
+#define SMMU_PMCG_SID_SPAN_SHIFT        29
+#define SMMU_PMCG_SMR0                  0xA00
+#define SMMU_PMCG_SMR(n)                (SMMU_PMCG_SMR0 + (n) * 4)
+#define SMMU_PMCG_CNTENSET0             0xC00
+#define SMMU_PMCG_CNTENCLR0             0xC20
+#define SMMU_PMCG_INTENSET0             0xC40
+#define SMMU_PMCG_INTENCLR0             0xC60
+#define SMMU_PMCG_OVSCLR0               0xC80
+#define SMMU_PMCG_OVSSET0               0xCC0
+#define SMMU_PMCG_CFGR                  0xE00
+#define SMMU_PMCG_CFGR_SID_FILTER_TYPE  BIT(23)
+#define SMMU_PMCG_CFGR_MSI              BIT(21)
+#define SMMU_PMCG_CFGR_RELOC_CTRS       BIT(20)
+#define SMMU_PMCG_CFGR_SIZE             GENMASK(13, 8)
+#define SMMU_PMCG_CFGR_NCTR             GENMASK(5, 0)
+#define SMMU_PMCG_CR                    0xE04
+#define SMMU_PMCG_CR_ENABLE             BIT(0)
+#define SMMU_PMCG_CEID0                 0xE20
+#define SMMU_PMCG_CEID1                 0xE28
+#define SMMU_PMCG_IRQ_CTRL              0xE50
+#define SMMU_PMCG_IRQ_CTRL_IRQEN        BIT(0)
+#define SMMU_PMCG_IRQ_CFG0              0xE58
+#define SMMU_PMCG_IRQ_CFG1              0xE60
+#define SMMU_PMCG_IRQ_CFG2              0xE64
+
+/* MSI config fields */
+#define MSI_CFG0_ADDR_MASK              GENMASK_ULL(51, 2)
+#define MSI_CFG2_MEMATTR_DEVICE_nGnRE   0x1
+
+#define SMMU_PMCG_DEFAULT_FILTER_SPAN   1
+#define SMMU_PMCG_DEFAULT_FILTER_SID    GENMASK(31, 0)
+
+#define SMMU_PMCG_MAX_COUNTERS          64
+#define SMMU_PMCG_ARCH_MAX_EVENTS       128
+
+#define SMMU_PMCG_PA_SHIFT              12
+
+#define SMMU_PMCG_EVCNTR_RDONLY         BIT(0)
+
+static int cpuhp_state_num;
+
+struct smmu_pmu {
+	struct hlist_node node;
+	struct perf_event *events[SMMU_PMCG_MAX_COUNTERS];
+	DECLARE_BITMAP(used_counters, SMMU_PMCG_MAX_COUNTERS);
+	DECLARE_BITMAP(supported_events, SMMU_PMCG_ARCH_MAX_EVENTS);
+	unsigned int irq;
+	unsigned int on_cpu;
+	struct pmu pmu;
+	unsigned int num_counters;
+	struct device *dev;
+	void __iomem *reg_base;
+	void __iomem *reloc_base;
+	u64 counter_mask;
+	u32 options;
+	bool global_filter;
+	u32 global_filter_span;
+	u32 global_filter_sid;
+};
+
+#define to_smmu_pmu(p) (container_of(p, struct smmu_pmu, pmu))
+
+#define SMMU_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end)        \
+	static inline u32 get_##_name(struct perf_event *event)            \
+	{                                                                  \
+		return FIELD_GET(GENMASK_ULL(_end, _start),                \
+				 event->attr._config);                     \
+	}                                                                  \
+
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 15);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_stream_id, config1, 0, 31);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_span, config1, 32, 32);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_enable, config1, 33, 33);
+
+static inline void smmu_pmu_enable(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+	writel(SMMU_PMCG_IRQ_CTRL_IRQEN,
+	       smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+	writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
+}
+
+static inline void smmu_pmu_disable(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+	writel(0, smmu_pmu->reg_base + SMMU_PMCG_CR);
+	writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+}
+
+static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
+					      u32 idx, u64 value)
+{
+	if (smmu_pmu->counter_mask & BIT(32))
+		writeq(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+	else
+		writel(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+}
+
+static inline u64 smmu_pmu_counter_get_value(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	u64 value;
+
+	if (smmu_pmu->counter_mask & BIT(32))
+		value = readq(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+	else
+		value = readl(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+
+	return value;
+}
+
+static inline void smmu_pmu_counter_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENSET0);
+}
+
+static inline void smmu_pmu_counter_disable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+}
+
+static inline void smmu_pmu_interrupt_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENSET0);
+}
+
+static inline void smmu_pmu_interrupt_disable(struct smmu_pmu *smmu_pmu,
+					      u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+}
+
+static inline void smmu_pmu_set_evtyper(struct smmu_pmu *smmu_pmu, u32 idx,
+					u32 val)
+{
+	writel(val, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
+}
+
+static inline void smmu_pmu_set_smr(struct smmu_pmu *smmu_pmu, u32 idx, u32 val)
+{
+	writel(val, smmu_pmu->reg_base + SMMU_PMCG_SMR(idx));
+}
+
+static void smmu_pmu_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	u64 delta, prev, now;
+	u32 idx = hwc->idx;
+
+	do {
+		prev = local64_read(&hwc->prev_count);
+		now = smmu_pmu_counter_get_value(smmu_pmu, idx);
+	} while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);
+
+	/* handle overflow. */
+	delta = now - prev;
+	delta &= smmu_pmu->counter_mask;
+
+	local64_add(delta, &event->count);
+}
+
+static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu,
+				struct hw_perf_event *hwc)
+{
+	u32 idx = hwc->idx;
+	u64 new;
+
+	if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) {
+		/*
+		 * On platforms that require this quirk, if the counter starts
+		 * at < half_counter value and wraps, the current logic of
+		 * handling the overflow may not work. It is expected that,
+		 * those platforms will have full 64 counter bits implemented
+		 * so that such a possibility is remote(eg: HiSilicon HIP08).
+		 */
+		new = smmu_pmu_counter_get_value(smmu_pmu, idx);
+	} else {
+		/*
+		 * We limit the max period to half the max counter value
+		 * of the counter size, so that even in the case of extreme
+		 * interrupt latency the counter will (hopefully) not wrap
+		 * past its initial value.
+		 */
+		new = smmu_pmu->counter_mask >> 1;
+		smmu_pmu_counter_set_value(smmu_pmu, idx, new);
+	}
+
+	local64_set(&hwc->prev_count, new);
+}
+
+static void smmu_pmu_set_event_filter(struct perf_event *event,
+				      int idx, u32 span, u32 sid)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	u32 evtyper;
+
+	evtyper = get_event(event) | span << SMMU_PMCG_SID_SPAN_SHIFT;
+	smmu_pmu_set_evtyper(smmu_pmu, idx, evtyper);
+	smmu_pmu_set_smr(smmu_pmu, idx, sid);
+}
+
+static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
+				       struct perf_event *event, int idx)
+{
+	u32 span, sid;
+	unsigned int num_ctrs = smmu_pmu->num_counters;
+	bool filter_en = !!get_filter_enable(event);
+
+	span = filter_en ? get_filter_span(event) :
+			   SMMU_PMCG_DEFAULT_FILTER_SPAN;
+	sid = filter_en ? get_filter_stream_id(event) :
+			   SMMU_PMCG_DEFAULT_FILTER_SID;
+
+	/* Support individual filter settings */
+	if (!smmu_pmu->global_filter) {
+		smmu_pmu_set_event_filter(event, idx, span, sid);
+		return 0;
+	}
+
+	/* Requested settings same as current global settings*/
+	if (span == smmu_pmu->global_filter_span &&
+	    sid == smmu_pmu->global_filter_sid)
+		return 0;
+
+	if (!bitmap_empty(smmu_pmu->used_counters, num_ctrs))
+		return -EAGAIN;
+
+	smmu_pmu_set_event_filter(event, 0, span, sid);
+	smmu_pmu->global_filter_span = span;
+	smmu_pmu->global_filter_sid = sid;
+	return 0;
+}
+
+static int smmu_pmu_get_event_idx(struct smmu_pmu *smmu_pmu,
+				  struct perf_event *event)
+{
+	int idx, err;
+	unsigned int num_ctrs = smmu_pmu->num_counters;
+
+	idx = find_first_zero_bit(smmu_pmu->used_counters, num_ctrs);
+	if (idx == num_ctrs)
+		/* The counters are all in use. */
+		return -EAGAIN;
+
+	err = smmu_pmu_apply_event_filter(smmu_pmu, event, idx);
+	if (err)
+		return err;
+
+	set_bit(idx, smmu_pmu->used_counters);
+
+	return idx;
+}
+
+/*
+ * Implementation of abstract pmu functionality required by
+ * the core perf events code.
+ */
+
+static int smmu_pmu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct device *dev = smmu_pmu->dev;
+	struct perf_event *sibling;
+	u16 event_id;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (hwc->sample_period) {
+		dev_dbg(dev, "Sampling not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (event->cpu < 0) {
+		dev_dbg(dev, "Per-task mode not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Verify specified event is supported on this PMU */
+	event_id = get_event(event);
+	if (event_id < SMMU_PMCG_ARCH_MAX_EVENTS &&
+	    (!test_bit(event_id, smmu_pmu->supported_events))) {
+		dev_dbg(dev, "Invalid event %d for this PMU\n", event_id);
+		return -EINVAL;
+	}
+
+	/* Don't allow groups with mixed PMUs, except for s/w events */
+	if (event->group_leader->pmu != event->pmu &&
+	    !is_software_event(event->group_leader)) {
+		dev_dbg(dev, "Can't create mixed PMU group\n");
+		return -EINVAL;
+	}
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu != event->pmu &&
+		    !is_software_event(sibling)) {
+			dev_dbg(dev, "Can't create mixed PMU group\n");
+			return -EINVAL;
+		}
+	}
+
+	hwc->idx = -1;
+
+	/*
+	 * Ensure all events are on the same cpu so all events are in the
+	 * same cpu context, to avoid races on pmu_enable etc.
+	 */
+	event->cpu = smmu_pmu->on_cpu;
+
+	return 0;
+}
+
+static void smmu_pmu_event_start(struct perf_event *event, int flags)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	hwc->state = 0;
+
+	smmu_pmu_set_period(smmu_pmu, hwc);
+
+	smmu_pmu_counter_enable(smmu_pmu, idx);
+}
+
+static void smmu_pmu_event_stop(struct perf_event *event, int flags)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (hwc->state & PERF_HES_STOPPED)
+		return;
+
+	smmu_pmu_counter_disable(smmu_pmu, idx);
+	/* As the counter gets updated on _start, ignore PERF_EF_UPDATE */
+	smmu_pmu_event_update(event);
+	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int smmu_pmu_event_add(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+
+	idx = smmu_pmu_get_event_idx(smmu_pmu, event);
+	if (idx < 0)
+		return idx;
+
+	hwc->idx = idx;
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	smmu_pmu->events[idx] = event;
+	local64_set(&hwc->prev_count, 0);
+
+	smmu_pmu_interrupt_enable(smmu_pmu, idx);
+
+	if (flags & PERF_EF_START)
+		smmu_pmu_event_start(event, flags);
+
+	/* Propagate changes to the userspace mapping. */
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void smmu_pmu_event_del(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	int idx = hwc->idx;
+
+	smmu_pmu_event_stop(event, flags | PERF_EF_UPDATE);
+	smmu_pmu_interrupt_disable(smmu_pmu, idx);
+	smmu_pmu->events[idx] = NULL;
+	clear_bit(idx, smmu_pmu->used_counters);
+
+	perf_event_update_userpage(event);
+}
+
+static void smmu_pmu_event_read(struct perf_event *event)
+{
+	smmu_pmu_event_update(event);
+}
+
+/* cpumask */
+
+static ssize_t smmu_pmu_cpumask_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
+}
+
+static struct device_attribute smmu_pmu_cpumask_attr =
+		__ATTR(cpumask, 0444, smmu_pmu_cpumask_show, NULL);
+
+static struct attribute *smmu_pmu_cpumask_attrs[] = {
+	&smmu_pmu_cpumask_attr.attr,
+	NULL
+};
+
+static struct attribute_group smmu_pmu_cpumask_group = {
+	.attrs = smmu_pmu_cpumask_attrs,
+};
+
+/* Events */
+
+static ssize_t smmu_pmu_event_show(struct device *dev,
+				   struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define SMMU_EVENT_ATTR(name, config) \
+	PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
+		       config, smmu_pmu_event_show)
+SMMU_EVENT_ATTR(cycles, 0);
+SMMU_EVENT_ATTR(transaction, 1);
+SMMU_EVENT_ATTR(tlb_miss, 2);
+SMMU_EVENT_ATTR(config_cache_miss, 3);
+SMMU_EVENT_ATTR(trans_table_walk_access, 4);
+SMMU_EVENT_ATTR(config_struct_access, 5);
+SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
+SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);
+
+static struct attribute *smmu_pmu_events[] = {
+	&smmu_event_attr_cycles.attr.attr,
+	&smmu_event_attr_transaction.attr.attr,
+	&smmu_event_attr_tlb_miss.attr.attr,
+	&smmu_event_attr_config_cache_miss.attr.attr,
+	&smmu_event_attr_trans_table_walk_access.attr.attr,
+	&smmu_event_attr_config_struct_access.attr.attr,
+	&smmu_event_attr_pcie_ats_trans_rq.attr.attr,
+	&smmu_event_attr_pcie_ats_trans_passed.attr.attr,
+	NULL
+};
+
+static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
+					 struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+
+	if (test_bit(pmu_attr->id, smmu_pmu->supported_events))
+		return attr->mode;
+
+	return 0;
+}
+
+static struct attribute_group smmu_pmu_events_group = {
+	.name = "events",
+	.attrs = smmu_pmu_events,
+	.is_visible = smmu_pmu_event_is_visible,
+};
+
+/* Formats */
+PMU_FORMAT_ATTR(event,		   "config:0-15");
+PMU_FORMAT_ATTR(filter_stream_id,  "config1:0-31");
+PMU_FORMAT_ATTR(filter_span,	   "config1:32");
+PMU_FORMAT_ATTR(filter_enable,	   "config1:33");
+
+static struct attribute *smmu_pmu_formats[] = {
+	&format_attr_event.attr,
+	&format_attr_filter_stream_id.attr,
+	&format_attr_filter_span.attr,
+	&format_attr_filter_enable.attr,
+	NULL
+};
+
+static struct attribute_group smmu_pmu_format_group = {
+	.name = "format",
+	.attrs = smmu_pmu_formats,
+};
+
+static const struct attribute_group *smmu_pmu_attr_grps[] = {
+	&smmu_pmu_cpumask_group,
+	&smmu_pmu_events_group,
+	&smmu_pmu_format_group,
+	NULL
+};
+
+/*
+ * Generic device handlers
+ */
+
+static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct smmu_pmu *smmu_pmu;
+	unsigned int target;
+
+	smmu_pmu = hlist_entry_safe(node, struct smmu_pmu, node);
+	if (cpu != smmu_pmu->on_cpu)
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
+	smmu_pmu->on_cpu = target;
+	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+
+	return 0;
+}
+
+static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
+{
+	struct smmu_pmu *smmu_pmu = data;
+	u64 ovsr;
+	unsigned int idx;
+
+	ovsr = readq(smmu_pmu->reloc_base + SMMU_PMCG_OVSSET0);
+	if (!ovsr)
+		return IRQ_NONE;
+
+	writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+
+	for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
+		struct perf_event *event = smmu_pmu->events[idx];
+		struct hw_perf_event *hwc;
+
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		smmu_pmu_event_update(event);
+		hwc = &event->hw;
+
+		smmu_pmu_set_period(smmu_pmu, hwc);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void smmu_pmu_free_msis(void *data)
+{
+	struct device *dev = data;
+
+	platform_msi_domain_free_irqs(dev);
+}
+
+static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	phys_addr_t doorbell;
+	struct device *dev = msi_desc_to_dev(desc);
+	struct smmu_pmu *pmu = dev_get_drvdata(dev);
+
+	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+	doorbell &= MSI_CFG0_ADDR_MASK;
+
+	writeq_relaxed(doorbell, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+	writel_relaxed(msg->data, pmu->reg_base + SMMU_PMCG_IRQ_CFG1);
+	writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE,
+		       pmu->reg_base + SMMU_PMCG_IRQ_CFG2);
+}
+
+static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
+{
+	struct msi_desc *desc;
+	struct device *dev = pmu->dev;
+	int ret;
+
+	/* Clear MSI address reg */
+	writeq_relaxed(0, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+
+	/* MSI supported or not */
+	if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
+		return;
+
+	ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
+	if (ret) {
+		dev_warn(dev, "failed to allocate MSIs\n");
+		return;
+	}
+
+	desc = first_msi_entry(dev);
+	if (desc)
+		pmu->irq = desc->irq;
+
+	/* Add callback to free MSIs on teardown */
+	devm_add_action(dev, smmu_pmu_free_msis, dev);
+}
+
+static int smmu_pmu_setup_irq(struct smmu_pmu *pmu)
+{
+	unsigned long flags = IRQF_NOBALANCING | IRQF_SHARED | IRQF_NO_THREAD;
+	int irq, ret = -ENXIO;
+
+	smmu_pmu_setup_msi(pmu);
+
+	irq = pmu->irq;
+	if (irq)
+		ret = devm_request_irq(pmu->dev, irq, smmu_pmu_handle_irq,
+				       flags, "smmuv3-pmu", pmu);
+	return ret;
+}
+
+static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu)
+{
+	u64 counter_present_mask = GENMASK_ULL(smmu_pmu->num_counters - 1, 0);
+
+	smmu_pmu_disable(&smmu_pmu->pmu);
+
+	/* Disable counter and interrupt */
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+}
+
+static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
+{
+	u32 model;
+
+	model = *(u32 *)dev_get_platdata(smmu_pmu->dev);
+
+	switch (model) {
+	case IORT_SMMU_V3_PMCG_HISI_HIP08:
+		/* HiSilicon Erratum 162001800 */
+		smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY;
+		break;
+	}
+
+	dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options);
+}
+
+static int smmu_pmu_probe(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu;
+	struct resource *res_0, *res_1;
+	u32 cfgr, reg_size;
+	u64 ceid_64[2];
+	int irq, err;
+	char *name;
+	struct device *dev = &pdev->dev;
+
+	smmu_pmu = devm_kzalloc(dev, sizeof(*smmu_pmu), GFP_KERNEL);
+	if (!smmu_pmu)
+		return -ENOMEM;
+
+	smmu_pmu->dev = dev;
+	platform_set_drvdata(pdev, smmu_pmu);
+
+	smmu_pmu->pmu = (struct pmu) {
+		.task_ctx_nr    = perf_invalid_context,
+		.pmu_enable	= smmu_pmu_enable,
+		.pmu_disable	= smmu_pmu_disable,
+		.event_init	= smmu_pmu_event_init,
+		.add		= smmu_pmu_event_add,
+		.del		= smmu_pmu_event_del,
+		.start		= smmu_pmu_event_start,
+		.stop		= smmu_pmu_event_stop,
+		.read		= smmu_pmu_event_read,
+		.attr_groups	= smmu_pmu_attr_grps,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	};
+
+	res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0);
+	if (IS_ERR(smmu_pmu->reg_base))
+		return PTR_ERR(smmu_pmu->reg_base);
+
+	cfgr = readl_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CFGR);
+
+	/* Determine if page 1 is present */
+	if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
+		res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1);
+		if (IS_ERR(smmu_pmu->reloc_base))
+			return PTR_ERR(smmu_pmu->reloc_base);
+	} else {
+		smmu_pmu->reloc_base = smmu_pmu->reg_base;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq > 0)
+		smmu_pmu->irq = irq;
+
+	ceid_64[0] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID0);
+	ceid_64[1] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID1);
+	bitmap_from_arr32(smmu_pmu->supported_events, (u32 *)ceid_64,
+			  SMMU_PMCG_ARCH_MAX_EVENTS);
+
+	smmu_pmu->num_counters = FIELD_GET(SMMU_PMCG_CFGR_NCTR, cfgr) + 1;
+
+	smmu_pmu->global_filter = !!(cfgr & SMMU_PMCG_CFGR_SID_FILTER_TYPE);
+
+	reg_size = FIELD_GET(SMMU_PMCG_CFGR_SIZE, cfgr);
+	smmu_pmu->counter_mask = GENMASK_ULL(reg_size, 0);
+
+	smmu_pmu_reset(smmu_pmu);
+
+	err = smmu_pmu_setup_irq(smmu_pmu);
+	if (err) {
+		dev_err(dev, "Setup irq failed, PMU @%pa\n", &res_0->start);
+		return err;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "smmuv3_pmcg_%llx",
+			      (res_0->start) >> SMMU_PMCG_PA_SHIFT);
+	if (!name) {
+		dev_err(dev, "Create name failed, PMU @%pa\n", &res_0->start);
+		return -EINVAL;
+	}
+
+	smmu_pmu_get_acpi_options(smmu_pmu);
+
+	/* Pick one CPU to be the preferred one to use */
+	smmu_pmu->on_cpu = raw_smp_processor_id();
+	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
+				      cpumask_of(smmu_pmu->on_cpu)));
+
+	err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
+					       &smmu_pmu->node);
+	if (err) {
+		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
+			err, &res_0->start);
+		goto out_cpuhp_err;
+	}
+
+	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
+	if (err) {
+		dev_err(dev, "Error %d registering PMU @%pa\n",
+			err, &res_0->start);
+		goto out_unregister;
+	}
+
+	dev_info(dev, "Registered PMU @ %pa using %d counters with %s filter settings\n",
+		 &res_0->start, smmu_pmu->num_counters,
+		 smmu_pmu->global_filter ? "Global(Counter0)" :
+		 "Individual");
+
+	return 0;
+
+out_unregister:
+	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+out_cpuhp_err:
+	put_cpu();
+	return err;
+}
+
+static int smmu_pmu_remove(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&smmu_pmu->pmu);
+	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+
+	return 0;
+}
+
+static void smmu_pmu_shutdown(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+	smmu_pmu_disable(&smmu_pmu->pmu);
+}
+
+static struct platform_driver smmu_pmu_driver = {
+	.driver = {
+		.name = "arm-smmu-v3-pmcg",
+	},
+	.probe = smmu_pmu_probe,
+	.remove = smmu_pmu_remove,
+	.shutdown = smmu_pmu_shutdown,
+};
+
+static int __init arm_smmu_pmu_init(void)
+{
+	cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+						  "perf/arm/pmcg:online",
+						  NULL,
+						  smmu_pmu_offline_cpu);
+	if (cpuhp_state_num < 0)
+		return cpuhp_state_num;
+
+	return platform_driver_register(&smmu_pmu_driver);
+}
+module_init(arm_smmu_pmu_init);
+
+static void __exit arm_smmu_pmu_exit(void)
+{
+	platform_driver_unregister(&smmu_pmu_driver);
+	cpuhp_remove_multi_state(cpuhp_state_num);
+}
+
+module_exit(arm_smmu_pmu_exit);
+
+MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
+MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
+MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/cpcap-battery.c b/drivers/power/supply/cpcap-battery.c
index 08d5037fd052..6887870ba32c 100644
--- a/drivers/power/supply/cpcap-battery.c
+++ b/drivers/power/supply/cpcap-battery.c
@@ -221,6 +221,9 @@ static int cpcap_battery_cc_raw_div(struct cpcap_battery_ddata *ddata,
 	int avg_current;
 	u32 cc_lsb;
 
+	if (!divider)
+		return 0;
+
 	sample &= 0xffffff;		/* 24-bits, unsigned */
 	offset &= 0x7ff;		/* 10-bits, signed */
 
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index dce24f596160..5358a80d854f 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -383,15 +383,11 @@ int power_supply_uevent(struct device *dev, struct kobj_uevent_env *env)
 	char *prop_buf;
 	char *attrname;
 
-	dev_dbg(dev, "uevent\n");
-
 	if (!psy || !psy->desc) {
 		dev_dbg(dev, "No power supply yet\n");
 		return ret;
 	}
 
-	dev_dbg(dev, "POWER_SUPPLY_NAME=%s\n", psy->desc->name);
-
 	ret = add_uevent_var(env, "POWER_SUPPLY_NAME=%s", psy->desc->name);
 	if (ret)
 		return ret;
@@ -427,8 +423,6 @@ int power_supply_uevent(struct device *dev, struct kobj_uevent_env *env)
 			goto out;
 		}
 
-		dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf);
-
 		ret = add_uevent_var(env, "POWER_SUPPLY_%s=%s", attrname, prop_buf);
 		kfree(attrname);
 		if (ret)
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index e9aa71cdfc44..d2ab3f07c008 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -45,8 +45,8 @@ static struct list_head sclp_req_queue;
 /* Data for read and and init requests. */
 static struct sclp_req sclp_read_req;
 static struct sclp_req sclp_init_req;
-static char sclp_read_sccb[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
-static char sclp_init_sccb[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+static void *sclp_read_sccb;
+static struct init_sccb *sclp_init_sccb;
 
 /* Suspend request */
 static DECLARE_COMPLETION(sclp_request_queue_flushed);
@@ -753,9 +753,8 @@ EXPORT_SYMBOL(sclp_remove_processed);
 static inline void
 __sclp_make_init_req(sccb_mask_t receive_mask, sccb_mask_t send_mask)
 {
-	struct init_sccb *sccb;
+	struct init_sccb *sccb = sclp_init_sccb;
 
-	sccb = (struct init_sccb *) sclp_init_sccb;
 	clear_page(sccb);
 	memset(&sclp_init_req, 0, sizeof(struct sclp_req));
 	sclp_init_req.command = SCLP_CMDW_WRITE_EVENT_MASK;
@@ -782,7 +781,7 @@ static int
 sclp_init_mask(int calculate)
 {
 	unsigned long flags;
-	struct init_sccb *sccb = (struct init_sccb *) sclp_init_sccb;
+	struct init_sccb *sccb = sclp_init_sccb;
 	sccb_mask_t receive_mask;
 	sccb_mask_t send_mask;
 	int retry;
@@ -1175,6 +1174,9 @@ sclp_init(void)
 	if (sclp_init_state != sclp_init_state_uninitialized)
 		goto fail_unlock;
 	sclp_init_state = sclp_init_state_initializing;
+	sclp_read_sccb = (void *) __get_free_page(GFP_ATOMIC | GFP_DMA);
+	sclp_init_sccb = (void *) __get_free_page(GFP_ATOMIC | GFP_DMA);
+	BUG_ON(!sclp_read_sccb || !sclp_init_sccb);
 	/* Set up variables */
 	INIT_LIST_HEAD(&sclp_req_queue);
 	INIT_LIST_HEAD(&sclp_reg_list);
@@ -1207,6 +1209,8 @@ fail_unregister_reboot_notifier:
 	unregister_reboot_notifier(&sclp_reboot_notifier);
 fail_init_state_uninitialized:
 	sclp_init_state = sclp_init_state_uninitialized;
+	free_page((unsigned long) sclp_read_sccb);
+	free_page((unsigned long) sclp_init_sccb);
 fail_unlock:
 	spin_unlock_irqrestore(&sclp_lock, flags);
 	return rc;
diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h
index 367e9d384d85..196333013e54 100644
--- a/drivers/s390/char/sclp.h
+++ b/drivers/s390/char/sclp.h
@@ -197,7 +197,9 @@ struct read_info_sccb {
 	u32	hmfai;			/* 124-127 */
 	u8	_pad_128[134 - 128];	/* 128-133 */
 	u8	byte_134;			/* 134 */
-	u8	_pad_135[4096 - 135];	/* 135-4095 */
+	u8	cpudirq;		/* 135 */
+	u16	cbl;			/* 136-137 */
+	u8	_pad_138[4096 - 138];	/* 138-4095 */
 } __packed __aligned(PAGE_SIZE);
 
 struct read_storage_sccb {
@@ -319,7 +321,7 @@ extern int sclp_console_drop;
 extern unsigned long sclp_console_full;
 extern bool sclp_mask_compat_mode;
 
-extern char sclp_early_sccb[PAGE_SIZE];
+extern char *sclp_early_sccb;
 
 void sclp_early_wait_irq(void);
 int sclp_early_cmd(sclp_cmdw_t cmd, void *sccb);
@@ -365,14 +367,14 @@ sclp_ascebc(unsigned char ch)
 
 /* translate string from EBCDIC to ASCII */
 static inline void
-sclp_ebcasc_str(unsigned char *str, int nr)
+sclp_ebcasc_str(char *str, int nr)
 {
 	(MACHINE_IS_VM) ? EBCASC(str, nr) : EBCASC_500(str, nr);
 }
 
 /* translate string from ASCII to EBCDIC */
 static inline void
-sclp_ascebc_str(unsigned char *str, int nr)
+sclp_ascebc_str(char *str, int nr)
 {
 	(MACHINE_IS_VM) ? ASCEBC(str, nr) : ASCEBC_500(str, nr);
 }
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 8332788681c4..6c90aa725f23 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -40,6 +40,8 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
 	sclp.has_gisaf = !!(sccb->fac118 & 0x08);
 	sclp.has_hvs = !!(sccb->fac119 & 0x80);
 	sclp.has_kss = !!(sccb->fac98 & 0x01);
+	sclp.has_sipl = !!(sccb->cbl & 0x02);
+	sclp.has_sipl_g2 = !!(sccb->cbl & 0x04);
 	if (sccb->fac85 & 0x02)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
 	if (sccb->fac91 & 0x40)
@@ -93,6 +95,7 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
 	sclp.mtid_prev = (sccb->fac42 & 0x80) ? (sccb->fac66 & 31) : 0;
 
 	sclp.hmfai = sccb->hmfai;
+	sclp.has_dirq = !!(sccb->cpudirq & 0x80);
 }
 
 /*
@@ -144,7 +147,7 @@ static void __init sclp_early_console_detect(struct init_sccb *sccb)
 
 void __init sclp_early_detect(void)
 {
-	void *sccb = &sclp_early_sccb;
+	void *sccb = sclp_early_sccb;
 
 	sclp_early_facilities_detect(sccb);
 	sclp_early_init_core_info(sccb);
diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c
index 387c114ded3f..7737470f8498 100644
--- a/drivers/s390/char/sclp_early_core.c
+++ b/drivers/s390/char/sclp_early_core.c
@@ -16,7 +16,7 @@
 
 static struct read_info_sccb __bootdata(sclp_info_sccb);
 static int __bootdata(sclp_info_sccb_valid);
-char sclp_early_sccb[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
+char *sclp_early_sccb = (char *) EARLY_SCCB_OFFSET;
 int sclp_init_state __section(.data) = sclp_init_state_uninitialized;
 /*
  * Used to keep track of the size of the event masks. Qemu until version 2.11
@@ -91,8 +91,8 @@ static void sclp_early_print_lm(const char *str, unsigned int len)
 	struct mto *mto;
 	struct go *go;
 
-	sccb = (struct write_sccb *) &sclp_early_sccb;
-	end = (unsigned char *) sccb + sizeof(sclp_early_sccb) - 1;
+	sccb = (struct write_sccb *) sclp_early_sccb;
+	end = (unsigned char *) sccb + EARLY_SCCB_SIZE - 1;
 	memset(sccb, 0, sizeof(*sccb));
 	ptr = (unsigned char *) &sccb->msg.mdb.mto;
 	offset = 0;
@@ -139,9 +139,9 @@ static void sclp_early_print_vt220(const char *str, unsigned int len)
 {
 	struct vt220_sccb *sccb;
 
-	sccb = (struct vt220_sccb *) &sclp_early_sccb;
-	if (sizeof(*sccb) + len >= sizeof(sclp_early_sccb))
-		len = sizeof(sclp_early_sccb) - sizeof(*sccb);
+	sccb = (struct vt220_sccb *) sclp_early_sccb;
+	if (sizeof(*sccb) + len >= EARLY_SCCB_SIZE)
+		len = EARLY_SCCB_SIZE - sizeof(*sccb);
 	memset(sccb, 0, sizeof(*sccb));
 	memcpy(&sccb->msg.data, str, len);
 	sccb->header.length = sizeof(*sccb) + len;
@@ -199,7 +199,7 @@ static int sclp_early_setup(int disable, int *have_linemode, int *have_vt220)
 	BUILD_BUG_ON(sizeof(struct init_sccb) > PAGE_SIZE);
 
 	*have_linemode = *have_vt220 = 0;
-	sccb = (struct init_sccb *) &sclp_early_sccb;
+	sccb = (struct init_sccb *) sclp_early_sccb;
 	receive_mask = disable ? 0 : EVTYP_OPCMD_MASK;
 	send_mask = disable ? 0 : EVTYP_VT220MSG_MASK | EVTYP_MSG_MASK;
 	rc = sclp_early_set_event_mask(sccb, receive_mask, send_mask);
@@ -304,7 +304,7 @@ int __init sclp_early_get_hsa_size(unsigned long *hsa_size)
 void __weak __init add_mem_detect_block(u64 start, u64 end) {}
 int __init sclp_early_read_storage_info(void)
 {
-	struct read_storage_sccb *sccb = (struct read_storage_sccb *)&sclp_early_sccb;
+	struct read_storage_sccb *sccb = (struct read_storage_sccb *)sclp_early_sccb;
 	int rc, id, max_id = 0;
 	unsigned long rn, rzm;
 	sclp_cmdw_t command;
@@ -320,8 +320,8 @@ int __init sclp_early_read_storage_info(void)
 	rzm <<= 20;
 
 	for (id = 0; id <= max_id; id++) {
-		memset(sclp_early_sccb, 0, sizeof(sclp_early_sccb));
-		sccb->header.length = sizeof(sclp_early_sccb);
+		memset(sclp_early_sccb, 0, EARLY_SCCB_SIZE);
+		sccb->header.length = EARLY_SCCB_SIZE;
 		command = SCLP_CMDW_READ_STORAGE_INFO | (id << 8);
 		rc = sclp_early_cmd(command, sccb);
 		if (rc)
diff --git a/drivers/s390/char/sclp_sdias.c b/drivers/s390/char/sclp_sdias.c
index 8e0b69a2f11a..13f97fd73aca 100644
--- a/drivers/s390/char/sclp_sdias.c
+++ b/drivers/s390/char/sclp_sdias.c
@@ -29,7 +29,7 @@ static struct sclp_register sclp_sdias_register = {
 	.send_mask = EVTYP_SDIAS_MASK,
 };
 
-static struct sdias_sccb sccb __attribute__((aligned(4096)));
+static struct sdias_sccb *sclp_sdias_sccb;
 static struct sdias_evbuf sdias_evbuf;
 
 static DECLARE_COMPLETION(evbuf_accepted);
@@ -58,6 +58,7 @@ static void sdias_callback(struct sclp_req *request, void *data)
 
 static int sdias_sclp_send(struct sclp_req *req)
 {
+	struct sdias_sccb *sccb = sclp_sdias_sccb;
 	int retries;
 	int rc;
 
@@ -78,16 +79,16 @@ static int sdias_sclp_send(struct sclp_req *req)
 			continue;
 		}
 		/* if not accepted, retry */
-		if (!(sccb.evbuf.hdr.flags & 0x80)) {
+		if (!(sccb->evbuf.hdr.flags & 0x80)) {
 			TRACE("sclp request failed: flags=%x\n",
-			      sccb.evbuf.hdr.flags);
+			      sccb->evbuf.hdr.flags);
 			continue;
 		}
 		/*
 		 * for the sync interface the response is in the initial sccb
 		 */
 		if (!sclp_sdias_register.receiver_fn) {
-			memcpy(&sdias_evbuf, &sccb.evbuf, sizeof(sdias_evbuf));
+			memcpy(&sdias_evbuf, &sccb->evbuf, sizeof(sdias_evbuf));
 			TRACE("sync request done\n");
 			return 0;
 		}
@@ -104,23 +105,24 @@ static int sdias_sclp_send(struct sclp_req *req)
  */
 int sclp_sdias_blk_count(void)
 {
+	struct sdias_sccb *sccb = sclp_sdias_sccb;
 	struct sclp_req request;
 	int rc;
 
 	mutex_lock(&sdias_mutex);
 
-	memset(&sccb, 0, sizeof(sccb));
+	memset(sccb, 0, sizeof(*sccb));
 	memset(&request, 0, sizeof(request));
 
-	sccb.hdr.length = sizeof(sccb);
-	sccb.evbuf.hdr.length = sizeof(struct sdias_evbuf);
-	sccb.evbuf.hdr.type = EVTYP_SDIAS;
-	sccb.evbuf.event_qual = SDIAS_EQ_SIZE;
-	sccb.evbuf.data_id = SDIAS_DI_FCP_DUMP;
-	sccb.evbuf.event_id = 4712;
-	sccb.evbuf.dbs = 1;
+	sccb->hdr.length = sizeof(*sccb);
+	sccb->evbuf.hdr.length = sizeof(struct sdias_evbuf);
+	sccb->evbuf.hdr.type = EVTYP_SDIAS;
+	sccb->evbuf.event_qual = SDIAS_EQ_SIZE;
+	sccb->evbuf.data_id = SDIAS_DI_FCP_DUMP;
+	sccb->evbuf.event_id = 4712;
+	sccb->evbuf.dbs = 1;
 
-	request.sccb = &sccb;
+	request.sccb = sccb;
 	request.command = SCLP_CMDW_WRITE_EVENT_DATA;
 	request.status = SCLP_REQ_FILLED;
 	request.callback = sdias_callback;
@@ -130,8 +132,8 @@ int sclp_sdias_blk_count(void)
 		pr_err("sclp_send failed for get_nr_blocks\n");
 		goto out;
 	}
-	if (sccb.hdr.response_code != 0x0020) {
-		TRACE("send failed: %x\n", sccb.hdr.response_code);
+	if (sccb->hdr.response_code != 0x0020) {
+		TRACE("send failed: %x\n", sccb->hdr.response_code);
 		rc = -EIO;
 		goto out;
 	}
@@ -163,30 +165,31 @@ out:
  */
 int sclp_sdias_copy(void *dest, int start_blk, int nr_blks)
 {
+	struct sdias_sccb *sccb = sclp_sdias_sccb;
 	struct sclp_req request;
 	int rc;
 
 	mutex_lock(&sdias_mutex);
 
-	memset(&sccb, 0, sizeof(sccb));
+	memset(sccb, 0, sizeof(*sccb));
 	memset(&request, 0, sizeof(request));
 
-	sccb.hdr.length = sizeof(sccb);
-	sccb.evbuf.hdr.length = sizeof(struct sdias_evbuf);
-	sccb.evbuf.hdr.type = EVTYP_SDIAS;
-	sccb.evbuf.hdr.flags = 0;
-	sccb.evbuf.event_qual = SDIAS_EQ_STORE_DATA;
-	sccb.evbuf.data_id = SDIAS_DI_FCP_DUMP;
-	sccb.evbuf.event_id = 4712;
-	sccb.evbuf.asa_size = SDIAS_ASA_SIZE_64;
-	sccb.evbuf.event_status = 0;
-	sccb.evbuf.blk_cnt = nr_blks;
-	sccb.evbuf.asa = (unsigned long)dest;
-	sccb.evbuf.fbn = start_blk;
-	sccb.evbuf.lbn = 0;
-	sccb.evbuf.dbs = 1;
-
-	request.sccb	 = &sccb;
+	sccb->hdr.length = sizeof(*sccb);
+	sccb->evbuf.hdr.length = sizeof(struct sdias_evbuf);
+	sccb->evbuf.hdr.type = EVTYP_SDIAS;
+	sccb->evbuf.hdr.flags = 0;
+	sccb->evbuf.event_qual = SDIAS_EQ_STORE_DATA;
+	sccb->evbuf.data_id = SDIAS_DI_FCP_DUMP;
+	sccb->evbuf.event_id = 4712;
+	sccb->evbuf.asa_size = SDIAS_ASA_SIZE_64;
+	sccb->evbuf.event_status = 0;
+	sccb->evbuf.blk_cnt = nr_blks;
+	sccb->evbuf.asa = (unsigned long)dest;
+	sccb->evbuf.fbn = start_blk;
+	sccb->evbuf.lbn = 0;
+	sccb->evbuf.dbs = 1;
+
+	request.sccb	 = sccb;
 	request.command  = SCLP_CMDW_WRITE_EVENT_DATA;
 	request.status	 = SCLP_REQ_FILLED;
 	request.callback = sdias_callback;
@@ -196,8 +199,8 @@ int sclp_sdias_copy(void *dest, int start_blk, int nr_blks)
 		pr_err("sclp_send failed: %x\n", rc);
 		goto out;
 	}
-	if (sccb.hdr.response_code != 0x0020) {
-		TRACE("copy failed: %x\n", sccb.hdr.response_code);
+	if (sccb->hdr.response_code != 0x0020) {
+		TRACE("copy failed: %x\n", sccb->hdr.response_code);
 		rc = -EIO;
 		goto out;
 	}
@@ -256,6 +259,8 @@ int __init sclp_sdias_init(void)
 {
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
 		return 0;
+	sclp_sdias_sccb = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
+	BUG_ON(!sclp_sdias_sccb);
 	sdias_dbf = debug_register("dump_sdias", 4, 1, 4 * sizeof(long));
 	debug_register_view(sdias_dbf, &debug_sprintf_view);
 	debug_set_level(sdias_dbf, 6);
@@ -264,6 +269,7 @@ int __init sclp_sdias_init(void)
 	if (sclp_sdias_init_async() == 0)
 		goto out;
 	TRACE("init failed\n");
+	free_page((unsigned long) sclp_sdias_sccb);
 	return -ENODEV;
 out:
 	TRACE("init done\n");
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 76d3c50bf078..f75d3bfb5af3 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -51,7 +51,7 @@ static struct dentry *zcore_dir;
 static struct dentry *zcore_memmap_file;
 static struct dentry *zcore_reipl_file;
 static struct dentry *zcore_hsa_file;
-static struct ipl_parameter_block *ipl_block;
+static struct ipl_parameter_block *zcore_ipl_block;
 
 static char hsa_buf[PAGE_SIZE] __aligned(PAGE_SIZE);
 
@@ -182,8 +182,8 @@ static const struct file_operations zcore_memmap_fops = {
 static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf,
 				 size_t count, loff_t *ppos)
 {
-	if (ipl_block) {
-		diag308(DIAG308_SET, ipl_block);
+	if (zcore_ipl_block) {
+		diag308(DIAG308_SET, zcore_ipl_block);
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 	}
 	return count;
@@ -265,18 +265,20 @@ static int __init zcore_reipl_init(void)
 		return rc;
 	if (ipib_info.ipib == 0)
 		return 0;
-	ipl_block = (void *) __get_free_page(GFP_KERNEL);
-	if (!ipl_block)
+	zcore_ipl_block = (void *) __get_free_page(GFP_KERNEL);
+	if (!zcore_ipl_block)
 		return -ENOMEM;
 	if (ipib_info.ipib < sclp.hsa_size)
-		rc = memcpy_hsa_kernel(ipl_block, ipib_info.ipib, PAGE_SIZE);
+		rc = memcpy_hsa_kernel(zcore_ipl_block, ipib_info.ipib,
+				       PAGE_SIZE);
 	else
-		rc = memcpy_real(ipl_block, (void *) ipib_info.ipib, PAGE_SIZE);
-	if (rc || (__force u32)csum_partial(ipl_block, ipl_block->hdr.len, 0) !=
+		rc = memcpy_real(zcore_ipl_block, (void *) ipib_info.ipib,
+				 PAGE_SIZE);
+	if (rc || (__force u32)csum_partial(zcore_ipl_block, zcore_ipl_block->hdr.len, 0) !=
 	    ipib_info.checksum) {
 		TRACE("Checksum does not match\n");
-		free_page((unsigned long) ipl_block);
-		ipl_block = NULL;
+		free_page((unsigned long) zcore_ipl_block);
+		zcore_ipl_block = NULL;
 	}
 	return 0;
 }
diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile
index f230516abb96..f6a8db04177c 100644
--- a/drivers/s390/cio/Makefile
+++ b/drivers/s390/cio/Makefile
@@ -20,5 +20,6 @@ obj-$(CONFIG_CCWGROUP) += ccwgroup.o
 qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o
 obj-$(CONFIG_QDIO) += qdio.o
 
-vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o
+vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \
+	vfio_ccw_async.o
 obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index a45011e4529e..4534afc63591 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -27,6 +27,8 @@
 static DEFINE_SPINLOCK(airq_lists_lock);
 static struct hlist_head airq_lists[MAX_ISC+1];
 
+static struct kmem_cache *airq_iv_cache;
+
 /**
  * register_adapter_interrupt() - register adapter interrupt handler
  * @airq: pointer to adapter interrupt descriptor
@@ -95,7 +97,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy)
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(airq, head, list)
 		if ((*airq->lsi_ptr & airq->lsi_mask) != 0)
-			airq->handler(airq);
+			airq->handler(airq, !tpi_info->directed_irq);
 	rcu_read_unlock();
 
 	return IRQ_HANDLED;
@@ -129,10 +131,21 @@ struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags)
 	if (!iv)
 		goto out;
 	iv->bits = bits;
+	iv->flags = flags;
 	size = BITS_TO_LONGS(bits) * sizeof(unsigned long);
-	iv->vector = kzalloc(size, GFP_KERNEL);
-	if (!iv->vector)
-		goto out_free;
+
+	if (flags & AIRQ_IV_CACHELINE) {
+		if ((cache_line_size() * BITS_PER_BYTE) < bits)
+			goto out_free;
+
+		iv->vector = kmem_cache_zalloc(airq_iv_cache, GFP_KERNEL);
+		if (!iv->vector)
+			goto out_free;
+	} else {
+		iv->vector = kzalloc(size, GFP_KERNEL);
+		if (!iv->vector)
+			goto out_free;
+	}
 	if (flags & AIRQ_IV_ALLOC) {
 		iv->avail = kmalloc(size, GFP_KERNEL);
 		if (!iv->avail)
@@ -165,7 +178,10 @@ out_free:
 	kfree(iv->ptr);
 	kfree(iv->bitlock);
 	kfree(iv->avail);
-	kfree(iv->vector);
+	if (iv->flags & AIRQ_IV_CACHELINE)
+		kmem_cache_free(airq_iv_cache, iv->vector);
+	else
+		kfree(iv->vector);
 	kfree(iv);
 out:
 	return NULL;
@@ -181,7 +197,10 @@ void airq_iv_release(struct airq_iv *iv)
 	kfree(iv->data);
 	kfree(iv->ptr);
 	kfree(iv->bitlock);
-	kfree(iv->vector);
+	if (iv->flags & AIRQ_IV_CACHELINE)
+		kmem_cache_free(airq_iv_cache, iv->vector);
+	else
+		kfree(iv->vector);
 	kfree(iv->avail);
 	kfree(iv);
 }
@@ -275,3 +294,13 @@ unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
 	return bit;
 }
 EXPORT_SYMBOL(airq_iv_scan);
+
+static int __init airq_init(void)
+{
+	airq_iv_cache = kmem_cache_create("airq_iv_cache", cache_line_size(),
+					  cache_line_size(), 0, NULL);
+	if (!airq_iv_cache)
+		return -ENOMEM;
+	return 0;
+}
+subsys_initcall(airq_init);
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index de744ca158fd..18f5458f90e8 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -564,7 +564,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 }
 
 static struct irqaction io_interrupt = {
-	.name	 = "IO",
+	.name	 = "I/O",
 	.handler = do_cio_interrupt,
 };
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 9811fd8a0c73..06a91743335a 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -51,7 +51,7 @@ struct tpi_info {
 	struct subchannel_id schid;
 	u32 intparm;
 	u32 adapter_IO:1;
-	u32 :1;
+	u32 directed_irq:1;
 	u32 isc:3;
 	u32 :27;
 	u32 type:3;
@@ -115,7 +115,7 @@ struct subchannel {
 	struct schib_config config;
 } __attribute__ ((aligned(8)));
 
-DECLARE_PER_CPU(struct irb, cio_irb);
+DECLARE_PER_CPU_ALIGNED(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
diff --git a/drivers/s390/cio/ioasm.c b/drivers/s390/cio/ioasm.c
index 14d328338ce2..08eb10283b18 100644
--- a/drivers/s390/cio/ioasm.c
+++ b/drivers/s390/cio/ioasm.c
@@ -233,6 +233,7 @@ int hsch(struct subchannel_id schid)
 
 	return ccode;
 }
+EXPORT_SYMBOL(hsch);
 
 static inline int __xsch(struct subchannel_id schid)
 {
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index a6f7c2986b94..a06944399865 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -228,9 +228,6 @@ struct qdio_q {
 	 */
 	int first_to_check;
 
-	/* first_to_check of the last time */
-	int last_move;
-
 	/* beginning position for calling the program */
 	int first_to_kick;
 
@@ -341,8 +338,7 @@ static inline int multicast_outbound(struct qdio_q *q)
 	       (q->nr == q->irq_ptr->nr_output_qs - 1);
 }
 
-#define pci_out_supported(q) \
-	(q->irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED)
+#define pci_out_supported(irq) ((irq)->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED)
 #define is_qebsm(q)			(q->irq_ptr->sch_token != 0)
 
 #define need_siga_in(q)			(q->irq_ptr->siga_flag.input)
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index d2f98e5829d4..35410e6eda2e 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -121,15 +121,14 @@ static int qstat_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "Timestamp: %Lx  Last AI: %Lx\n",
 		   q->timestamp, last_ai_time);
-	seq_printf(m, "nr_used: %d  ftc: %d  last_move: %d\n",
-		   atomic_read(&q->nr_buf_used),
-		   q->first_to_check, q->last_move);
+	seq_printf(m, "nr_used: %d  ftc: %d\n",
+		   atomic_read(&q->nr_buf_used), q->first_to_check);
 	if (q->is_input_q) {
 		seq_printf(m, "polling: %d  ack start: %d  ack count: %d\n",
 			   q->u.in.polling, q->u.in.ack_start,
 			   q->u.in.ack_count);
-		seq_printf(m, "DSCI: %d   IRQs disabled: %u\n",
-			   *(u32 *)q->irq_ptr->dsci,
+		seq_printf(m, "DSCI: %x   IRQs disabled: %u\n",
+			   *(u8 *)q->irq_ptr->dsci,
 			   test_bit(QDIO_QUEUE_IRQS_DISABLED,
 			   &q->u.in.queue_irq_state));
 	}
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 9537e656e927..cfce255521ac 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -371,7 +371,7 @@ static inline int qdio_siga_input(struct qdio_q *q)
 static inline void qdio_sync_queues(struct qdio_q *q)
 {
 	/* PCI capable outbound queues will also be scanned so sync them too */
-	if (pci_out_supported(q))
+	if (pci_out_supported(q->irq_ptr))
 		qdio_siga_sync_all(q);
 	else
 		qdio_siga_sync_q(q);
@@ -415,7 +415,8 @@ static inline void account_sbals(struct qdio_q *q, unsigned int count)
 	q->q_stats.nr_sbals[pos]++;
 }
 
-static void process_buffer_error(struct qdio_q *q, int count)
+static void process_buffer_error(struct qdio_q *q, unsigned int start,
+				 int count)
 {
 	unsigned char state = (q->is_input_q) ? SLSB_P_INPUT_NOT_INIT :
 					SLSB_P_OUTPUT_NOT_INIT;
@@ -424,29 +425,29 @@ static void process_buffer_error(struct qdio_q *q, int count)
 
 	/* special handling for no target buffer empty */
 	if (queue_type(q) == QDIO_IQDIO_QFMT && !q->is_input_q &&
-	    q->sbal[q->first_to_check]->element[15].sflags == 0x10) {
+	    q->sbal[start]->element[15].sflags == 0x10) {
 		qperf_inc(q, target_full);
-		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x",
-			      q->first_to_check);
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", start);
 		goto set;
 	}
 
 	DBF_ERROR("%4x BUF ERROR", SCH_NO(q));
 	DBF_ERROR((q->is_input_q) ? "IN:%2d" : "OUT:%2d", q->nr);
-	DBF_ERROR("FTC:%3d C:%3d", q->first_to_check, count);
+	DBF_ERROR("FTC:%3d C:%3d", start, count);
 	DBF_ERROR("F14:%2x F15:%2x",
-		  q->sbal[q->first_to_check]->element[14].sflags,
-		  q->sbal[q->first_to_check]->element[15].sflags);
+		  q->sbal[start]->element[14].sflags,
+		  q->sbal[start]->element[15].sflags);
 
 set:
 	/*
 	 * Interrupts may be avoided as long as the error is present
 	 * so change the buffer state immediately to avoid starvation.
 	 */
-	set_buf_states(q, q->first_to_check, state, count);
+	set_buf_states(q, start, state, count);
 }
 
-static inline void inbound_primed(struct qdio_q *q, int count)
+static inline void inbound_primed(struct qdio_q *q, unsigned int start,
+				  int count)
 {
 	int new;
 
@@ -457,7 +458,7 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 		if (!q->u.in.polling) {
 			q->u.in.polling = 1;
 			q->u.in.ack_count = count;
-			q->u.in.ack_start = q->first_to_check;
+			q->u.in.ack_start = start;
 			return;
 		}
 
@@ -465,7 +466,7 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 		set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
 			       q->u.in.ack_count);
 		q->u.in.ack_count = count;
-		q->u.in.ack_start = q->first_to_check;
+		q->u.in.ack_start = start;
 		return;
 	}
 
@@ -473,7 +474,7 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 	 * ACK the newest buffer. The ACK will be removed in qdio_stop_polling
 	 * or by the next inbound run.
 	 */
-	new = add_buf(q->first_to_check, count - 1);
+	new = add_buf(start, count - 1);
 	if (q->u.in.polling) {
 		/* reset the previous ACK but first set the new one */
 		set_buf_state(q, new, SLSB_P_INPUT_ACK);
@@ -488,10 +489,10 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 	if (!count)
 		return;
 	/* need to change ALL buffers to get more interrupts */
-	set_buf_states(q, q->first_to_check, SLSB_P_INPUT_NOT_INIT, count);
+	set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count);
 }
 
-static int get_inbound_buffer_frontier(struct qdio_q *q)
+static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 {
 	unsigned char state = 0;
 	int count;
@@ -504,64 +505,58 @@ static int get_inbound_buffer_frontier(struct qdio_q *q)
 	 */
 	count = min(atomic_read(&q->nr_buf_used), QDIO_MAX_BUFFERS_MASK);
 	if (!count)
-		goto out;
+		return 0;
 
 	/*
 	 * No siga sync here, as a PCI or we after a thin interrupt
 	 * already sync'ed the queues.
 	 */
-	count = get_buf_states(q, q->first_to_check, &state, count, 1, 0);
+	count = get_buf_states(q, start, &state, count, 1, 0);
 	if (!count)
-		goto out;
+		return 0;
 
 	switch (state) {
 	case SLSB_P_INPUT_PRIMED:
-		inbound_primed(q, count);
-		q->first_to_check = add_buf(q->first_to_check, count);
+		inbound_primed(q, start, count);
 		if (atomic_sub_return(count, &q->nr_buf_used) == 0)
 			qperf_inc(q, inbound_queue_full);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals(q, count);
-		break;
+		return count;
 	case SLSB_P_INPUT_ERROR:
-		process_buffer_error(q, count);
-		q->first_to_check = add_buf(q->first_to_check, count);
+		process_buffer_error(q, start, count);
 		if (atomic_sub_return(count, &q->nr_buf_used) == 0)
 			qperf_inc(q, inbound_queue_full);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals_error(q, count);
-		break;
+		return count;
 	case SLSB_CU_INPUT_EMPTY:
 	case SLSB_P_INPUT_NOT_INIT:
 	case SLSB_P_INPUT_ACK:
 		if (q->irq_ptr->perf_stat_enabled)
 			q->q_stats.nr_sbal_nop++;
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in nop:%1d %#02x",
-			q->nr, q->first_to_check);
-		break;
+			      q->nr, start);
+		return 0;
 	default:
 		WARN_ON_ONCE(1);
+		return 0;
 	}
-out:
-	return q->first_to_check;
 }
 
-static int qdio_inbound_q_moved(struct qdio_q *q)
+static int qdio_inbound_q_moved(struct qdio_q *q, unsigned int start)
 {
-	int bufnr;
+	int count;
 
-	bufnr = get_inbound_buffer_frontier(q);
+	count = get_inbound_buffer_frontier(q, start);
 
-	if (bufnr != q->last_move) {
-		q->last_move = bufnr;
-		if (!is_thinint_irq(q->irq_ptr) && MACHINE_IS_LPAR)
-			q->u.in.timestamp = get_tod_clock();
-		return 1;
-	} else
-		return 0;
+	if (count && !is_thinint_irq(q->irq_ptr) && MACHINE_IS_LPAR)
+		q->u.in.timestamp = get_tod_clock();
+
+	return count;
 }
 
-static inline int qdio_inbound_q_done(struct qdio_q *q)
+static inline int qdio_inbound_q_done(struct qdio_q *q, unsigned int start)
 {
 	unsigned char state = 0;
 
@@ -570,7 +565,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q)
 
 	if (need_siga_sync(q))
 		qdio_siga_sync_q(q);
-	get_buf_state(q, q->first_to_check, &state, 0);
+	get_buf_state(q, start, &state, 0);
 
 	if (state == SLSB_P_INPUT_PRIMED || state == SLSB_P_INPUT_ERROR)
 		/* more work coming */
@@ -588,8 +583,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q)
 	 * has (probably) not moved (see qdio_inbound_processing).
 	 */
 	if (get_tod_clock_fast() > q->u.in.timestamp + QDIO_INPUT_THRESHOLD) {
-		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x",
-			      q->first_to_check);
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x", start);
 		return 1;
 	} else
 		return 0;
@@ -637,17 +631,13 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 	return phys_aob;
 }
 
-static void qdio_kick_handler(struct qdio_q *q)
+static void qdio_kick_handler(struct qdio_q *q, unsigned int count)
 {
 	int start = q->first_to_kick;
-	int end = q->first_to_check;
-	int count;
 
 	if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
 		return;
 
-	count = sub_buf(end, start);
-
 	if (q->is_input_q) {
 		qperf_inc(q, inbound_handler);
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "kih s:%02x c:%02x", start, count);
@@ -663,7 +653,7 @@ static void qdio_kick_handler(struct qdio_q *q)
 		   q->irq_ptr->int_parm);
 
 	/* for the next time */
-	q->first_to_kick = end;
+	q->first_to_kick = add_buf(start, count);
 	q->qdio_error = 0;
 }
 
@@ -678,14 +668,20 @@ static inline int qdio_tasklet_schedule(struct qdio_q *q)
 
 static void __qdio_inbound_processing(struct qdio_q *q)
 {
+	unsigned int start = q->first_to_check;
+	int count;
+
 	qperf_inc(q, tasklet_inbound);
 
-	if (!qdio_inbound_q_moved(q))
+	count = qdio_inbound_q_moved(q, start);
+	if (count == 0)
 		return;
 
-	qdio_kick_handler(q);
+	start = add_buf(start, count);
+	q->first_to_check = start;
+	qdio_kick_handler(q, count);
 
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		/* means poll time is not yet over */
 		qperf_inc(q, tasklet_inbound_resched);
 		if (!qdio_tasklet_schedule(q))
@@ -697,7 +693,7 @@ static void __qdio_inbound_processing(struct qdio_q *q)
 	 * We need to check again to not lose initiative after
 	 * resetting the ACK state.
 	 */
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		qperf_inc(q, tasklet_inbound_resched2);
 		qdio_tasklet_schedule(q);
 	}
@@ -709,7 +705,7 @@ void qdio_inbound_processing(unsigned long data)
 	__qdio_inbound_processing(q);
 }
 
-static int get_outbound_buffer_frontier(struct qdio_q *q)
+static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 {
 	unsigned char state = 0;
 	int count;
@@ -718,7 +714,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 
 	if (need_siga_sync(q))
 		if (((queue_type(q) != QDIO_IQDIO_QFMT) &&
-		    !pci_out_supported(q)) ||
+		    !pci_out_supported(q->irq_ptr)) ||
 		    (queue_type(q) == QDIO_IQDIO_QFMT &&
 		    multicast_outbound(q)))
 			qdio_siga_sync_q(q);
@@ -729,12 +725,11 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 	 */
 	count = min(atomic_read(&q->nr_buf_used), QDIO_MAX_BUFFERS_MASK);
 	if (!count)
-		goto out;
+		return 0;
 
-	count = get_buf_states(q, q->first_to_check, &state, count, 0,
-			       q->u.out.use_cq);
+	count = get_buf_states(q, start, &state, count, 0, q->u.out.use_cq);
 	if (!count)
-		goto out;
+		return 0;
 
 	switch (state) {
 	case SLSB_P_OUTPUT_EMPTY:
@@ -743,34 +738,29 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 			"out empty:%1d %02x", q->nr, count);
 
 		atomic_sub(count, &q->nr_buf_used);
-		q->first_to_check = add_buf(q->first_to_check, count);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals(q, count);
-
-		break;
+		return count;
 	case SLSB_P_OUTPUT_ERROR:
-		process_buffer_error(q, count);
-		q->first_to_check = add_buf(q->first_to_check, count);
+		process_buffer_error(q, start, count);
 		atomic_sub(count, &q->nr_buf_used);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals_error(q, count);
-		break;
+		return count;
 	case SLSB_CU_OUTPUT_PRIMED:
 		/* the adapter has not fetched the output yet */
 		if (q->irq_ptr->perf_stat_enabled)
 			q->q_stats.nr_sbal_nop++;
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out primed:%1d",
 			      q->nr);
-		break;
+		return 0;
 	case SLSB_P_OUTPUT_NOT_INIT:
 	case SLSB_P_OUTPUT_HALTED:
-		break;
+		return 0;
 	default:
 		WARN_ON_ONCE(1);
+		return 0;
 	}
-
-out:
-	return q->first_to_check;
 }
 
 /* all buffers processed? */
@@ -779,18 +769,16 @@ static inline int qdio_outbound_q_done(struct qdio_q *q)
 	return atomic_read(&q->nr_buf_used) == 0;
 }
 
-static inline int qdio_outbound_q_moved(struct qdio_q *q)
+static inline int qdio_outbound_q_moved(struct qdio_q *q, unsigned int start)
 {
-	int bufnr;
+	int count;
 
-	bufnr = get_outbound_buffer_frontier(q);
+	count = get_outbound_buffer_frontier(q, start);
 
-	if (bufnr != q->last_move) {
-		q->last_move = bufnr;
+	if (count)
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out moved:%1d", q->nr);
-		return 1;
-	} else
-		return 0;
+
+	return count;
 }
 
 static int qdio_kick_outbound_q(struct qdio_q *q, unsigned long aob)
@@ -837,15 +825,21 @@ retry:
 
 static void __qdio_outbound_processing(struct qdio_q *q)
 {
+	unsigned int start = q->first_to_check;
+	int count;
+
 	qperf_inc(q, tasklet_outbound);
 	WARN_ON_ONCE(atomic_read(&q->nr_buf_used) < 0);
 
-	if (qdio_outbound_q_moved(q))
-		qdio_kick_handler(q);
+	count = qdio_outbound_q_moved(q, start);
+	if (count) {
+		q->first_to_check = add_buf(start, count);
+		qdio_kick_handler(q, count);
+	}
 
-	if (queue_type(q) == QDIO_ZFCP_QFMT)
-		if (!pci_out_supported(q) && !qdio_outbound_q_done(q))
-			goto sched;
+	if (queue_type(q) == QDIO_ZFCP_QFMT && !pci_out_supported(q->irq_ptr) &&
+	    !qdio_outbound_q_done(q))
+		goto sched;
 
 	if (q->u.out.pci_out_enabled)
 		return;
@@ -881,37 +875,40 @@ void qdio_outbound_timer(struct timer_list *t)
 	qdio_tasklet_schedule(q);
 }
 
-static inline void qdio_check_outbound_after_thinint(struct qdio_q *q)
+static inline void qdio_check_outbound_pci_queues(struct qdio_irq *irq)
 {
 	struct qdio_q *out;
 	int i;
 
-	if (!pci_out_supported(q))
+	if (!pci_out_supported(irq))
 		return;
 
-	for_each_output_queue(q->irq_ptr, out, i)
+	for_each_output_queue(irq, out, i)
 		if (!qdio_outbound_q_done(out))
 			qdio_tasklet_schedule(out);
 }
 
 static void __tiqdio_inbound_processing(struct qdio_q *q)
 {
+	unsigned int start = q->first_to_check;
+	int count;
+
 	qperf_inc(q, tasklet_inbound);
 	if (need_siga_sync(q) && need_siga_sync_after_ai(q))
 		qdio_sync_queues(q);
 
-	/*
-	 * The interrupt could be caused by a PCI request. Check the
-	 * PCI capable outbound queues.
-	 */
-	qdio_check_outbound_after_thinint(q);
+	/* The interrupt could be caused by a PCI request: */
+	qdio_check_outbound_pci_queues(q->irq_ptr);
 
-	if (!qdio_inbound_q_moved(q))
+	count = qdio_inbound_q_moved(q, start);
+	if (count == 0)
 		return;
 
-	qdio_kick_handler(q);
+	start = add_buf(start, count);
+	q->first_to_check = start;
+	qdio_kick_handler(q, count);
 
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		qperf_inc(q, tasklet_inbound_resched);
 		if (!qdio_tasklet_schedule(q))
 			return;
@@ -922,7 +919,7 @@ static void __tiqdio_inbound_processing(struct qdio_q *q)
 	 * We need to check again to not lose initiative after
 	 * resetting the ACK state.
 	 */
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		qperf_inc(q, tasklet_inbound_resched2);
 		qdio_tasklet_schedule(q);
 	}
@@ -976,7 +973,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr)
 		}
 	}
 
-	if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED))
+	if (!pci_out_supported(irq_ptr))
 		return;
 
 	for_each_output_queue(irq_ptr, q, i) {
@@ -1642,7 +1639,7 @@ int qdio_start_irq(struct ccw_device *cdev, int nr)
 	 */
 	if (test_nonshared_ind(irq_ptr))
 		goto rescan;
-	if (!qdio_inbound_q_done(q))
+	if (!qdio_inbound_q_done(q, q->first_to_check))
 		goto rescan;
 	return 0;
 
@@ -1672,12 +1669,14 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr,
 			  int *error)
 {
 	struct qdio_q *q;
-	int start, end;
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
+	unsigned int start;
+	int count;
 
 	if (!irq_ptr)
 		return -ENODEV;
 	q = irq_ptr->input_qs[nr];
+	start = q->first_to_check;
 
 	/*
 	 * Cannot rely on automatic sync after interrupt since queues may
@@ -1686,25 +1685,27 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr,
 	if (need_siga_sync(q))
 		qdio_sync_queues(q);
 
-	/* check the PCI capable outbound queues. */
-	qdio_check_outbound_after_thinint(q);
+	qdio_check_outbound_pci_queues(irq_ptr);
 
-	if (!qdio_inbound_q_moved(q))
+	count = qdio_inbound_q_moved(q, start);
+	if (count == 0)
 		return 0;
 
+	start = add_buf(start, count);
+	q->first_to_check = start;
+
 	/* Note: upper-layer MUST stop processing immediately here ... */
 	if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
 		return -EIO;
 
-	start = q->first_to_kick;
-	end = q->first_to_check;
-	*bufnr = start;
+	*bufnr = q->first_to_kick;
 	*error = q->qdio_error;
 
 	/* for the next time */
-	q->first_to_kick = end;
+	q->first_to_kick = add_buf(q->first_to_kick, count);
 	q->qdio_error = 0;
-	return sub_buf(end, start);
+
+	return count;
 }
 EXPORT_SYMBOL(qdio_get_next_buffers);
 
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index a59887fad13e..99d7d2566a3a 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -523,7 +523,7 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
 		 irq_ptr->schid.sch_no,
 		 is_thinint_irq(irq_ptr),
 		 (irq_ptr->sch_token) ? 1 : 0,
-		 (irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) ? 1 : 0,
+		 pci_out_supported(irq_ptr) ? 1 : 0,
 		 css_general_characteristics.aif_tdd,
 		 (irq_ptr->siga_flag.input) ? "R" : " ",
 		 (irq_ptr->siga_flag.output) ? "W" : " ",
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 07dea602205b..28d59ac2204c 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -40,7 +40,7 @@ static LIST_HEAD(tiq_list);
 static DEFINE_MUTEX(tiq_list_lock);
 
 /* Adapter interrupt definitions */
-static void tiqdio_thinint_handler(struct airq_struct *airq);
+static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating);
 
 static struct airq_struct tiqdio_airq = {
 	.handler = tiqdio_thinint_handler,
@@ -179,7 +179,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
  * tiqdio_thinint_handler - thin interrupt handler for qdio
  * @airq: pointer to adapter interrupt descriptor
  */
-static void tiqdio_thinint_handler(struct airq_struct *airq)
+static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 {
 	u32 si_used = clear_shared_ind();
 	struct qdio_q *q;
diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
new file mode 100644
index 000000000000..8c1d2357ef5b
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Async I/O region for vfio_ccw
+ *
+ * Copyright Red Hat, Inc. 2019
+ *
+ * Author(s): Cornelia Huck <cohuck@redhat.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "vfio_ccw_private.h"
+
+static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
+					  char __user *buf, size_t count,
+					  loff_t *ppos)
+{
+	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_cmd_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	mutex_lock(&private->io_mutex);
+	region = private->region[i].data;
+	if (copy_to_user(buf, (void *)region + pos, count))
+		ret = -EFAULT;
+	else
+		ret = count;
+	mutex_unlock(&private->io_mutex);
+	return ret;
+}
+
+static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private,
+					   const char __user *buf, size_t count,
+					   loff_t *ppos)
+{
+	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_cmd_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	if (!mutex_trylock(&private->io_mutex))
+		return -EAGAIN;
+
+	region = private->region[i].data;
+	if (copy_from_user((void *)region + pos, buf, count)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
+
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_ASYNC_REQ);
+
+	ret = region->ret_code ? region->ret_code : count;
+
+out_unlock:
+	mutex_unlock(&private->io_mutex);
+	return ret;
+}
+
+static void vfio_ccw_async_region_release(struct vfio_ccw_private *private,
+					  struct vfio_ccw_region *region)
+{
+
+}
+
+const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
+	.read = vfio_ccw_async_region_read,
+	.write = vfio_ccw_async_region_write,
+	.release = vfio_ccw_async_region_release,
+};
+
+int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private)
+{
+	return vfio_ccw_register_dev_region(private,
+					    VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD,
+					    &vfio_ccw_async_region_ops,
+					    sizeof(struct ccw_cmd_region),
+					    VFIO_REGION_INFO_FLAG_READ |
+					    VFIO_REGION_INFO_FLAG_WRITE,
+					    private->cmd_region);
+}
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 384b3987eeb4..0e79799e9a71 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -362,6 +362,7 @@ static void cp_unpin_free(struct channel_program *cp)
 	struct ccwchain *chain, *temp;
 	int i;
 
+	cp->initialized = false;
 	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++) {
 			pfn_array_table_unpin_free(chain->ch_pat + i,
@@ -732,6 +733,9 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 	 */
 	cp->orb.cmd.c64 = 1;
 
+	if (!ret)
+		cp->initialized = true;
+
 	return ret;
 }
 
@@ -746,7 +750,8 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
  */
 void cp_free(struct channel_program *cp)
 {
-	cp_unpin_free(cp);
+	if (cp->initialized)
+		cp_unpin_free(cp);
 }
 
 /**
@@ -791,6 +796,10 @@ int cp_prefetch(struct channel_program *cp)
 	struct ccwchain *chain;
 	int len, idx, ret;
 
+	/* this is an error in the caller */
+	if (!cp->initialized)
+		return -EINVAL;
+
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		len = chain->ch_len;
 		for (idx = 0; idx < len; idx++) {
@@ -826,6 +835,10 @@ union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm)
 	struct ccwchain *chain;
 	struct ccw1 *cpa;
 
+	/* this is an error in the caller */
+	if (!cp->initialized)
+		return NULL;
+
 	orb = &cp->orb;
 
 	orb->cmd.intparm = intparm;
@@ -862,6 +875,9 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
 	u32 cpa = scsw->cmd.cpa;
 	u32 ccw_head;
 
+	if (!cp->initialized)
+		return;
+
 	/*
 	 * LATER:
 	 * For now, only update the cmd.cpa part. We may need to deal with
@@ -898,6 +914,9 @@ bool cp_iova_pinned(struct channel_program *cp, u64 iova)
 	struct ccwchain *chain;
 	int i;
 
+	if (!cp->initialized)
+		return false;
+
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++)
 			if (pfn_array_table_iova_pinned(chain->ch_pat + i,
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index a4b74fb1aa57..3c20cd208da5 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -21,6 +21,7 @@
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @mdev: the mediated device to perform page pinning/unpinning
+ * @initialized: whether this instance is actually initialized
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -30,6 +31,7 @@ struct channel_program {
 	struct list_head ccwchain_list;
 	union orb orb;
 	struct device *mdev;
+	bool initialized;
 };
 
 extern int cp_init(struct channel_program *cp, struct device *mdev,
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 0b3b9de45c60..ee8767f5845a 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -3,9 +3,11 @@
  * VFIO based Physical Subchannel device driver
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/module.h>
@@ -23,6 +25,7 @@
 
 struct workqueue_struct *vfio_ccw_work_q;
 static struct kmem_cache *vfio_ccw_io_region;
+static struct kmem_cache *vfio_ccw_cmd_region;
 
 /*
  * Helpers
@@ -40,26 +43,30 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 	if (ret != -EBUSY)
 		goto out_unlock;
 
+	iretry = 255;
 	do {
-		iretry = 255;
 
 		ret = cio_cancel_halt_clear(sch, &iretry);
-		while (ret == -EBUSY) {
-			/*
-			 * Flush all I/O and wait for
-			 * cancel/halt/clear completion.
-			 */
-			private->completion = &completion;
-			spin_unlock_irq(sch->lock);
 
-			wait_for_completion_timeout(&completion, 3*HZ);
+		if (ret == -EIO) {
+			pr_err("vfio_ccw: could not quiesce subchannel 0.%x.%04x!\n",
+			       sch->schid.ssid, sch->schid.sch_no);
+			break;
+		}
+
+		/*
+		 * Flush all I/O and wait for
+		 * cancel/halt/clear completion.
+		 */
+		private->completion = &completion;
+		spin_unlock_irq(sch->lock);
 
-			spin_lock_irq(sch->lock);
-			private->completion = NULL;
-			flush_workqueue(vfio_ccw_work_q);
-			ret = cio_cancel_halt_clear(sch, &iretry);
-		};
+		if (ret == -EBUSY)
+			wait_for_completion_timeout(&completion, 3*HZ);
 
+		private->completion = NULL;
+		flush_workqueue(vfio_ccw_work_q);
+		spin_lock_irq(sch->lock);
 		ret = cio_disable_subchannel(sch);
 	} while (ret == -EBUSY);
 out_unlock:
@@ -84,7 +91,9 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 		if (is_final)
 			cp_free(&private->cp);
 	}
+	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
+	mutex_unlock(&private->io_mutex);
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger, 1);
@@ -108,7 +117,7 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 {
 	struct pmcw *pmcw = &sch->schib.pmcw;
 	struct vfio_ccw_private *private;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (pmcw->qf) {
 		dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n",
@@ -122,13 +131,17 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 
 	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
 					       GFP_KERNEL | GFP_DMA);
-	if (!private->io_region) {
-		kfree(private);
-		return -ENOMEM;
-	}
+	if (!private->io_region)
+		goto out_free;
+
+	private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
+						GFP_KERNEL | GFP_DMA);
+	if (!private->cmd_region)
+		goto out_free;
 
 	private->sch = sch;
 	dev_set_drvdata(&sch->dev, private);
+	mutex_init(&private->io_mutex);
 
 	spin_lock_irq(sch->lock);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
@@ -152,7 +165,10 @@ out_disable:
 	cio_disable_subchannel(sch);
 out_free:
 	dev_set_drvdata(&sch->dev, NULL);
-	kmem_cache_free(vfio_ccw_io_region, private->io_region);
+	if (private->cmd_region)
+		kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
+	if (private->io_region)
+		kmem_cache_free(vfio_ccw_io_region, private->io_region);
 	kfree(private);
 	return ret;
 }
@@ -167,6 +183,7 @@ static int vfio_ccw_sch_remove(struct subchannel *sch)
 
 	dev_set_drvdata(&sch->dev, NULL);
 
+	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
 	kmem_cache_free(vfio_ccw_io_region, private->io_region);
 	kfree(private);
 
@@ -241,7 +258,7 @@ static struct css_driver vfio_ccw_sch_driver = {
 
 static int __init vfio_ccw_sch_init(void)
 {
-	int ret;
+	int ret = -ENOMEM;
 
 	vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
 	if (!vfio_ccw_work_q)
@@ -251,20 +268,30 @@ static int __init vfio_ccw_sch_init(void)
 					sizeof(struct ccw_io_region), 0,
 					SLAB_ACCOUNT, 0,
 					sizeof(struct ccw_io_region), NULL);
-	if (!vfio_ccw_io_region) {
-		destroy_workqueue(vfio_ccw_work_q);
-		return -ENOMEM;
-	}
+	if (!vfio_ccw_io_region)
+		goto out_err;
+
+	vfio_ccw_cmd_region = kmem_cache_create_usercopy("vfio_ccw_cmd_region",
+					sizeof(struct ccw_cmd_region), 0,
+					SLAB_ACCOUNT, 0,
+					sizeof(struct ccw_cmd_region), NULL);
+	if (!vfio_ccw_cmd_region)
+		goto out_err;
 
 	isc_register(VFIO_CCW_ISC);
 	ret = css_driver_register(&vfio_ccw_sch_driver);
 	if (ret) {
 		isc_unregister(VFIO_CCW_ISC);
-		kmem_cache_destroy(vfio_ccw_io_region);
-		destroy_workqueue(vfio_ccw_work_q);
+		goto out_err;
 	}
 
 	return ret;
+
+out_err:
+	kmem_cache_destroy(vfio_ccw_cmd_region);
+	kmem_cache_destroy(vfio_ccw_io_region);
+	destroy_workqueue(vfio_ccw_work_q);
+	return ret;
 }
 
 static void __exit vfio_ccw_sch_exit(void)
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index cab17865aafe..49d9d3da0282 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -3,8 +3,10 @@
  * Finite state machine for vfio-ccw device handling
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/vfio.h>
@@ -28,9 +30,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	sch = private->sch;
 
 	spin_lock_irqsave(sch->lock, flags);
-	private->state = VFIO_CCW_STATE_BUSY;
 
 	orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
+	if (!orb) {
+		ret = -EIO;
+		goto out;
+	}
 
 	/* Issue "Start Subchannel" */
 	ccode = ssch(sch->schid, orb);
@@ -42,6 +47,7 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 		 */
 		sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
 		ret = 0;
+		private->state = VFIO_CCW_STATE_CP_PENDING;
 		break;
 	case 1:		/* Status pending */
 	case 2:		/* Busy */
@@ -64,6 +70,76 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	default:
 		ret = ccode;
 	}
+out:
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
+}
+
+static int fsm_do_halt(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	unsigned long flags;
+	int ccode;
+	int ret;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+
+	/* Issue "Halt Subchannel" */
+	ccode = hsch(sch->schid);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl |= SCSW_ACTL_HALT_PEND;
+		ret = 0;
+		break;
+	case 1:		/* Status pending */
+	case 2:		/* Busy */
+		ret = -EBUSY;
+		break;
+	case 3:		/* Device not operational */
+		ret = -ENODEV;
+		break;
+	default:
+		ret = ccode;
+	}
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
+}
+
+static int fsm_do_clear(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	unsigned long flags;
+	int ccode;
+	int ret;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+
+	/* Issue "Clear Subchannel" */
+	ccode = csch(sch->schid);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl = SCSW_ACTL_CLEAR_PEND;
+		/* TODO: check what else we might need to clear */
+		ret = 0;
+		break;
+	case 3:		/* Device not operational */
+		ret = -ENODEV;
+		break;
+	default:
+		ret = ccode;
+	}
 	spin_unlock_irqrestore(sch->lock, flags);
 	return ret;
 }
@@ -102,6 +178,30 @@ static void fsm_io_busy(struct vfio_ccw_private *private,
 	private->io_region->ret_code = -EBUSY;
 }
 
+static void fsm_io_retry(struct vfio_ccw_private *private,
+			 enum vfio_ccw_event event)
+{
+	private->io_region->ret_code = -EAGAIN;
+}
+
+static void fsm_async_error(struct vfio_ccw_private *private,
+			    enum vfio_ccw_event event)
+{
+	struct ccw_cmd_region *cmd_region = private->cmd_region;
+
+	pr_err("vfio-ccw: FSM: %s request from state:%d\n",
+	       cmd_region->command == VFIO_CCW_ASYNC_CMD_HSCH ? "halt" :
+	       cmd_region->command == VFIO_CCW_ASYNC_CMD_CSCH ? "clear" :
+	       "<unknown>", private->state);
+	cmd_region->ret_code = -EIO;
+}
+
+static void fsm_async_retry(struct vfio_ccw_private *private,
+			    enum vfio_ccw_event event)
+{
+	private->cmd_region->ret_code = -EAGAIN;
+}
+
 static void fsm_disabled_irq(struct vfio_ccw_private *private,
 			     enum vfio_ccw_event event)
 {
@@ -130,8 +230,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	struct mdev_device *mdev = private->mdev;
 	char *errstr = "request";
 
-	private->state = VFIO_CCW_STATE_BUSY;
-
+	private->state = VFIO_CCW_STATE_CP_PROCESSING;
 	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
 
 	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
@@ -166,22 +265,42 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		}
 		return;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
-		/* XXX: Handle halt. */
+		/* halt is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
 		goto err_out;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_CLEAR_FUNC) {
-		/* XXX: Handle clear. */
+		/* clear is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
 		goto err_out;
 	}
 
 err_out:
-	private->state = VFIO_CCW_STATE_IDLE;
 	trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private),
 			       io_region->ret_code, errstr);
 }
 
 /*
+ * Deal with an async request from userspace.
+ */
+static void fsm_async_request(struct vfio_ccw_private *private,
+			      enum vfio_ccw_event event)
+{
+	struct ccw_cmd_region *cmd_region = private->cmd_region;
+
+	switch (cmd_region->command) {
+	case VFIO_CCW_ASYNC_CMD_HSCH:
+		cmd_region->ret_code = fsm_do_halt(private);
+		break;
+	case VFIO_CCW_ASYNC_CMD_CSCH:
+		cmd_region->ret_code = fsm_do_clear(private);
+		break;
+	default:
+		/* should not happen? */
+		cmd_region->ret_code = -EINVAL;
+	}
+}
+
+/*
  * Got an interrupt for a normal io (state busy).
  */
 static void fsm_irq(struct vfio_ccw_private *private,
@@ -204,21 +323,31 @@ fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = {
 	[VFIO_CCW_STATE_NOT_OPER] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_nop,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_error,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_disabled_irq,
 	},
 	[VFIO_CCW_STATE_STANDBY] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_error,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
 	[VFIO_CCW_STATE_IDLE] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_request,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_request,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_CP_PROCESSING] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_retry,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_retry,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
-	[VFIO_CCW_STATE_BUSY] = {
+	[VFIO_CCW_STATE_CP_PENDING] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_request,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
 };
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index f673e106c041..5eb61116ca6f 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -3,13 +3,17 @@
  * Physical device callbacks for vfio_ccw
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/vfio.h>
 #include <linux/mdev.h>
+#include <linux/nospec.h>
+#include <linux/slab.h>
 
 #include "vfio_ccw_private.h"
 
@@ -130,11 +134,12 @@ static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
 
 	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
 	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_mdev_reset(mdev))
+		if (!vfio_ccw_sch_quiesce(private->sch))
 			private->state = VFIO_CCW_STATE_STANDBY;
 		/* The state will be NOT_OPER on error. */
 	}
 
+	cp_free(&private->cp);
 	private->mdev = NULL;
 	atomic_inc(&private->avail);
 
@@ -146,20 +151,66 @@ static int vfio_ccw_mdev_open(struct mdev_device *mdev)
 	struct vfio_ccw_private *private =
 		dev_get_drvdata(mdev_parent_dev(mdev));
 	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
+	int ret;
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	return vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
-				      &events, &private->nb);
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+				     &events, &private->nb);
+	if (ret)
+		return ret;
+
+	ret = vfio_ccw_register_async_dev_regions(private);
+	if (ret)
+		vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+					 &private->nb);
+	return ret;
 }
 
 static void vfio_ccw_mdev_release(struct mdev_device *mdev)
 {
 	struct vfio_ccw_private *private =
 		dev_get_drvdata(mdev_parent_dev(mdev));
+	int i;
 
+	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
+	    (private->state != VFIO_CCW_STATE_STANDBY)) {
+		if (!vfio_ccw_mdev_reset(mdev))
+			private->state = VFIO_CCW_STATE_STANDBY;
+		/* The state will be NOT_OPER on error. */
+	}
+
+	cp_free(&private->cp);
 	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
 				 &private->nb);
+
+	for (i = 0; i < private->num_regions; i++)
+		private->region[i].ops->release(private, &private->region[i]);
+
+	private->num_regions = 0;
+	kfree(private->region);
+	private->region = NULL;
+}
+
+static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
+					    char __user *buf, size_t count,
+					    loff_t *ppos)
+{
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_io_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	mutex_lock(&private->io_mutex);
+	region = private->io_region;
+	if (copy_to_user(buf, (void *)region + pos, count))
+		ret = -EFAULT;
+	else
+		ret = count;
+	mutex_unlock(&private->io_mutex);
+	return ret;
 }
 
 static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
@@ -167,18 +218,54 @@ static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
 				  size_t count,
 				  loff_t *ppos)
 {
+	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
 	struct vfio_ccw_private *private;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
+		return -EINVAL;
+
+	switch (index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
+	default:
+		index -= VFIO_CCW_NUM_REGIONS;
+		return private->region[index].ops->read(private, buf, count,
+							ppos);
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private,
+					     const char __user *buf,
+					     size_t count, loff_t *ppos)
+{
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_io_region *region;
+	int ret;
 
-	if (*ppos + count > sizeof(*region))
+	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!mutex_trylock(&private->io_mutex))
+		return -EAGAIN;
+
 	region = private->io_region;
-	if (copy_to_user(buf, (void *)region + *ppos, count))
-		return -EFAULT;
+	if (copy_from_user((void *)region + pos, buf, count)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
 
-	return count;
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
+	if (region->ret_code != 0)
+		private->state = VFIO_CCW_STATE_IDLE;
+	ret = (region->ret_code != 0) ? region->ret_code : count;
+
+out_unlock:
+	mutex_unlock(&private->io_mutex);
+	return ret;
 }
 
 static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
@@ -186,42 +273,47 @@ static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
 				   size_t count,
 				   loff_t *ppos)
 {
+	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
 	struct vfio_ccw_private *private;
-	struct ccw_io_region *region;
-
-	if (*ppos + count > sizeof(*region))
-		return -EINVAL;
 
 	private = dev_get_drvdata(mdev_parent_dev(mdev));
-	if (private->state != VFIO_CCW_STATE_IDLE)
-		return -EACCES;
 
-	region = private->io_region;
-	if (copy_from_user((void *)region + *ppos, buf, count))
-		return -EFAULT;
+	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
+		return -EINVAL;
 
-	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
-	if (region->ret_code != 0) {
-		private->state = VFIO_CCW_STATE_IDLE;
-		return region->ret_code;
+	switch (index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
+	default:
+		index -= VFIO_CCW_NUM_REGIONS;
+		return private->region[index].ops->write(private, buf, count,
+							 ppos);
 	}
 
-	return count;
+	return -EINVAL;
 }
 
-static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info)
+static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info,
+					 struct mdev_device *mdev)
 {
+	struct vfio_ccw_private *private;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET;
-	info->num_regions = VFIO_CCW_NUM_REGIONS;
+	info->num_regions = VFIO_CCW_NUM_REGIONS + private->num_regions;
 	info->num_irqs = VFIO_CCW_NUM_IRQS;
 
 	return 0;
 }
 
 static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
-					 u16 *cap_type_id,
-					 void **cap_type)
+					 struct mdev_device *mdev,
+					 unsigned long arg)
 {
+	struct vfio_ccw_private *private;
+	int i;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	switch (info->index) {
 	case VFIO_CCW_CONFIG_REGION_INDEX:
 		info->offset = 0;
@@ -229,9 +321,55 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
 		info->flags = VFIO_REGION_INFO_FLAG_READ
 			      | VFIO_REGION_INFO_FLAG_WRITE;
 		return 0;
-	default:
-		return -EINVAL;
+	default: /* all other regions are handled via capability chain */
+	{
+		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+		struct vfio_region_info_cap_type cap_type = {
+			.header.id = VFIO_REGION_INFO_CAP_TYPE,
+			.header.version = 1 };
+		int ret;
+
+		if (info->index >=
+		    VFIO_CCW_NUM_REGIONS + private->num_regions)
+			return -EINVAL;
+
+		info->index = array_index_nospec(info->index,
+						 VFIO_CCW_NUM_REGIONS +
+						 private->num_regions);
+
+		i = info->index - VFIO_CCW_NUM_REGIONS;
+
+		info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index);
+		info->size = private->region[i].size;
+		info->flags = private->region[i].flags;
+
+		cap_type.type = private->region[i].type;
+		cap_type.subtype = private->region[i].subtype;
+
+		ret = vfio_info_add_capability(&caps, &cap_type.header,
+					       sizeof(cap_type));
+		if (ret)
+			return ret;
+
+		info->flags |= VFIO_REGION_INFO_FLAG_CAPS;
+		if (info->argsz < sizeof(*info) + caps.size) {
+			info->argsz = sizeof(*info) + caps.size;
+			info->cap_offset = 0;
+		} else {
+			vfio_info_cap_shift(&caps, sizeof(*info));
+			if (copy_to_user((void __user *)arg + sizeof(*info),
+					 caps.buf, caps.size)) {
+				kfree(caps.buf);
+				return -EFAULT;
+			}
+			info->cap_offset = sizeof(*info);
+		}
+
+		kfree(caps.buf);
+
 	}
+	}
+	return 0;
 }
 
 static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
@@ -308,6 +446,32 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
 	}
 }
 
+int vfio_ccw_register_dev_region(struct vfio_ccw_private *private,
+				 unsigned int subtype,
+				 const struct vfio_ccw_regops *ops,
+				 size_t size, u32 flags, void *data)
+{
+	struct vfio_ccw_region *region;
+
+	region = krealloc(private->region,
+			  (private->num_regions + 1) * sizeof(*region),
+			  GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
+
+	private->region = region;
+	private->region[private->num_regions].type = VFIO_REGION_TYPE_CCW;
+	private->region[private->num_regions].subtype = subtype;
+	private->region[private->num_regions].ops = ops;
+	private->region[private->num_regions].size = size;
+	private->region[private->num_regions].flags = flags;
+	private->region[private->num_regions].data = data;
+
+	private->num_regions++;
+
+	return 0;
+}
+
 static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 				   unsigned int cmd,
 				   unsigned long arg)
@@ -328,7 +492,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_device_info(&info);
+		ret = vfio_ccw_mdev_get_device_info(&info, mdev);
 		if (ret)
 			return ret;
 
@@ -337,8 +501,6 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 	case VFIO_DEVICE_GET_REGION_INFO:
 	{
 		struct vfio_region_info info;
-		u16 cap_type_id = 0;
-		void *cap_type = NULL;
 
 		minsz = offsetofend(struct vfio_region_info, offset);
 
@@ -348,8 +510,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_region_info(&info, &cap_type_id,
-						    &cap_type);
+		ret = vfio_ccw_mdev_get_region_info(&info, mdev, arg);
 		if (ret)
 			return ret;
 
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 08e9a7dc9176..f1092c3dc1b1 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -3,9 +3,11 @@
  * Private stuff for vfio_ccw driver
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #ifndef _VFIO_CCW_PRIVATE_H_
@@ -19,6 +21,40 @@
 #include "css.h"
 #include "vfio_ccw_cp.h"
 
+#define VFIO_CCW_OFFSET_SHIFT   10
+#define VFIO_CCW_OFFSET_TO_INDEX(off)	(off >> VFIO_CCW_OFFSET_SHIFT)
+#define VFIO_CCW_INDEX_TO_OFFSET(index)	((u64)(index) << VFIO_CCW_OFFSET_SHIFT)
+#define VFIO_CCW_OFFSET_MASK	(((u64)(1) << VFIO_CCW_OFFSET_SHIFT) - 1)
+
+/* capability chain handling similar to vfio-pci */
+struct vfio_ccw_private;
+struct vfio_ccw_region;
+
+struct vfio_ccw_regops {
+	ssize_t	(*read)(struct vfio_ccw_private *private, char __user *buf,
+			size_t count, loff_t *ppos);
+	ssize_t	(*write)(struct vfio_ccw_private *private,
+			 const char __user *buf, size_t count, loff_t *ppos);
+	void	(*release)(struct vfio_ccw_private *private,
+			   struct vfio_ccw_region *region);
+};
+
+struct vfio_ccw_region {
+	u32				type;
+	u32				subtype;
+	const struct vfio_ccw_regops	*ops;
+	void				*data;
+	size_t				size;
+	u32				flags;
+};
+
+int vfio_ccw_register_dev_region(struct vfio_ccw_private *private,
+				 unsigned int subtype,
+				 const struct vfio_ccw_regops *ops,
+				 size_t size, u32 flags, void *data);
+
+int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private);
+
 /**
  * struct vfio_ccw_private
  * @sch: pointer to the subchannel
@@ -28,6 +64,10 @@
  * @mdev: pointer to the mediated device
  * @nb: notifier for vfio events
  * @io_region: MMIO region to input/output I/O arguments/results
+ * @io_mutex: protect against concurrent update of I/O regions
+ * @region: additional regions for other subchannel operations
+ * @cmd_region: MMIO region for asynchronous I/O commands other than START
+ * @num_regions: number of additional regions
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
@@ -42,6 +82,10 @@ struct vfio_ccw_private {
 	struct mdev_device	*mdev;
 	struct notifier_block	nb;
 	struct ccw_io_region	*io_region;
+	struct mutex		io_mutex;
+	struct vfio_ccw_region *region;
+	struct ccw_cmd_region	*cmd_region;
+	int num_regions;
 
 	struct channel_program	cp;
 	struct irb		irb;
@@ -63,7 +107,8 @@ enum vfio_ccw_state {
 	VFIO_CCW_STATE_NOT_OPER,
 	VFIO_CCW_STATE_STANDBY,
 	VFIO_CCW_STATE_IDLE,
-	VFIO_CCW_STATE_BUSY,
+	VFIO_CCW_STATE_CP_PROCESSING,
+	VFIO_CCW_STATE_CP_PENDING,
 	/* last element! */
 	NR_VFIO_CCW_STATES
 };
@@ -75,6 +120,7 @@ enum vfio_ccw_event {
 	VFIO_CCW_EVENT_NOT_OPER,
 	VFIO_CCW_EVENT_IO_REQ,
 	VFIO_CCW_EVENT_INTERRUPT,
+	VFIO_CCW_EVENT_ASYNC_REQ,
 	/* last element! */
 	NR_VFIO_CCW_EVENTS
 };
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 1546389d71db..cc30e4f07fff 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -116,7 +116,7 @@ static int user_set_domain;
 static struct bus_type ap_bus_type;
 
 /* Adapter interrupt definitions */
-static void ap_interrupt_handler(struct airq_struct *airq);
+static void ap_interrupt_handler(struct airq_struct *airq, bool floating);
 
 static int ap_airq_flag;
 
@@ -393,7 +393,7 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *unused)
  * ap_interrupt_handler() - Schedule ap_tasklet on interrupt
  * @airq: pointer to adapter interrupt descriptor
  */
-static void ap_interrupt_handler(struct airq_struct *airq)
+static void ap_interrupt_handler(struct airq_struct *airq, bool floating)
 {
 	inc_irq_stat(IRQIO_APB);
 	if (!ap_suspend_flag)
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 689c2af7026a..c31b2d31cd83 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -659,6 +659,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO);
 
 	if (mex->outputdatalength < mex->inputdatalength) {
+		func_code = 0;
 		rc = -EINVAL;
 		goto out;
 	}
@@ -742,6 +743,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	trace_s390_zcrypt_req(crt, TP_ICARSACRT);
 
 	if (crt->outputdatalength < crt->inputdatalength) {
+		func_code = 0;
 		rc = -EINVAL;
 		goto out;
 	}
@@ -951,6 +953,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 
 		targets = kcalloc(target_num, sizeof(*targets), GFP_KERNEL);
 		if (!targets) {
+			func_code = 0;
 			rc = -ENOMEM;
 			goto out;
 		}
@@ -958,6 +961,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 		uptr = (struct ep11_target_dev __force __user *) xcrb->targets;
 		if (copy_from_user(targets, uptr,
 				   target_num * sizeof(*targets))) {
+			func_code = 0;
 			rc = -EFAULT;
 			goto out_free;
 		}
diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
index 0aab90817326..66eac2b9704d 100644
--- a/drivers/s390/net/ism.h
+++ b/drivers/s390/net/ism.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <net/smc.h>
+#include <asm/pci_insn.h>
 
 #define UTIL_STR_LEN	16
 
@@ -194,8 +195,6 @@ struct ism_dev {
 	struct pci_dev *pdev;
 	struct smcd_dev *smcd;
 
-	void __iomem *ctl;
-
 	struct ism_sba *sba;
 	dma_addr_t sba_dma_addr;
 	DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS);
@@ -209,13 +208,37 @@ struct ism_dev {
 #define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
 	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
 
+static inline void __ism_read_cmd(struct ism_dev *ism, void *data,
+				  unsigned long offset, unsigned long len)
+{
+	struct zpci_dev *zdev = to_zpci(ism->pdev);
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 2, 8);
+
+	while (len > 0) {
+		__zpci_load(data, req, offset);
+		offset += 8;
+		data += 8;
+		len -= 8;
+	}
+}
+
+static inline void __ism_write_cmd(struct ism_dev *ism, void *data,
+				   unsigned long offset, unsigned long len)
+{
+	struct zpci_dev *zdev = to_zpci(ism->pdev);
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 2, len);
+
+	if (len)
+		__zpci_store_block(data, req, offset);
+}
+
 static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data,
 			     unsigned int size)
 {
 	struct zpci_dev *zdev = to_zpci(ism->pdev);
 	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size);
 
-	return zpci_write_block(req, data, dmb_req);
+	return __zpci_store_block(data, req, dmb_req);
 }
 
 #endif /* S390_ISM_H */
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 3e132592c1fe..4fc2056bd227 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -38,19 +38,18 @@ static int ism_cmd(struct ism_dev *ism, void *cmd)
 	struct ism_req_hdr *req = cmd;
 	struct ism_resp_hdr *resp = cmd;
 
-	memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req));
-	memcpy_toio(ism->ctl, req, sizeof(*req));
+	__ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req));
+	__ism_write_cmd(ism, req, 0, sizeof(*req));
 
 	WRITE_ONCE(resp->ret, ISM_ERROR);
 
-	memcpy_fromio(resp, ism->ctl, sizeof(*resp));
+	__ism_read_cmd(ism, resp, 0, sizeof(*resp));
 	if (resp->ret) {
 		debug_text_event(ism_debug_info, 0, "cmd failure");
 		debug_event(ism_debug_info, 0, resp, sizeof(*resp));
 		goto out;
 	}
-	memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp),
-		      resp->len - sizeof(*resp));
+	__ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp));
 out:
 	return resp->ret;
 }
@@ -512,13 +511,9 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto err_disable;
 
-	ism->ctl = pci_iomap(pdev, 2, 0);
-	if (!ism->ctl)
-		goto err_resource;
-
 	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (ret)
-		goto err_unmap;
+		goto err_resource;
 
 	dma_set_seg_boundary(&pdev->dev, SZ_1M - 1);
 	dma_set_max_seg_size(&pdev->dev, SZ_1M);
@@ -527,7 +522,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
 				   ISM_NR_DMBS);
 	if (!ism->smcd)
-		goto err_unmap;
+		goto err_resource;
 
 	ism->smcd->priv = ism;
 	ret = ism_dev_init(ism);
@@ -538,8 +533,6 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 err_free:
 	smcd_free_dev(ism->smcd);
-err_unmap:
-	pci_iounmap(pdev, ism->ctl);
 err_resource:
 	pci_release_mem_regions(pdev);
 err_disable:
@@ -568,7 +561,6 @@ static void ism_remove(struct pci_dev *pdev)
 	ism_dev_exit(ism);
 
 	smcd_free_dev(ism->smcd);
-	pci_iounmap(pdev, ism->ctl);
 	pci_release_mem_regions(pdev);
 	pci_disable_device(pdev);
 	dev_set_drvdata(&pdev->dev, NULL);
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 74c328321889..991420caa4f2 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -182,7 +182,7 @@ static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info)
 	write_unlock_irqrestore(&info->lock, flags);
 }
 
-static void virtio_airq_handler(struct airq_struct *airq)
+static void virtio_airq_handler(struct airq_struct *airq, bool floating)
 {
 	struct airq_info *info = container_of(airq, struct airq_info, airq);
 	unsigned long ai;
diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h
index 0e119d838e1b..762cb77253b9 100644
--- a/drivers/scsi/bfa/bfa.h
+++ b/drivers/scsi/bfa/bfa.h
@@ -62,8 +62,7 @@ void bfa_isr_unhandled(struct bfa_s *bfa, struct bfi_msg_s *m);
 			((__bfa)->iocfc.cfg.drvcfg.num_reqq_elems - 1); \
 		writel((__bfa)->iocfc.req_cq_pi[__reqq],		\
 			(__bfa)->iocfc.bfa_regs.cpe_q_pi[__reqq]);	\
-		mmiowb();      \
-	} while (0)
+		} while (0)
 
 #define bfa_rspq_pi(__bfa, __rspq)					\
 	(*(u32 *)((__bfa)->iocfc.rsp_cq_shadow_pi[__rspq].kva))
diff --git a/drivers/scsi/bfa/bfa_hw_cb.c b/drivers/scsi/bfa/bfa_hw_cb.c
index c4a0c0eb88a5..4a0d881b2602 100644
--- a/drivers/scsi/bfa/bfa_hw_cb.c
+++ b/drivers/scsi/bfa/bfa_hw_cb.c
@@ -61,7 +61,6 @@ bfa_hwcb_rspq_ack_msix(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
@@ -72,7 +71,6 @@ bfa_hwcb_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
diff --git a/drivers/scsi/bfa/bfa_hw_ct.c b/drivers/scsi/bfa/bfa_hw_ct.c
index b0ff378dece2..b7be5f4f02a5 100644
--- a/drivers/scsi/bfa/bfa_hw_ct.c
+++ b/drivers/scsi/bfa/bfa_hw_ct.c
@@ -81,7 +81,6 @@ bfa_hwct_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 /*
@@ -94,7 +93,6 @@ bfa_hwct2_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 {
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
index 039328d9ef13..19734ec7f42e 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
@@ -991,7 +991,6 @@ void bnx2fc_arm_cq(struct bnx2fc_rport *tgt)
 			FCOE_CQE_TOGGLE_BIT_SHIFT);
 	msg = *((u32 *)rx_db);
 	writel(cpu_to_le32(msg), tgt->ctx_base);
-	mmiowb();
 
 }
 
@@ -1409,7 +1408,6 @@ void bnx2fc_ring_doorbell(struct bnx2fc_rport *tgt)
 				(tgt->sq_curr_toggle_bit << 15);
 	msg = *((u32 *)sq_db);
 	writel(cpu_to_le32(msg), tgt->ctx_base);
-	mmiowb();
 
 }
 
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index fae6f71e677d..12666313b937 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -253,7 +253,6 @@ void bnx2i_put_rq_buf(struct bnx2i_conn *bnx2i_conn, int count)
 		writew(ep->qp.rq_prod_idx,
 		       ep->qp.ctx_base + CNIC_RECV_DOORBELL);
 	}
-	mmiowb();
 }
 
 
@@ -279,8 +278,6 @@ static void bnx2i_ring_sq_dbell(struct bnx2i_conn *bnx2i_conn, int count)
 		bnx2i_ring_577xx_doorbell(bnx2i_conn);
 	} else
 		writew(count, ep->qp.ctx_base + CNIC_SEND_DOORBELL);
-
-	mmiowb(); /* flush posted PCI writes */
 }
 
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 293f5cf524d7..59a6546fd602 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -815,7 +815,6 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance,
 	       &(regs)->inbound_high_queue_port);
 	writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1,
 	       &(regs)->inbound_low_queue_port);
-	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 1d17128030cd..e35c2b64c145 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -242,7 +242,6 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		&instance->reg_set->inbound_low_queue_port);
 	writel(le32_to_cpu(req_desc->u.high),
 		&instance->reg_set->inbound_high_queue_port);
-	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
 }
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 1d8c584ec1e9..f60b9e0a6ca6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3333,7 +3333,6 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 	spin_lock_irqsave(writeq_lock, flags);
 	__raw_writel((u32)(b), addr);
 	__raw_writel((u32)(b >> 32), (addr + 4));
-	mmiowb();
 	spin_unlock_irqrestore(writeq_lock, flags);
 }
 
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index 6ca583bdde23..53e8221f6816 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -807,7 +807,6 @@ void qedf_ring_doorbell(struct qedf_rport *fcport)
 	writel(*(u32 *)&dbell, fcport->p_doorbell);
 	/* Make sure SQ index is updated so f/w prcesses requests in order */
 	wmb();
-	mmiowb();
 }
 
 static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req,
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index e2a995a6e8e7..f8f86774f77f 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -985,7 +985,6 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 	 * others they are two different assembly operations.
 	 */
 	wmb();
-	mmiowb();
 	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_MP_REQ,
 		  "prod_idx=0x%x, fw_prod_idx=0x%x, cid=0x%x\n",
 		  qedi_conn->ep->sq_prod_idx, qedi_conn->ep->fw_sq_prod_idx,
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 6856dfdfa473..327eff67a1ee 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -3004,8 +3004,6 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	sp->flags |= SRB_SENT;
 	ha->actthreads++;
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	/* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */
-	mmiowb();
 
  out:
 	if (status)
@@ -3254,8 +3252,6 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	sp->flags |= SRB_SENT;
 	ha->actthreads++;
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	/* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */
-	mmiowb();
 
 out:
 	if (status)
@@ -3367,19 +3363,8 @@ qla1280_isp_cmd(struct scsi_qla_host *ha)
 
 	/*
 	 * Update request index to mailbox4 (Request Queue In).
-	 * The mmiowb() ensures that this write is ordered with writes by other
-	 * CPUs.  Without the mmiowb(), it is possible for the following:
-	 *    CPUA posts write of index 5 to mailbox4
-	 *    CPUA releases host lock
-	 *    CPUB acquires host lock
-	 *    CPUB posts write of index 6 to mailbox4
-	 *    On PCI bus, order reverses and write of 6 posts, then index 5,
-	 *       causing chip to issue full queue of stale commands
-	 * The mmiowb() prevents future writes from crossing the barrier.
-	 * See Documentation/driver-api/device-io.rst for more information.
 	 */
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	mmiowb();
 
 	LEAVE("qla1280_isp_cmd");
 }
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 84807a9b4b13..da2d2ab8104d 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -305,7 +305,6 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 		else if (i % 2)
 			pr_cont(".");
 		writew(sprom[i], bus->mmio + bus->sprom_offset + (i * 2));
-		mmiowb();
 		msleep(20);
 	}
 	err = pci_read_config_dword(pdev, SSB_SPROMCTL, &spromctl);
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index 567013f8a8be..d7d730c245c5 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -338,7 +338,6 @@ static void ssb_pcmcia_write8(struct ssb_device *dev, u16 offset, u8 value)
 	err = select_core_and_segment(dev, &offset);
 	if (likely(!err))
 		writeb(value, bus->mmio + offset);
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 
@@ -352,7 +351,6 @@ static void ssb_pcmcia_write16(struct ssb_device *dev, u16 offset, u16 value)
 	err = select_core_and_segment(dev, &offset);
 	if (likely(!err))
 		writew(value, bus->mmio + offset);
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 
@@ -368,7 +366,6 @@ static void ssb_pcmcia_write32(struct ssb_device *dev, u16 offset, u32 value)
 		writew((value & 0x0000FFFF), bus->mmio + offset);
 		writew(((value & 0xFFFF0000) >> 16), bus->mmio + offset + 2);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 
@@ -424,7 +421,6 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 		WARN_ON(1);
 	}
 unlock:
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 #endif /* CONFIG_SSB_BLOCKIO */
diff --git a/drivers/staging/comedi/drivers/mite.c b/drivers/staging/comedi/drivers/mite.c
index 61e03ad84123..639ec1586976 100644
--- a/drivers/staging/comedi/drivers/mite.c
+++ b/drivers/staging/comedi/drivers/mite.c
@@ -371,7 +371,6 @@ static unsigned int mite_get_status(struct mite_channel *mite_chan)
 		writel(CHOR_CLRDONE,
 		       mite->mmio + MITE_CHOR(mite_chan->channel));
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&mite->lock, flags);
 	return status;
 }
@@ -451,7 +450,6 @@ void mite_dma_arm(struct mite_channel *mite_chan)
 	mite_chan->done = 0;
 	/* arm */
 	writel(CHOR_START, mite->mmio + MITE_CHOR(mite_chan->channel));
-	mmiowb();
 	spin_unlock_irqrestore(&mite->lock, flags);
 }
 EXPORT_SYMBOL_GPL(mite_dma_arm);
@@ -638,7 +636,6 @@ void mite_release_channel(struct mite_channel *mite_chan)
 		       CHCR_CLR_LC_IE | CHCR_CLR_CONT_RB_IE,
 		       mite->mmio + MITE_CHCR(mite_chan->channel));
 		mite_chan->ring = NULL;
-		mmiowb();
 	}
 	spin_unlock_irqrestore(&mite->lock, flags);
 }
diff --git a/drivers/staging/comedi/drivers/ni_660x.c b/drivers/staging/comedi/drivers/ni_660x.c
index 405573e927cf..4ee9b260eab0 100644
--- a/drivers/staging/comedi/drivers/ni_660x.c
+++ b/drivers/staging/comedi/drivers/ni_660x.c
@@ -320,7 +320,6 @@ static inline void ni_660x_set_dma_channel(struct comedi_device *dev,
 	ni_660x_write(dev, chip, devpriv->dma_cfg[chip] |
 		      NI660X_DMA_CFG_RESET(mite_channel),
 		      NI660X_DMA_CFG);
-	mmiowb();
 }
 
 static inline void ni_660x_unset_dma_channel(struct comedi_device *dev,
@@ -333,7 +332,6 @@ static inline void ni_660x_unset_dma_channel(struct comedi_device *dev,
 	devpriv->dma_cfg[chip] &= ~NI660X_DMA_CFG_SEL_MASK(mite_channel);
 	devpriv->dma_cfg[chip] |= NI660X_DMA_CFG_SEL_NONE(mite_channel);
 	ni_660x_write(dev, chip, devpriv->dma_cfg[chip], NI660X_DMA_CFG);
-	mmiowb();
 }
 
 static int ni_660x_request_mite_channel(struct comedi_device *dev,
diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c
index b04dad8c7092..668f2aa16baa 100644
--- a/drivers/staging/comedi/drivers/ni_mio_common.c
+++ b/drivers/staging/comedi/drivers/ni_mio_common.c
@@ -547,7 +547,6 @@ static inline void ni_set_bitfield(struct comedi_device *dev, int reg,
 			reg);
 		break;
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&devpriv->soft_reg_copy_lock, flags);
 }
 
diff --git a/drivers/staging/comedi/drivers/ni_pcidio.c b/drivers/staging/comedi/drivers/ni_pcidio.c
index 4bdef87d5dd7..8f3864799c19 100644
--- a/drivers/staging/comedi/drivers/ni_pcidio.c
+++ b/drivers/staging/comedi/drivers/ni_pcidio.c
@@ -310,7 +310,6 @@ static int ni_pcidio_request_di_mite_channel(struct comedi_device *dev)
 	writeb(primary_DMAChannel_bits(devpriv->di_mite_chan->channel) |
 	       secondary_DMAChannel_bits(devpriv->di_mite_chan->channel),
 	       dev->mmio + DMA_LINE_CONTROL_GROUP1);
-	mmiowb();
 	spin_unlock_irqrestore(&devpriv->mite_channel_lock, flags);
 	return 0;
 }
@@ -327,7 +326,6 @@ static void ni_pcidio_release_di_mite_channel(struct comedi_device *dev)
 		writeb(primary_DMAChannel_bits(0) |
 		       secondary_DMAChannel_bits(0),
 		       dev->mmio + DMA_LINE_CONTROL_GROUP1);
-		mmiowb();
 	}
 	spin_unlock_irqrestore(&devpriv->mite_channel_lock, flags);
 }
diff --git a/drivers/staging/comedi/drivers/ni_tio.c b/drivers/staging/comedi/drivers/ni_tio.c
index 048cb35723ad..c1131a1622c0 100644
--- a/drivers/staging/comedi/drivers/ni_tio.c
+++ b/drivers/staging/comedi/drivers/ni_tio.c
@@ -234,7 +234,6 @@ static void ni_tio_set_bits_transient(struct ni_gpct *counter,
 		regs[reg] &= ~mask;
 		regs[reg] |= (value & mask);
 		ni_tio_write(counter, regs[reg] | transient, reg);
-		mmiowb();
 		spin_unlock_irqrestore(&counter_dev->regs_lock, flags);
 	}
 }
diff --git a/drivers/staging/comedi/drivers/s626.c b/drivers/staging/comedi/drivers/s626.c
index f5af6f4069dc..39049d3c56d7 100644
--- a/drivers/staging/comedi/drivers/s626.c
+++ b/drivers/staging/comedi/drivers/s626.c
@@ -108,7 +108,6 @@ static void s626_mc_enable(struct comedi_device *dev,
 {
 	unsigned int val = (cmd << 16) | cmd;
 
-	mmiowb();
 	writel(val, dev->mmio + reg);
 }
 
@@ -116,7 +115,6 @@ static void s626_mc_disable(struct comedi_device *dev,
 			    unsigned int cmd, unsigned int reg)
 {
 	writel(cmd << 16, dev->mmio + reg);
-	mmiowb();
 }
 
 static bool s626_mc_test(struct comedi_device *dev,
diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
index 45e7e5cbdffb..7c71ffb733a1 100644
--- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
@@ -230,7 +230,7 @@ static void get_single_name(acpi_handle handle, char *name)
 	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer)))
 		pr_warn("Failed to get device name from acpi handle\n");
 	else {
-		memcpy(name, buffer.pointer, ACPI_NAME_SIZE);
+		memcpy(name, buffer.pointer, ACPI_NAMESEG_SIZE);
 		kfree(buffer.pointer);
 	}
 }
diff --git a/drivers/tty/rocket.c b/drivers/tty/rocket.c
index b121d8f8f3d7..27aeca30eeae 100644
--- a/drivers/tty/rocket.c
+++ b/drivers/tty/rocket.c
@@ -266,7 +266,7 @@ MODULE_PARM_DESC(pc104_3, "set interface types for ISA(PC104) board #3 (e.g. pc1
 module_param_array(pc104_4, ulong, NULL, 0);
 MODULE_PARM_DESC(pc104_4, "set interface types for ISA(PC104) board #4 (e.g. pc104_4=232,232,485,485,...");
 
-static int rp_init(void);
+static int __init rp_init(void);
 static void rp_cleanup_module(void);
 
 module_init(rp_init);
diff --git a/drivers/tty/serial/men_z135_uart.c b/drivers/tty/serial/men_z135_uart.c
index ef89534dd760..e5d3ebab6dae 100644
--- a/drivers/tty/serial/men_z135_uart.c
+++ b/drivers/tty/serial/men_z135_uart.c
@@ -353,7 +353,6 @@ static void men_z135_handle_tx(struct men_z135_port *uart)
 
 	memcpy_toio(port->membase + MEN_Z135_TX_RAM, &xmit->buf[xmit->tail], n);
 	xmit->tail = (xmit->tail + n) & (UART_XMIT_SIZE - 1);
-	mmiowb();
 
 	iowrite32(n & 0x3ff, port->membase + MEN_Z135_TX_CTRL);
 
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index 1b4008d022bf..d22ccb32aa9b 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -248,7 +248,6 @@ static void serial_txx9_initialize(struct uart_port *port)
 	sio_out(up, TXX9_SIFCR, TXX9_SIFCR_SWRST);
 	/* TX4925 BUG WORKAROUND.  Accessing SIOC register
 	 * immediately after soft reset causes bus error. */
-	mmiowb();
 	udelay(1);
 	while ((sio_in(up, TXX9_SIFCR) & TXX9_SIFCR_SWRST) && --tmout)
 		udelay(1);
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 8987cec9549d..ebcadaad89d1 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -473,11 +473,6 @@ static int usb_unbind_interface(struct device *dev)
 		pm_runtime_disable(dev);
 	pm_runtime_set_suspended(dev);
 
-	/* Undo any residual pm_autopm_get_interface_* calls */
-	for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r)
-		usb_autopm_put_interface_no_suspend(intf);
-	atomic_set(&intf->pm_usage_cnt, 0);
-
 	if (!error)
 		usb_autosuspend_device(udev);
 
@@ -1633,7 +1628,6 @@ void usb_autopm_put_interface(struct usb_interface *intf)
 	int			status;
 
 	usb_mark_last_busy(udev);
-	atomic_dec(&intf->pm_usage_cnt);
 	status = pm_runtime_put_sync(&intf->dev);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
@@ -1662,7 +1656,6 @@ void usb_autopm_put_interface_async(struct usb_interface *intf)
 	int			status;
 
 	usb_mark_last_busy(udev);
-	atomic_dec(&intf->pm_usage_cnt);
 	status = pm_runtime_put(&intf->dev);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
@@ -1684,7 +1677,6 @@ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf)
 	struct usb_device	*udev = interface_to_usbdev(intf);
 
 	usb_mark_last_busy(udev);
-	atomic_dec(&intf->pm_usage_cnt);
 	pm_runtime_put_noidle(&intf->dev);
 }
 EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend);
@@ -1715,8 +1707,6 @@ int usb_autopm_get_interface(struct usb_interface *intf)
 	status = pm_runtime_get_sync(&intf->dev);
 	if (status < 0)
 		pm_runtime_put_sync(&intf->dev);
-	else
-		atomic_inc(&intf->pm_usage_cnt);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
 			status);
@@ -1750,8 +1740,6 @@ int usb_autopm_get_interface_async(struct usb_interface *intf)
 	status = pm_runtime_get(&intf->dev);
 	if (status < 0 && status != -EINPROGRESS)
 		pm_runtime_put_noidle(&intf->dev);
-	else
-		atomic_inc(&intf->pm_usage_cnt);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
 			status);
@@ -1775,7 +1763,6 @@ void usb_autopm_get_interface_no_resume(struct usb_interface *intf)
 	struct usb_device	*udev = interface_to_usbdev(intf);
 
 	usb_mark_last_busy(udev);
-	atomic_inc(&intf->pm_usage_cnt);
 	pm_runtime_get_noresume(&intf->dev);
 }
 EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 82239f27c4cc..e844bb7b5676 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -820,9 +820,11 @@ int usb_string(struct usb_device *dev, int index, char *buf, size_t size)
 
 	if (dev->state == USB_STATE_SUSPENDED)
 		return -EHOSTUNREACH;
-	if (size <= 0 || !buf || !index)
+	if (size <= 0 || !buf)
 		return -EINVAL;
 	buf[0] = 0;
+	if (index <= 0 || index >= 256)
+		return -EINVAL;
 	tbuf = kmalloc(256, GFP_NOIO);
 	if (!tbuf)
 		return -ENOMEM;
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
index c9cfb100ecdc..cac991173ac0 100644
--- a/drivers/usb/early/xhci-dbc.c
+++ b/drivers/usb/early/xhci-dbc.c
@@ -533,8 +533,6 @@ static int xdbc_handle_external_reset(void)
 
 	xdbc_mem_init();
 
-	mmiowb();
-
 	ret = xdbc_start();
 	if (ret < 0)
 		goto reset_out;
@@ -587,8 +585,6 @@ static int __init xdbc_early_setup(void)
 
 	xdbc_mem_init();
 
-	mmiowb();
-
 	ret = xdbc_start();
 	if (ret < 0) {
 		writel(0, &xdbc.xdbc_reg->control);
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index baf72f95f0f1..213b52508621 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -979,8 +979,18 @@ static int dummy_udc_start(struct usb_gadget *g,
 	struct dummy_hcd	*dum_hcd = gadget_to_dummy_hcd(g);
 	struct dummy		*dum = dum_hcd->dum;
 
-	if (driver->max_speed == USB_SPEED_UNKNOWN)
+	switch (g->speed) {
+	/* All the speeds we support */
+	case USB_SPEED_LOW:
+	case USB_SPEED_FULL:
+	case USB_SPEED_HIGH:
+	case USB_SPEED_SUPER:
+		break;
+	default:
+		dev_err(dummy_dev(dum_hcd), "Unsupported driver max speed %d\n",
+				driver->max_speed);
 		return -EINVAL;
+	}
 
 	/*
 	 * SLAVE side init ... the layer above hardware, which
@@ -1784,9 +1794,10 @@ static void dummy_timer(struct timer_list *t)
 		/* Bus speed is 500000 bytes/ms, so use a little less */
 		total = 490000;
 		break;
-	default:
+	default:	/* Can't happen */
 		dev_err(dummy_dev(dum_hcd), "bogus device speed\n");
-		return;
+		total = 0;
+		break;
 	}
 
 	/* FIXME if HZ != 1000 this will probably misbehave ... */
@@ -1828,7 +1839,7 @@ restart:
 
 		/* Used up this frame's bandwidth? */
 		if (total <= 0)
-			break;
+			continue;
 
 		/* find the gadget's ep for this request (if configured) */
 		address = usb_pipeendpoint (urb->pipe);
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index d932cc31711e..52e32644a4b2 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -421,8 +421,6 @@ static int xhci_dbc_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	string_length = xhci_dbc_populate_strings(dbc->string);
 	xhci_dbc_init_contexts(xhci, string_length);
 
-	mmiowb();
-
 	xhci_dbc_eps_init(xhci);
 	dbc->state = DS_INITIALIZED;
 
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 6d9fd5f64903..7b306aa22d25 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -314,6 +314,7 @@ static void yurex_disconnect(struct usb_interface *interface)
 	usb_deregister_dev(interface, &yurex_class);
 
 	/* prevent more I/O from starting */
+	usb_poison_urb(dev->urb);
 	mutex_lock(&dev->io_mutex);
 	dev->interface = NULL;
 	mutex_unlock(&dev->io_mutex);
diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index 31b024441938..cc794e25a0b6 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -763,18 +763,16 @@ static void rts51x_suspend_timer_fn(struct timer_list *t)
 		break;
 	case RTS51X_STAT_IDLE:
 	case RTS51X_STAT_SS:
-		usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n",
-			     atomic_read(&us->pusb_intf->pm_usage_cnt),
+		usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n",
 			     atomic_read(&us->pusb_intf->dev.power.usage_count));
 
-		if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) {
+		if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) {
 			usb_stor_dbg(us, "Ready to enter SS state\n");
 			rts51x_set_stat(chip, RTS51X_STAT_SS);
 			/* ignore mass storage interface's children */
 			pm_suspend_ignore_children(&us->pusb_intf->dev, true);
 			usb_autopm_put_interface_async(us->pusb_intf);
-			usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n",
-				     atomic_read(&us->pusb_intf->pm_usage_cnt),
+			usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n",
 				     atomic_read(&us->pusb_intf->dev.power.usage_count));
 		}
 		break;
@@ -807,11 +805,10 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 	int ret;
 
 	if (working_scsi(srb)) {
-		usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n",
-			     atomic_read(&us->pusb_intf->pm_usage_cnt),
+		usb_stor_dbg(us, "working scsi, power.usage:%d\n",
 			     atomic_read(&us->pusb_intf->dev.power.usage_count));
 
-		if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) {
+		if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) {
 			ret = usb_autopm_get_interface(us->pusb_intf);
 			usb_stor_dbg(us, "working scsi, ret=%d\n", ret);
 		}
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 97b09a42a10c..dbfb2f24d71e 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -361,16 +361,10 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu)
 	}
 
 	if (usb_endpoint_xfer_isoc(epd)) {
-		/* validate packet size and number of packets */
-		unsigned int maxp, packets, bytes;
-
-		maxp = usb_endpoint_maxp(epd);
-		maxp *= usb_endpoint_maxp_mult(epd);
-		bytes = pdu->u.cmd_submit.transfer_buffer_length;
-		packets = DIV_ROUND_UP(bytes, maxp);
-
+		/* validate number of packets */
 		if (pdu->u.cmd_submit.number_of_packets < 0 ||
-		    pdu->u.cmd_submit.number_of_packets > packets) {
+		    pdu->u.cmd_submit.number_of_packets >
+		    USBIP_MAX_ISO_PACKETS) {
 			dev_err(&sdev->udev->dev,
 				"CMD_SUBMIT: isoc invalid num packets %d\n",
 				pdu->u.cmd_submit.number_of_packets);
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index bf8afe9b5883..8be857a4fa13 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -121,6 +121,13 @@ extern struct device_attribute dev_attr_usbip_debug;
 #define USBIP_DIR_OUT	0x00
 #define USBIP_DIR_IN	0x01
 
+/*
+ * Arbitrary limit for the maximum number of isochronous packets in an URB,
+ * compare for example the uhci_submit_isochronous function in
+ * drivers/usb/host/uhci-q.c
+ */
+#define USBIP_MAX_ISO_PACKETS 1024
+
 /**
  * struct usbip_header_basic - data pertinent to every request
  * @command: the usbip request type
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index ba906876cc45..9e529cc2b4ff 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -464,7 +464,8 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+	if (efi_enabled(EFI_BOOT) &&
+	    !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
 		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
 		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
 			pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c
index 0f4ecfcdb549..a9fb77585272 100644
--- a/drivers/w1/masters/ds2490.c
+++ b/drivers/w1/masters/ds2490.c
@@ -1016,15 +1016,15 @@ static int ds_probe(struct usb_interface *intf,
 	/* alternative 3, 1ms interrupt (greatly speeds search), 64 byte bulk */
 	alt = 3;
 	err = usb_set_interface(dev->udev,
-		intf->altsetting[alt].desc.bInterfaceNumber, alt);
+		intf->cur_altsetting->desc.bInterfaceNumber, alt);
 	if (err) {
 		dev_err(&dev->udev->dev, "Failed to set alternative setting %d "
 			"for %d interface: err=%d.\n", alt,
-			intf->altsetting[alt].desc.bInterfaceNumber, err);
+			intf->cur_altsetting->desc.bInterfaceNumber, err);
 		goto err_out_clear;
 	}
 
-	iface_desc = &intf->altsetting[alt];
+	iface_desc = intf->cur_altsetting;
 	if (iface_desc->desc.bNumEndpoints != NUM_EP-1) {
 		pr_info("Num endpoints=%d. It is not DS9490R.\n",
 			iface_desc->desc.bNumEndpoints);
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index e8bd9887c566..e221e47396ab 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -161,7 +161,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd)
 		timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR);
 
 	timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) -
-		    arch_counter_get_cntvct();
+		    arch_timer_read_counter();
 
 	do_div(timeleft, gwdt->clk);
 
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 117e76b2f939..084e45882c73 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1687,7 +1687,6 @@ void __init xen_init_IRQ(void)
 
 #ifdef CONFIG_X86
 	if (xen_pv_domain()) {
-		irq_ctx_init(smp_processor_id());
 		if (xen_initial_domain())
 			pci_xen_initial_domain();
 	}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 24615c76c1d0..bb28e2ead679 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -264,7 +264,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bio_for_each_segment_all(bvec, &bio, i, iter_all) {
 		if (should_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		if (!bio_flagged(&bio, BIO_NO_PAGE_REF))
+			put_page(bvec->bv_page);
 	}
 
 	if (unlikely(bio.bi_status))
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 82fdda8ff5ab..2973608824ec 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6783,7 +6783,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	u64 extent_start = 0;
 	u64 extent_end = 0;
 	u64 objectid = btrfs_ino(inode);
-	u8 extent_type;
+	int extent_type = -1;
 	struct btrfs_path *path = NULL;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *item;
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index d09b6cdb785a..b283d3a6e837 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -205,28 +205,17 @@ static struct root_entry *lookup_root_entry(struct rb_root *root, u64 objectid)
 #ifdef CONFIG_STACKTRACE
 static void __save_stack_trace(struct ref_action *ra)
 {
-	struct stack_trace stack_trace;
-
-	stack_trace.max_entries = MAX_TRACE;
-	stack_trace.nr_entries = 0;
-	stack_trace.entries = ra->trace;
-	stack_trace.skip = 2;
-	save_stack_trace(&stack_trace);
-	ra->trace_len = stack_trace.nr_entries;
+	ra->trace_len = stack_trace_save(ra->trace, MAX_TRACE, 2);
 }
 
 static void __print_stack_trace(struct btrfs_fs_info *fs_info,
 				struct ref_action *ra)
 {
-	struct stack_trace trace;
-
 	if (ra->trace_len == 0) {
 		btrfs_err(fs_info, "  ref-verify: no stacktrace");
 		return;
 	}
-	trace.nr_entries = ra->trace_len;
-	trace.entries = ra->trace;
-	print_stack_trace(&trace, 2);
+	stack_trace_print(ra->trace, ra->trace_len, 2);
 }
 #else
 static void inline __save_stack_trace(struct ref_action *ra)
diff --git a/fs/inode.c b/fs/inode.c
index e9d97add2b36..9a453f3637f8 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1817,8 +1817,13 @@ int file_remove_privs(struct file *file)
 	int kill;
 	int error = 0;
 
-	/* Fast path for nothing security related */
-	if (IS_NOSEC(inode))
+	/*
+	 * Fast path for nothing security related.
+	 * As well for non-regular files, e.g. blkdev inodes.
+	 * For example, blkdev_write_iter() might get here
+	 * trying to remove privs which it is not allowed to.
+	 */
+	if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
 		return 0;
 
 	kill = dentry_needs_remove_privs(dentry);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0e9fb2cb1984..84efb8956734 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4,15 +4,28 @@
  * supporting fast/efficient IO.
  *
  * A note on the read/write ordering memory barriers that are matched between
- * the application and kernel side. When the application reads the CQ ring
- * tail, it must use an appropriate smp_rmb() to order with the smp_wmb()
- * the kernel uses after writing the tail. Failure to do so could cause a
- * delay in when the application notices that completion events available.
- * This isn't a fatal condition. Likewise, the application must use an
- * appropriate smp_wmb() both before writing the SQ tail, and after writing
- * the SQ tail. The first one orders the sqe writes with the tail write, and
- * the latter is paired with the smp_rmb() the kernel will issue before
- * reading the SQ tail on submission.
+ * the application and kernel side.
+ *
+ * After the application reads the CQ ring tail, it must use an
+ * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
+ * before writing the tail (using smp_load_acquire to read the tail will
+ * do). It also needs a smp_mb() before updating CQ head (ordering the
+ * entry load(s) with the head store), pairing with an implicit barrier
+ * through a control-dependency in io_get_cqring (smp_store_release to
+ * store head will do). Failure to do so could lead to reading invalid
+ * CQ entries.
+ *
+ * Likewise, the application must use an appropriate smp_wmb() before
+ * writing the SQ tail (ordering SQ entry stores with the tail store),
+ * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
+ * to store the tail will do). And it needs a barrier ordering the SQ
+ * head load before writing new SQ entries (smp_load_acquire to read
+ * head will do).
+ *
+ * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
+ * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
+ * updating the SQ tail; a full memory barrier smp_mb() is needed
+ * between.
  *
  * Also see the examples in the liburing library:
  *
@@ -70,20 +83,108 @@ struct io_uring {
 	u32 tail ____cacheline_aligned_in_smp;
 };
 
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_SQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_sqring_offsets when calling io_uring_setup.
+ */
 struct io_sq_ring {
+	/*
+	 * Head and tail offsets into the ring; the offsets need to be
+	 * masked to get valid indices.
+	 *
+	 * The kernel controls head and the application controls tail.
+	 */
 	struct io_uring		r;
+	/*
+	 * Bitmask to apply to head and tail offsets (constant, equals
+	 * ring_entries - 1)
+	 */
 	u32			ring_mask;
+	/* Ring size (constant, power of 2) */
 	u32			ring_entries;
+	/*
+	 * Number of invalid entries dropped by the kernel due to
+	 * invalid index stored in array
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application (i.e. get number of "new events" by comparing to
+	 * cached value).
+	 *
+	 * After a new SQ head value was read by the application this
+	 * counter includes all submissions that were dropped reaching
+	 * the new SQ head (and possibly more).
+	 */
 	u32			dropped;
+	/*
+	 * Runtime flags
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application.
+	 *
+	 * The application needs a full memory barrier before checking
+	 * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
+	 */
 	u32			flags;
+	/*
+	 * Ring buffer of indices into array of io_uring_sqe, which is
+	 * mmapped by the application using the IORING_OFF_SQES offset.
+	 *
+	 * This indirection could e.g. be used to assign fixed
+	 * io_uring_sqe entries to operations and only submit them to
+	 * the queue when needed.
+	 *
+	 * The kernel modifies neither the indices array nor the entries
+	 * array.
+	 */
 	u32			array[];
 };
 
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_CQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_cqring_offsets when calling io_uring_setup.
+ */
 struct io_cq_ring {
+	/*
+	 * Head and tail offsets into the ring; the offsets need to be
+	 * masked to get valid indices.
+	 *
+	 * The application controls head and the kernel tail.
+	 */
 	struct io_uring		r;
+	/*
+	 * Bitmask to apply to head and tail offsets (constant, equals
+	 * ring_entries - 1)
+	 */
 	u32			ring_mask;
+	/* Ring size (constant, power of 2) */
 	u32			ring_entries;
+	/*
+	 * Number of completion events lost because the queue was full;
+	 * this should be avoided by the application by making sure
+	 * there are not more requests pending thatn there is space in
+	 * the completion queue.
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application (i.e. get number of "new events" by comparing to
+	 * cached value).
+	 *
+	 * As completion events come in out of order this counter is not
+	 * ordered with any other data.
+	 */
 	u32			overflow;
+	/*
+	 * Ring buffer of completion events.
+	 *
+	 * The kernel writes completion events fresh every time they are
+	 * produced, so the application is allowed to modify pending
+	 * entries.
+	 */
 	struct io_uring_cqe	cqes[];
 };
 
@@ -221,7 +322,7 @@ struct io_kiocb {
 	struct list_head	list;
 	unsigned int		flags;
 	refcount_t		refs;
-#define REQ_F_FORCE_NONBLOCK	1	/* inline submission attempt */
+#define REQ_F_NOWAIT		1	/* must not punt to workers */
 #define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
 #define REQ_F_FIXED_FILE	4	/* ctx owns file */
 #define REQ_F_SEQ_PREV		8	/* sequential with previous */
@@ -317,12 +418,6 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 		/* order cqe stores with ring update */
 		smp_store_release(&ring->r.tail, ctx->cached_cq_tail);
 
-		/*
-		 * Write sider barrier of tail update, app has read side. See
-		 * comment at the top of this file.
-		 */
-		smp_wmb();
-
 		if (wq_has_sleeper(&ctx->cq_wait)) {
 			wake_up_interruptible(&ctx->cq_wait);
 			kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
@@ -336,8 +431,11 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	unsigned tail;
 
 	tail = ctx->cached_cq_tail;
-	/* See comment at the top of the file */
-	smp_rmb();
+	/*
+	 * writes to the cq entry need to come after reading head; the
+	 * control dependency is enough as we're using WRITE_ONCE to
+	 * fill the cq entry
+	 */
 	if (tail - READ_ONCE(ring->r.head) == ring->ring_entries)
 		return NULL;
 
@@ -774,10 +872,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
 	if (unlikely(ret))
 		return ret;
-	if (force_nonblock) {
+
+	/* don't allow async punt if RWF_NOWAIT was requested */
+	if (kiocb->ki_flags & IOCB_NOWAIT)
+		req->flags |= REQ_F_NOWAIT;
+
+	if (force_nonblock)
 		kiocb->ki_flags |= IOCB_NOWAIT;
-		req->flags |= REQ_F_FORCE_NONBLOCK;
-	}
+
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) ||
 		    !kiocb->ki_filp->f_op->iopoll)
@@ -1436,8 +1538,7 @@ restart:
 		struct sqe_submit *s = &req->submit;
 		const struct io_uring_sqe *sqe = s->sqe;
 
-		/* Ensure we clear previously set forced non-block flag */
-		req->flags &= ~REQ_F_FORCE_NONBLOCK;
+		/* Ensure we clear previously set non-block flag */
 		req->rw.ki_flags &= ~IOCB_NOWAIT;
 
 		ret = 0;
@@ -1467,10 +1568,11 @@ restart:
 					break;
 				cond_resched();
 			} while (1);
-
-			/* drop submission reference */
-			io_put_req(req);
 		}
+
+		/* drop submission reference */
+		io_put_req(req);
+
 		if (ret) {
 			io_cqring_add_event(ctx, sqe->user_data, ret, 0);
 			io_put_req(req);
@@ -1623,7 +1725,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 		goto out;
 
 	ret = __io_submit_sqe(ctx, req, s, true);
-	if (ret == -EAGAIN) {
+	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
 
 		sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
@@ -1697,24 +1799,10 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
 		 * write new data to them.
 		 */
 		smp_store_release(&ring->r.head, ctx->cached_sq_head);
-
-		/*
-		 * write side barrier of head update, app has read side. See
-		 * comment at the top of this file
-		 */
-		smp_wmb();
 	}
 }
 
 /*
- * Undo last io_get_sqring()
- */
-static void io_drop_sqring(struct io_ring_ctx *ctx)
-{
-	ctx->cached_sq_head--;
-}
-
-/*
  * Fetch an sqe, if one is available. Note that s->sqe will point to memory
  * that is mapped by userspace. This means that care needs to be taken to
  * ensure that reads are stable, as we cannot rely on userspace always
@@ -1736,8 +1824,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	 *    though the application is the one updating it.
 	 */
 	head = ctx->cached_sq_head;
-	/* See comment at the top of this file */
-	smp_rmb();
 	/* make sure SQ entry isn't read before tail */
 	if (head == smp_load_acquire(&ring->r.tail))
 		return false;
@@ -1753,8 +1839,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	/* drop invalid entries */
 	ctx->cached_sq_head++;
 	ring->dropped++;
-	/* See comment at the top of this file */
-	smp_wmb();
 	return false;
 }
 
@@ -1878,13 +1962,11 @@ static int io_sq_thread(void *data)
 				finish_wait(&ctx->sqo_wait, &wait);
 
 				ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
-				smp_wmb();
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
 			ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
-			smp_wmb();
 		}
 
 		i = 0;
@@ -1929,7 +2011,7 @@ static int io_sq_thread(void *data)
 static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
 	struct io_submit_state state, *statep = NULL;
-	int i, ret = 0, submit = 0;
+	int i, submit = 0;
 
 	if (to_submit > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, ctx, to_submit);
@@ -1938,6 +2020,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 
 	for (i = 0; i < to_submit; i++) {
 		struct sqe_submit s;
+		int ret;
 
 		if (!io_get_sqring(ctx, &s))
 			break;
@@ -1945,21 +2028,18 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		s.has_user = true;
 		s.needs_lock = false;
 		s.needs_fixed_file = false;
+		submit++;
 
 		ret = io_submit_sqe(ctx, &s, statep);
-		if (ret) {
-			io_drop_sqring(ctx);
-			break;
-		}
-
-		submit++;
+		if (ret)
+			io_cqring_add_event(ctx, s.sqe->user_data, ret, 0);
 	}
 	io_commit_sqring(ctx);
 
 	if (statep)
 		io_submit_state_end(statep);
 
-	return submit ? submit : ret;
+	return submit;
 }
 
 static unsigned io_cqring_events(struct io_cq_ring *ring)
@@ -2240,10 +2320,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 	mmgrab(current->mm);
 	ctx->sqo_mm = current->mm;
 
-	ret = -EINVAL;
-	if (!cpu_possible(p->sq_thread_cpu))
-		goto err;
-
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		ret = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
@@ -2254,11 +2330,11 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			ctx->sq_thread_idle = HZ;
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
-			int cpu;
+			int cpu = array_index_nospec(p->sq_thread_cpu,
+							nr_cpu_ids);
 
-			cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS);
 			ret = -EINVAL;
-			if (!cpu_possible(p->sq_thread_cpu))
+			if (!cpu_possible(cpu))
 				goto err;
 
 			ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread,
@@ -2321,8 +2397,12 @@ static int io_account_mem(struct user_struct *user, unsigned long nr_pages)
 
 static void io_mem_free(void *ptr)
 {
-	struct page *page = virt_to_head_page(ptr);
+	struct page *page;
+
+	if (!ptr)
+		return;
 
+	page = virt_to_head_page(ptr);
 	if (put_page_testzero(page))
 		free_compound_page(page);
 }
@@ -2363,7 +2443,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
 
 		if (ctx->account_mem)
 			io_unaccount_mem(ctx->user, imu->nr_bvecs);
-		kfree(imu->bvec);
+		kvfree(imu->bvec);
 		imu->nr_bvecs = 0;
 	}
 
@@ -2455,9 +2535,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 		if (!pages || nr_pages > got_pages) {
 			kfree(vmas);
 			kfree(pages);
-			pages = kmalloc_array(nr_pages, sizeof(struct page *),
+			pages = kvmalloc_array(nr_pages, sizeof(struct page *),
 						GFP_KERNEL);
-			vmas = kmalloc_array(nr_pages,
+			vmas = kvmalloc_array(nr_pages,
 					sizeof(struct vm_area_struct *),
 					GFP_KERNEL);
 			if (!pages || !vmas) {
@@ -2469,7 +2549,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			got_pages = nr_pages;
 		}
 
-		imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+		imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
 						GFP_KERNEL);
 		ret = -ENOMEM;
 		if (!imu->bvec) {
@@ -2508,6 +2588,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			}
 			if (ctx->account_mem)
 				io_unaccount_mem(ctx->user, nr_pages);
+			kvfree(imu->bvec);
 			goto err;
 		}
 
@@ -2530,12 +2611,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ctx->nr_user_bufs++;
 	}
-	kfree(pages);
-	kfree(vmas);
+	kvfree(pages);
+	kvfree(vmas);
 	return 0;
 err:
-	kfree(pages);
-	kfree(vmas);
+	kvfree(pages);
+	kvfree(vmas);
 	io_sqe_buffer_unregister(ctx);
 	return ret;
 }
@@ -2573,7 +2654,10 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	__poll_t mask = 0;
 
 	poll_wait(file, &ctx->cq_wait, wait);
-	/* See comment at the top of this file */
+	/*
+	 * synchronizes with barrier from wq_has_sleeper call in
+	 * io_commit_cqring
+	 */
 	smp_rmb();
 	if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head !=
 	    ctx->sq_ring->ring_entries)
@@ -2687,24 +2771,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		mutex_lock(&ctx->uring_lock);
 		submitted = io_ring_submit(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
-
-		if (submitted < 0)
-			goto out_ctx;
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
 		unsigned nr_events = 0;
 
 		min_complete = min(min_complete, ctx->cq_entries);
 
-		/*
-		 * The application could have included the 'to_submit' count
-		 * in how many events it wanted to wait for. If we failed to
-		 * submit the desired count, we may need to adjust the number
-		 * of events to poll/wait for.
-		 */
-		if (submitted < to_submit)
-			min_complete = min_t(unsigned, submitted, min_complete);
-
 		if (ctx->flags & IORING_SETUP_IOPOLL) {
 			mutex_lock(&ctx->uring_lock);
 			ret = io_iopoll_check(ctx, &nr_events, min_complete);
@@ -2750,17 +2822,12 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 		return -EOVERFLOW;
 
 	ctx->sq_sqes = io_mem_alloc(size);
-	if (!ctx->sq_sqes) {
-		io_mem_free(ctx->sq_ring);
+	if (!ctx->sq_sqes)
 		return -ENOMEM;
-	}
 
 	cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
-	if (!cq_ring) {
-		io_mem_free(ctx->sq_ring);
-		io_mem_free(ctx->sq_sqes);
+	if (!cq_ring)
 		return -ENOMEM;
-	}
 
 	ctx->cq_ring = cq_ring;
 	cq_ring->ring_mask = p->cq_entries - 1;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 6b9c27548997..63c6bb1f8c4d 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -346,10 +346,16 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	__kernel_fsid_t fsid = {};
 
 	fsnotify_foreach_obj_type(type) {
+		struct fsnotify_mark_connector *conn;
+
 		if (!fsnotify_iter_should_report_type(iter_info, type))
 			continue;
 
-		fsid = iter_info->marks[type]->connector->fsid;
+		conn = READ_ONCE(iter_info->marks[type]->connector);
+		/* Mark is just getting destroyed or created? */
+		if (!conn)
+			continue;
+		fsid = conn->fsid;
 		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
 			continue;
 		return fsid;
@@ -408,8 +414,12 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 			return 0;
 	}
 
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID))
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
 		fsid = fanotify_get_fsid(iter_info);
+		/* Racing with mark destruction or creation? */
+		if (!fsid.val[0] && !fsid.val[1])
+			return 0;
+	}
 
 	event = fanotify_alloc_event(group, inode, mask, data, data_type,
 				     &fsid);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d593d4269561..22acb0a79b53 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -239,13 +239,13 @@ static void fsnotify_drop_object(unsigned int type, void *objp)
 
 void fsnotify_put_mark(struct fsnotify_mark *mark)
 {
-	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector);
 	void *objp = NULL;
 	unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
 	bool free_conn = false;
 
 	/* Catch marks that were actually never attached to object */
-	if (!mark->connector) {
+	if (!conn) {
 		if (refcount_dec_and_test(&mark->refcnt))
 			fsnotify_final_mark_destroy(mark);
 		return;
@@ -255,10 +255,9 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	 * We have to be careful so that traversals of obj_list under lock can
 	 * safely grab mark reference.
 	 */
-	if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+	if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock))
 		return;
 
-	conn = mark->connector;
 	hlist_del_init_rcu(&mark->obj_list);
 	if (hlist_empty(&conn->list)) {
 		objp = fsnotify_detach_connector_from_object(conn, &type);
@@ -266,7 +265,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	} else {
 		__fsnotify_recalc_mask(conn);
 	}
-	mark->connector = NULL;
+	WRITE_ONCE(mark->connector, NULL);
 	spin_unlock(&conn->lock);
 
 	fsnotify_drop_object(type, objp);
@@ -620,7 +619,7 @@ restart:
 	/* mark should be the last entry.  last is the current last entry */
 	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
 added:
-	mark->connector = conn;
+	WRITE_ONCE(mark->connector, conn);
 out_err:
 	spin_unlock(&conn->lock);
 	spin_unlock(&mark->lock);
@@ -808,6 +807,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	refcount_set(&mark->refcnt, 1);
 	fsnotify_get_group(group);
 	mark->group = group;
+	WRITE_ONCE(mark->connector, NULL);
 }
 
 /*
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6a803a0b75df..f179568b4c76 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -407,7 +407,6 @@ static void unlock_trace(struct task_struct *task)
 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
 {
-	struct stack_trace trace;
 	unsigned long *entries;
 	int err;
 
@@ -430,20 +429,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 	if (!entries)
 		return -ENOMEM;
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
-	trace.entries		= entries;
-	trace.skip		= 0;
-
 	err = lock_trace(task);
 	if (!err) {
-		unsigned int i;
+		unsigned int i, nr_entries;
 
-		save_stack_trace_tsk(task, &trace);
+		nr_entries = stack_trace_save_tsk(task, entries,
+						  MAX_STACK_TRACE_DEPTH, 0);
 
-		for (i = 0; i < trace.nr_entries; i++) {
+		for (i = 0; i < nr_entries; i++) {
 			seq_printf(m, "[<0>] %pB\n", (void *)entries[i]);
 		}
+
 		unlock_trace(task);
 	}
 	kfree(entries);
@@ -489,10 +485,9 @@ static int lstats_show_proc(struct seq_file *m, void *v)
 				   lr->count, lr->time, lr->max);
 			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 				unsigned long bt = lr->backtrace[q];
+
 				if (!bt)
 					break;
-				if (bt == ULONG_MAX)
-					break;
 				seq_printf(m, " %ps", (void *)bt);
 			}
 			seq_putc(m, '\n');
diff --git a/fs/super.c b/fs/super.c
index 583a0124bc39..2739f57515f8 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1467,11 +1467,6 @@ int vfs_get_tree(struct fs_context *fc)
 	struct super_block *sb;
 	int error;
 
-	if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) {
-		errorf(fc, "Filesystem requires source device");
-		return -ENOENT;
-	}
-
 	if (fc->root)
 		return -EBUSY;
 
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 1fd3011ea623..7fd4802222b8 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -229,7 +229,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode)
 	case UFS_UID_44BSD:
 		return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid);
 	case UFS_UID_EFT:
-		if (inode->ui_u1.oldids.ui_suid == 0xFFFF)
+		if (inode->ui_u1.oldids.ui_sgid == 0xFFFF)
 			return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid);
 		/* Fall through */
 	default:
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0300374101cd..2a462cf4eaa9 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -91,8 +91,8 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev,
 bool acpi_dev_found(const char *hid);
 bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
 
-const char *
-acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv);
+struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv);
 
 #ifdef CONFIG_ACPI
 
@@ -687,6 +687,10 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 		adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set);
 }
 
+static inline void acpi_dev_put(struct acpi_device *adev)
+{
+	put_device(&adev->dev);
+}
 #else	/* CONFIG_ACPI */
 
 static inline int register_acpi_bus_type(void *bus) { return 0; }
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 24dbb4e742a6..3b1b1d0e4c33 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20190215
+#define ACPI_CA_VERSION                 0x20190405
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 65cc9cbf1141..d568128025df 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -66,14 +66,14 @@
  ******************************************************************************/
 
 struct acpi_table_header {
-	char signature[ACPI_NAME_SIZE];	/* ASCII table signature */
+	char signature[ACPI_NAMESEG_SIZE];	/* ASCII table signature */
 	u32 length;		/* Length of table in bytes, including this header */
 	u8 revision;		/* ACPI Specification minor version number */
 	u8 checksum;		/* To make sum of entire table == 0 */
 	char oem_id[ACPI_OEM_ID_SIZE];	/* ASCII OEM identification */
 	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE];	/* ASCII OEM table identification */
 	u32 oem_revision;	/* OEM revision number */
-	char asl_compiler_id[ACPI_NAME_SIZE];	/* ASCII ASL compiler vendor ID */
+	char asl_compiler_id[ACPI_NAMESEG_SIZE];	/* ASCII ASL compiler vendor ID */
 	u32 asl_compiler_revision;	/* ASL compiler version */
 };
 
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index f73382e82c26..ad6892a24015 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -375,7 +375,7 @@ typedef u64 acpi_physical_address;
 
 /* Names within the namespace are 4 bytes long */
 
-#define ACPI_NAME_SIZE                  4
+#define ACPI_NAMESEG_SIZE               4	/* Fixed by ACPI spec */
 #define ACPI_PATH_SEGMENT_LENGTH        5	/* 4 chars for name + 1 char for separator */
 #define ACPI_PATH_SEPARATOR             '.'
 
@@ -515,11 +515,11 @@ typedef u64 acpi_integer;
 /* Optimizations for 4-character (32-bit) acpi_name manipulation */
 
 #ifndef ACPI_MISALIGNMENT_NOT_SUPPORTED
-#define ACPI_COMPARE_NAME(a,b)          (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
-#define ACPI_MOVE_NAME(dest,src)        (*ACPI_CAST_PTR (u32, (dest)) = *ACPI_CAST_PTR (u32, (src)))
+#define ACPI_COMPARE_NAMESEG(a,b)       (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
+#define ACPI_COPY_NAMESEG(dest,src)     (*ACPI_CAST_PTR (u32, (dest)) = *ACPI_CAST_PTR (u32, (src)))
 #else
-#define ACPI_COMPARE_NAME(a,b)          (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAME_SIZE))
-#define ACPI_MOVE_NAME(dest,src)        (strncpy (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAME_SIZE))
+#define ACPI_COMPARE_NAMESEG(a,b)       (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAMESEG_SIZE))
+#define ACPI_COPY_NAMESEG(dest,src)     (strncpy (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAMESEG_SIZE))
 #endif
 
 /* Support for the special RSDP signature (8 characters) */
@@ -529,7 +529,7 @@ typedef u64 acpi_integer;
 
 /* Support for OEMx signature (x can be any character) */
 #define ACPI_IS_OEM_SIG(a)        (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_OEM_NAME, 3) &&\
-	 strnlen (a, ACPI_NAME_SIZE) == ACPI_NAME_SIZE)
+	 strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE)
 
 /*
  * Algorithm to obtain access bit width.
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index fcb61b4659b3..8666fe7f35d7 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -23,7 +23,9 @@
  *
  * Return:
  * 0 - On success
- * <0 - On error
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Operation not supported
  */
 static inline int
 arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
@@ -85,7 +87,9 @@ out_pagefault_enable:
  *
  * Return:
  * 0 - On success
- * <0 - On error
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG)
  */
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 303871651f8a..8f3bf95a36d1 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -19,12 +19,9 @@
 #include <asm-generic/iomap.h>
 #endif
 
+#include <asm/mmiowb.h>
 #include <asm-generic/pci_iomap.h>
 
-#ifndef mmiowb
-#define mmiowb() do {} while (0)
-#endif
-
 #ifndef __io_br
 #define __io_br()      barrier()
 #endif
@@ -49,7 +46,7 @@
 
 /* serialize device access against a spin_unlock, usually handled there. */
 #ifndef __io_aw
-#define __io_aw()      barrier()
+#define __io_aw()      mmiowb_set_pending()
 #endif
 
 #ifndef __io_pbw
diff --git a/include/asm-generic/mmiowb.h b/include/asm-generic/mmiowb.h
new file mode 100644
index 000000000000..9439ff037b2d
--- /dev/null
+++ b/include/asm-generic/mmiowb.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_MMIOWB_H
+#define __ASM_GENERIC_MMIOWB_H
+
+/*
+ * Generic implementation of mmiowb() tracking for spinlocks.
+ *
+ * If your architecture doesn't ensure that writes to an I/O peripheral
+ * within two spinlocked sections on two different CPUs are seen by the
+ * peripheral in the order corresponding to the lock handover, then you
+ * need to follow these FIVE easy steps:
+ *
+ * 	1. Implement mmiowb() (and arch_mmiowb_state() if you're fancy)
+ *	   in asm/mmiowb.h, then #include this file
+ *	2. Ensure your I/O write accessors call mmiowb_set_pending()
+ *	3. Select ARCH_HAS_MMIOWB
+ *	4. Untangle the resulting mess of header files
+ *	5. Complain to your architects
+ */
+#ifdef CONFIG_MMIOWB
+
+#include <linux/compiler.h>
+#include <asm-generic/mmiowb_types.h>
+
+#ifndef arch_mmiowb_state
+#include <asm/percpu.h>
+#include <asm/smp.h>
+
+DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state);
+#define __mmiowb_state()	this_cpu_ptr(&__mmiowb_state)
+#else
+#define __mmiowb_state()	arch_mmiowb_state()
+#endif	/* arch_mmiowb_state */
+
+static inline void mmiowb_set_pending(void)
+{
+	struct mmiowb_state *ms = __mmiowb_state();
+	ms->mmiowb_pending = ms->nesting_count;
+}
+
+static inline void mmiowb_spin_lock(void)
+{
+	struct mmiowb_state *ms = __mmiowb_state();
+	ms->nesting_count++;
+}
+
+static inline void mmiowb_spin_unlock(void)
+{
+	struct mmiowb_state *ms = __mmiowb_state();
+
+	if (unlikely(ms->mmiowb_pending)) {
+		ms->mmiowb_pending = 0;
+		mmiowb();
+	}
+
+	ms->nesting_count--;
+}
+#else
+#define mmiowb_set_pending()		do { } while (0)
+#define mmiowb_spin_lock()		do { } while (0)
+#define mmiowb_spin_unlock()		do { } while (0)
+#endif	/* CONFIG_MMIOWB */
+#endif	/* __ASM_GENERIC_MMIOWB_H */
diff --git a/include/asm-generic/mmiowb_types.h b/include/asm-generic/mmiowb_types.h
new file mode 100644
index 000000000000..8eb0095655e7
--- /dev/null
+++ b/include/asm-generic/mmiowb_types.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_MMIOWB_TYPES_H
+#define __ASM_GENERIC_MMIOWB_TYPES_H
+
+#include <linux/types.h>
+
+struct mmiowb_state {
+	u16	nesting_count;
+	u16	mmiowb_pending;
+};
+
+#endif	/* __ASM_GENERIC_MMIOWB_TYPES_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index fa782fba51ee..75d9d68a6de7 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1126,6 +1126,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
+extern void __init pgd_cache_init(void);
+
 #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
 static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
 {
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
deleted file mode 100644
index 93e67a055a4d..000000000000
--- a/include/asm-generic/rwsem.h
+++ /dev/null
@@ -1,140 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_RWSEM_H
-#define _ASM_GENERIC_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#ifdef __KERNEL__
-
-/*
- * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
- * Adapted largely from include/asm-i386/rwsem.h
- * by Paul Mackerras <paulus@samba.org>.
- */
-
-/*
- * the semaphore definition
- */
-#ifdef CONFIG_64BIT
-# define RWSEM_ACTIVE_MASK		0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK		0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-	}
-
-	return 0;
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
-		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-					     &sem->count);
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-					     &sem->count);
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	return 0;
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_dec_return_release(&sem->count);
-	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
-						    &sem->count) < 0))
-		rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	/*
-	 * When downgrading from exclusive to shared ownership,
-	 * anything inside the write-locked region cannot leak
-	 * into the read side. In contrast, anything in the
-	 * read-locked region is ok to be re-ordered into the
-	 * write side. As such, rely on RELEASE semantics.
-	 */
-	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
-	if (tmp < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-#endif	/* __KERNEL__ */
-#endif	/* _ASM_GENERIC_RWSEM_H */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d79abca81a52..d1779d442aa5 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -77,6 +77,20 @@ static inline int arch_is_kernel_data(unsigned long addr)
 }
 #endif
 
+/*
+ * Check if an address is part of freed initmem. This is needed on architectures
+ * with virt == phys kernel mapping, for code that wants to check if an address
+ * is part of a static object within [_stext, _end]. After initmem is freed,
+ * memory can be allocated from it, and such allocations would then have
+ * addresses within the range [_stext, _end].
+ */
+#ifndef arch_is_kernel_initmem_freed
+static inline int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+	return 0;
+}
+#endif
+
 /**
  * memory_contains - checks if an object is contained within a memory region
  * @begin: virtual address of the beginning of the memory region
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 6be86c1c5c58..480e5b2a5748 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -19,9 +19,140 @@
 #include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or switching
+ * the loaded mm.
+ */
+#ifndef nmi_uaccess_okay
+# define nmi_uaccess_okay() true
+#endif
 
 #ifdef CONFIG_MMU
 
+/*
+ * Generic MMU-gather implementation.
+ *
+ * The mmu_gather data structure is used by the mm code to implement the
+ * correct and efficient ordering of freeing pages and TLB invalidations.
+ *
+ * This correct ordering is:
+ *
+ *  1) unhook page
+ *  2) TLB invalidate page
+ *  3) free page
+ *
+ * That is, we must never free a page before we have ensured there are no live
+ * translations left to it. Otherwise it might be possible to observe (or
+ * worse, change) the page content after it has been reused.
+ *
+ * The mmu_gather API consists of:
+ *
+ *  - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ *
+ *    Finish in particular will issue a (final) TLB invalidate and free
+ *    all (remaining) queued pages.
+ *
+ *  - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
+ *
+ *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
+ *    there's large holes between the VMAs.
+ *
+ *  - tlb_remove_page() / __tlb_remove_page()
+ *  - tlb_remove_page_size() / __tlb_remove_page_size()
+ *
+ *    __tlb_remove_page_size() is the basic primitive that queues a page for
+ *    freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
+ *    boolean indicating if the queue is (now) full and a call to
+ *    tlb_flush_mmu() is required.
+ *
+ *    tlb_remove_page() and tlb_remove_page_size() imply the call to
+ *    tlb_flush_mmu() when required and has no return value.
+ *
+ *  - tlb_change_page_size()
+ *
+ *    call before __tlb_remove_page*() to set the current page-size; implies a
+ *    possible tlb_flush_mmu() call.
+ *
+ *  - tlb_flush_mmu() / tlb_flush_mmu_tlbonly()
+ *
+ *    tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
+ *                              related state, like the range)
+ *
+ *    tlb_flush_mmu() - in addition to the above TLB invalidate, also frees
+ *			whatever pages are still batched.
+ *
+ *  - mmu_gather::fullmm
+ *
+ *    A flag set by tlb_gather_mmu() to indicate we're going to free
+ *    the entire mm; this allows a number of optimizations.
+ *
+ *    - We can ignore tlb_{start,end}_vma(); because we don't
+ *      care about ranges. Everything will be shot down.
+ *
+ *    - (RISC) architectures that use ASIDs can cycle to a new ASID
+ *      and delay the invalidation until ASID space runs out.
+ *
+ *  - mmu_gather::need_flush_all
+ *
+ *    A flag that can be set by the arch code if it wants to force
+ *    flush the entire TLB irrespective of the range. For instance
+ *    x86-PAE needs this when changing top-level entries.
+ *
+ * And allows the architecture to provide and implement tlb_flush():
+ *
+ * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
+ * use of:
+ *
+ *  - mmu_gather::start / mmu_gather::end
+ *
+ *    which provides the range that needs to be flushed to cover the pages to
+ *    be freed.
+ *
+ *  - mmu_gather::freed_tables
+ *
+ *    set when we freed page table pages
+ *
+ *  - tlb_get_unmap_shift() / tlb_get_unmap_size()
+ *
+ *    returns the smallest TLB entry size unmapped in this range.
+ *
+ * If an architecture does not provide tlb_flush() a default implementation
+ * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is
+ * specified, in which case we'll default to flush_tlb_mm().
+ *
+ * Additionally there are a few opt-in features:
+ *
+ *  HAVE_MMU_GATHER_PAGE_SIZE
+ *
+ *  This ensures we call tlb_flush() every time tlb_change_page_size() actually
+ *  changes the size and provides mmu_gather::page_size to tlb_flush().
+ *
+ *  HAVE_RCU_TABLE_FREE
+ *
+ *  This provides tlb_remove_table(), to be used instead of tlb_remove_page()
+ *  for page directores (__p*_free_tlb()). This provides separate freeing of
+ *  the page-table pages themselves in a semi-RCU fashion (see comment below).
+ *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ *  and therefore doesn't naturally serialize with software page-table walkers.
+ *
+ *  When used, an architecture is expected to provide __tlb_remove_table()
+ *  which does the actual freeing of these pages.
+ *
+ *  HAVE_RCU_TABLE_NO_INVALIDATE
+ *
+ *  This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
+ *  freeing the page-table pages. This can be avoided if you use
+ *  HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
+ *  page-tables natively.
+ *
+ *  MMU_GATHER_NO_RANGE
+ *
+ *  Use this if your architecture lacks an efficient flush_tlb_range().
+ */
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
  * Semi RCU freeing of the page directories.
@@ -60,11 +191,11 @@ struct mmu_table_batch {
 #define MAX_TABLE_BATCH		\
 	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
 
-extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 #endif
 
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 /*
  * If we can't allocate a page to make a big batch of page pointers
  * to work on, then just handle a few from the on-stack structure.
@@ -89,14 +220,21 @@ struct mmu_gather_batch {
  */
 #define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
 
-/* struct mmu_gather is an opaque type used by the mm code for passing around
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
+#endif
+
+/*
+ * struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
 struct mmu_gather {
 	struct mm_struct	*mm;
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
+
 	unsigned long		start;
 	unsigned long		end;
 	/*
@@ -124,23 +262,30 @@ struct mmu_gather {
 	unsigned int		cleared_puds : 1;
 	unsigned int		cleared_p4ds : 1;
 
+	/*
+	 * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma
+	 */
+	unsigned int		vma_exec : 1;
+	unsigned int		vma_huge : 1;
+
+	unsigned int		batch_count;
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
-	unsigned int		batch_count;
-	int page_size;
-};
 
-#define HAVE_GENERIC_MMU_GATHER
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	unsigned int page_size;
+#endif
+#endif
+};
 
 void arch_tlb_gather_mmu(struct mmu_gather *tlb,
 	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
-void tlb_flush_mmu_free(struct mmu_gather *tlb);
-extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
-				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address,
@@ -163,8 +308,94 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	tlb->cleared_pmds = 0;
 	tlb->cleared_puds = 0;
 	tlb->cleared_p4ds = 0;
+	/*
+	 * Do not reset mmu_gather::vma_* fields here, we do not
+	 * call into tlb_start_vma() again to set them if there is an
+	 * intermediate flush.
+	 */
+}
+
+#ifdef CONFIG_MMU_GATHER_NO_RANGE
+
+#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma)
+#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not have efficient means of range flushing TLBs
+ * there is no point in doing intermediate flushes on tlb_end_vma() to keep the
+ * range small. We equally don't have to worry about page granularity or other
+ * things.
+ *
+ * All we need to do is issue a full flush for any !0 range.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->end)
+		flush_tlb_mm(tlb->mm);
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#define tlb_end_vma tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#else /* CONFIG_MMU_GATHER_NO_RANGE */
+
+#ifndef tlb_flush
+
+#if defined(tlb_start_vma) || defined(tlb_end_vma)
+#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not provide its own tlb_flush() implementation
+ * but does have a reasonably efficient flush_vma_range() implementation
+ * use that.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || tlb->need_flush_all) {
+		flush_tlb_mm(tlb->mm);
+	} else if (tlb->end) {
+		struct vm_area_struct vma = {
+			.vm_mm = tlb->mm,
+			.vm_flags = (tlb->vma_exec ? VM_EXEC    : 0) |
+				    (tlb->vma_huge ? VM_HUGETLB : 0),
+		};
+
+		flush_tlb_range(&vma, tlb->start, tlb->end);
+	}
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	/*
+	 * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
+	 * mips-4k) flush only large pages.
+	 *
+	 * flush_tlb_range() implementations that flush I-TLB also flush D-TLB
+	 * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
+	 * range.
+	 *
+	 * We rely on tlb_end_vma() to issue a flush, such that when we reset
+	 * these values the batch is empty.
+	 */
+	tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
+	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
 }
 
+#else
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#endif
+
+#endif /* CONFIG_MMU_GATHER_NO_RANGE */
+
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	if (!tlb->end)
@@ -196,21 +427,18 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
-#ifndef tlb_remove_check_page_size_change
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
+static inline void tlb_change_page_size(struct mmu_gather *tlb,
 						     unsigned int page_size)
 {
-	/*
-	 * We don't care about page size change, just update
-	 * mmu_gather page size here so that debug checks
-	 * doesn't throw false warning.
-	 */
-#ifdef CONFIG_DEBUG_VM
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	if (tlb->page_size && tlb->page_size != page_size) {
+		if (!tlb->fullmm)
+			tlb_flush_mmu(tlb);
+	}
+
 	tlb->page_size = page_size;
 #endif
 }
-#endif
 
 static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
 {
@@ -237,17 +465,30 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
  * the vmas are adjusted to only cover the region to be torn down.
  */
 #ifndef tlb_start_vma
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#endif
+static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (tlb->fullmm)
+		return;
 
-#define __tlb_end_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			tlb_flush_mmu_tlbonly(tlb);		\
-	} while (0)
+	tlb_update_vma_flags(tlb, vma);
+	flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
+#endif
 
 #ifndef tlb_end_vma
-#define tlb_end_vma	__tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (tlb->fullmm)
+		return;
+
+	/*
+	 * Do a TLB flush and reset the range at VMA boundaries; this avoids
+	 * the ranges growing with the unused space between consecutive VMAs,
+	 * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
+	 * this.
+	 */
+	tlb_flush_mmu_tlbonly(tlb);
+}
 #endif
 
 #ifndef __tlb_remove_tlb_entry
@@ -372,6 +613,4 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
 
 #endif /* CONFIG_MMU */
 
-#define tlb_migrate_finish(mm) do {} while (0)
-
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d5dcebd7aad3..ca55ae00f8c9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -669,12 +669,14 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 	return false;
 }
 
-static inline const char *
-acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
+static inline struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv)
 {
 	return NULL;
 }
 
+static inline void acpi_dev_put(struct acpi_device *adev) {}
+
 static inline bool is_acpi_node(struct fwnode_handle *fwnode)
 {
 	return false;
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 38cd77b39a64..723e4dfa1c14 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -26,6 +26,14 @@
 #define IORT_IRQ_MASK(irq)		(irq & 0xffffffffULL)
 #define IORT_IRQ_TRIGGER_MASK(irq)	((irq >> 32) & 0xffffffffULL)
 
+/*
+ * PMCG model identifiers for use in smmu pmu driver. Please note
+ * that this is purely for the use of software and has nothing to
+ * do with hardware or with IORT specification.
+ */
+#define IORT_SMMU_V3_PMCG_GENERIC        0x00000000 /* Generic SMMUv3 PMCG */
+#define IORT_SMMU_V3_PMCG_HISI_HIP08     0x00000001 /* HiSilicon HIP08 PMCG */
+
 int iort_register_domain_token(int trans_id, phys_addr_t base,
 			       struct fwnode_handle *fw_node);
 void iort_deregister_domain_token(int trans_id);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f02367faa58d..944ccc310201 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -510,7 +510,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		}					\
 _out:							\
 		rcu_read_unlock();			\
-		preempt_enable_no_resched();		\
+		preempt_enable();			\
 		_ret;					\
 	 })
 
diff --git a/include/linux/clk.h b/include/linux/clk.h
index d8bc1a856b39..f689fc58d7be 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -811,6 +811,22 @@ static inline bool clk_has_parent(struct clk *clk, struct clk *parent)
 	return true;
 }
 
+static inline int clk_set_rate_range(struct clk *clk, unsigned long min,
+				     unsigned long max)
+{
+	return 0;
+}
+
+static inline int clk_set_min_rate(struct clk *clk, unsigned long rate)
+{
+	return 0;
+}
+
+static inline int clk_set_max_rate(struct clk *clk, unsigned long rate)
+{
+	return 0;
+}
+
 static inline int clk_set_parent(struct clk *clk, struct clk *parent)
 {
 	return 0;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 445348facea9..d58aa0db05f9 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -67,7 +67,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 				.line = __LINE__,			\
 			};						\
 		______r = !!(cond);					\
-		______f.miss_hit[______r]++;					\
+		______r ? ______f.miss_hit[1]++ : ______f.miss_hit[0]++;\
 		______r;						\
 	}))
 #endif /* CONFIG_PROFILE_ALL_BRANCHES */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 5041357d0297..732745f865b7 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -137,9 +137,26 @@ static inline int disable_nonboot_cpus(void)
 	return freeze_secondary_cpus(0);
 }
 extern void enable_nonboot_cpus(void);
+
+static inline int suspend_disable_secondary_cpus(void)
+{
+	int cpu = 0;
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU))
+		cpu = -1;
+
+	return freeze_secondary_cpus(cpu);
+}
+static inline void suspend_enable_secondary_cpus(void)
+{
+	return enable_nonboot_cpus();
+}
+
 #else /* !CONFIG_PM_SLEEP_SMP */
 static inline int disable_nonboot_cpus(void) { return 0; }
 static inline void enable_nonboot_cpus(void) {}
+static inline int suspend_disable_secondary_cpus(void) { return 0; }
+static inline void suspend_enable_secondary_cpus(void) { }
 #endif /* !CONFIG_PM_SLEEP_SMP */
 
 void cpu_startup_entry(enum cpuhp_state state);
@@ -175,6 +192,7 @@ enum cpuhp_smt_control {
 	CPU_SMT_DISABLED,
 	CPU_SMT_FORCE_DISABLED,
 	CPU_SMT_NOT_SUPPORTED,
+	CPU_SMT_NOT_IMPLEMENTED,
 };
 
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
@@ -182,9 +200,33 @@ extern enum cpuhp_smt_control cpu_smt_control;
 extern void cpu_smt_disable(bool force);
 extern void cpu_smt_check_topology(void);
 #else
-# define cpu_smt_control		(CPU_SMT_ENABLED)
+# define cpu_smt_control		(CPU_SMT_NOT_IMPLEMENTED)
 static inline void cpu_smt_disable(bool force) { }
 static inline void cpu_smt_check_topology(void) { }
 #endif
 
+/*
+ * These are used for a global "mitigations=" cmdline option for toggling
+ * optional CPU mitigations.
+ */
+enum cpu_mitigations {
+	CPU_MITIGATIONS_OFF,
+	CPU_MITIGATIONS_AUTO,
+	CPU_MITIGATIONS_AUTO_NOSMT,
+};
+
+extern enum cpu_mitigations cpu_mitigations;
+
+/* mitigations=off */
+static inline bool cpu_mitigations_off(void)
+{
+	return cpu_mitigations == CPU_MITIGATIONS_OFF;
+}
+
+/* mitigations=auto,nosmt */
+static inline bool cpu_mitigations_auto_nosmt(void)
+{
+	return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
+}
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index c46fdb36700b..8de8c4f15163 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -102,9 +102,7 @@ const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list);
 extern const char * dmi_get_system_info(int field);
 extern const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from);
-extern void dmi_scan_machine(void);
-extern void dmi_memdev_walk(void);
-extern void dmi_set_dump_stack_arch_desc(void);
+extern void dmi_setup(void);
 extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp);
 extern int dmi_get_bios_year(void);
 extern int dmi_name_in_vendors(const char *str);
@@ -122,9 +120,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0;
 static inline const char * dmi_get_system_info(int field) { return NULL; }
 static inline const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from) { return NULL; }
-static inline void dmi_scan_machine(void) { return; }
-static inline void dmi_memdev_walk(void) { }
-static inline void dmi_set_dump_stack_arch_desc(void) { }
+static inline void dmi_setup(void) { }
 static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp)
 {
 	if (yearp)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6074aa064b54..7d3abde3f183 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -20,6 +20,7 @@
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
 #include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
 
 #include <net/sch_generic.h>
 
@@ -503,7 +504,6 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
@@ -733,24 +733,15 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	fp->undo_set_mem = 1;
+	set_vm_flush_reset_perms(fp);
 	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
-	if (fp->undo_set_mem)
-		set_memory_rw((unsigned long)fp, fp->pages);
-}
-
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
+	set_vm_flush_reset_perms(hdr);
 	set_memory_ro((unsigned long)hdr, hdr->pages);
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
-	set_memory_rw((unsigned long)hdr, hdr->pages);
+	set_memory_x((unsigned long)hdr, hdr->pages);
 }
 
 static inline struct bpf_binary_header *
@@ -788,7 +779,6 @@ void __bpf_prog_free(struct bpf_prog *fp);
 
 static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
 {
-	bpf_prog_unlock_ro(fp);
 	__bpf_prog_free(fp);
 }
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 730876187344..20899919ead8 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -241,21 +241,11 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) {
 
 #ifdef CONFIG_STACK_TRACER
 
-#define STACK_TRACE_ENTRIES 500
-
-struct stack_trace;
-
-extern unsigned stack_trace_index[];
-extern struct stack_trace stack_trace_max;
-extern unsigned long stack_trace_max_size;
-extern arch_spinlock_t stack_trace_max_lock;
-
 extern int stack_tracer_enabled;
-void stack_trace_print(void);
-int
-stack_trace_sysctl(struct ctl_table *table, int write,
-		   void __user *buffer, size_t *lenp,
-		   loff_t *ppos);
+
+int stack_trace_sysctl(struct ctl_table *table, int write,
+		       void __user *buffer, size_t *lenp,
+		       loff_t *ppos);
 
 /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
 DECLARE_PER_CPU(int, disable_stack_tracer);
diff --git a/include/linux/ima.h b/include/linux/ima.h
index dc12fbcf484c..fd9f7cf4cdf5 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -31,7 +31,7 @@ extern void ima_post_path_mknod(struct dentry *dentry);
 extern void ima_add_kexec_buffer(struct kimage *image);
 #endif
 
-#if defined(CONFIG_X86) && defined(CONFIG_EFI)
+#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390)
 extern bool arch_ima_get_secureboot(void);
 extern const char * const *arch_get_ima_policy(void);
 #else
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 690b238a44d5..c7eef32e7739 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
 			 void (*func)(unsigned long), unsigned long data);
 
-struct tasklet_hrtimer {
-	struct hrtimer		timer;
-	struct tasklet_struct	tasklet;
-	enum hrtimer_restart	(*function)(struct hrtimer *);
-};
-
-extern void
-tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-		     enum hrtimer_restart (*function)(struct hrtimer *),
-		     clockid_t which_clock, enum hrtimer_mode mode);
-
-static inline
-void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
-			   const enum hrtimer_mode mode)
-{
-	hrtimer_start(&ttimer->timer, time, mode);
-}
-
-static inline
-void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
-{
-	hrtimer_cancel(&ttimer->timer);
-	tasklet_kill(&ttimer->tasklet);
-}
-
 /*
  * Autoprobing for irqs:
  *
diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h
index a49f2b45b3f0..42710d5949ba 100644
--- a/include/linux/jump_label_ratelimit.h
+++ b/include/linux/jump_label_ratelimit.h
@@ -12,21 +12,79 @@ struct static_key_deferred {
 	struct delayed_work work;
 };
 
-extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
-extern void static_key_deferred_flush(struct static_key_deferred *key);
+struct static_key_true_deferred {
+	struct static_key_true key;
+	unsigned long timeout;
+	struct delayed_work work;
+};
+
+struct static_key_false_deferred {
+	struct static_key_false key;
+	unsigned long timeout;
+	struct delayed_work work;
+};
+
+#define static_key_slow_dec_deferred(x)					\
+	__static_key_slow_dec_deferred(&(x)->key, &(x)->work, (x)->timeout)
+#define static_branch_slow_dec_deferred(x)				\
+	__static_key_slow_dec_deferred(&(x)->key.key, &(x)->work, (x)->timeout)
+
+#define static_key_deferred_flush(x)					\
+	__static_key_deferred_flush((x), &(x)->work)
+
+extern void
+__static_key_slow_dec_deferred(struct static_key *key,
+			       struct delayed_work *work,
+			       unsigned long timeout);
+extern void __static_key_deferred_flush(void *key, struct delayed_work *work);
 extern void
 jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
 
+extern void jump_label_update_timeout(struct work_struct *work);
+
+#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl)			\
+	struct static_key_true_deferred name = {			\
+		.key =		{ STATIC_KEY_INIT_TRUE },		\
+		.timeout =	(rl),					\
+		.work =	__DELAYED_WORK_INITIALIZER((name).work,		\
+						   jump_label_update_timeout, \
+						   0),			\
+	}
+
+#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl)			\
+	struct static_key_false_deferred name = {			\
+		.key =		{ STATIC_KEY_INIT_FALSE },		\
+		.timeout =	(rl),					\
+		.work =	__DELAYED_WORK_INITIALIZER((name).work,		\
+						   jump_label_update_timeout, \
+						   0),			\
+	}
+
+#define static_branch_deferred_inc(x)	static_branch_inc(&(x)->key)
+
 #else	/* !CONFIG_JUMP_LABEL */
 struct static_key_deferred {
 	struct static_key  key;
 };
+struct static_key_true_deferred {
+	struct static_key_true key;
+};
+struct static_key_false_deferred {
+	struct static_key_false key;
+};
+#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl)	\
+	struct static_key_true_deferred name = { STATIC_KEY_TRUE_INIT }
+#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl)	\
+	struct static_key_false_deferred name = { STATIC_KEY_FALSE_INIT }
+
+#define static_branch_slow_dec_deferred(x)	static_branch_dec(&(x)->key)
+
 static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
 	STATIC_KEY_CHECK_USE(key);
 	static_key_slow_dec(&key->key);
 }
-static inline void static_key_deferred_flush(struct static_key_deferred *key)
+static inline void static_key_deferred_flush(void *key)
 {
 	STATIC_KEY_CHECK_USE(key);
 }
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 79c3873d58ac..6e2377e6c1d6 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -66,6 +66,11 @@ struct lock_class_key {
 
 extern struct lock_class_key __lockdep_no_validate__;
 
+struct lock_trace {
+	unsigned int		nr_entries;
+	unsigned int		offset;
+};
+
 #define LOCKSTAT_POINTS		4
 
 /*
@@ -100,7 +105,7 @@ struct lock_class {
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
-	struct stack_trace		usage_traces[XXX_LOCK_USAGE_STATES];
+	struct lock_trace		usage_traces[XXX_LOCK_USAGE_STATES];
 
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
@@ -188,7 +193,7 @@ struct lock_list {
 	struct list_head		entry;
 	struct lock_class		*class;
 	struct lock_class		*links_to;
-	struct stack_trace		trace;
+	struct lock_trace		trace;
 	int				distance;
 
 	/*
@@ -471,7 +476,7 @@ struct pin_cookie { };
 
 #define NIL_COOKIE (struct pin_cookie){ }
 
-#define lockdep_pin_lock(l)			({ struct pin_cookie cookie; cookie; })
+#define lockdep_pin_lock(l)			({ struct pin_cookie cookie = { }; cookie; })
 #define lockdep_repin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 #define lockdep_unpin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6b10c21630f5..083d7b4863ed 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2610,37 +2610,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 extern bool _debug_pagealloc_enabled;
-extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
 static inline bool debug_pagealloc_enabled(void)
 {
-	return _debug_pagealloc_enabled;
+	return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled;
 }
 
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
+extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable)
 {
-	if (!debug_pagealloc_enabled())
-		return;
-
 	__kernel_map_pages(page, numpages, enable);
 }
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
-#else	/* CONFIG_DEBUG_PAGEALLOC */
+#else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
 #endif	/* CONFIG_HIBERNATION */
-static inline bool debug_pagealloc_enabled(void)
-{
-	return false;
-}
-#endif	/* CONFIG_DEBUG_PAGEALLOC */
+#endif	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e47ef764f613..15a82ff0aefe 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -240,7 +240,6 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_NO_NMI			0x02
 #define PERF_PMU_CAP_AUX_NO_SG			0x04
-#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
@@ -464,7 +463,7 @@ enum perf_addr_filter_action_t {
 /**
  * struct perf_addr_filter - address range filter definition
  * @entry:	event's filter list linkage
- * @inode:	object file's inode for file-based filters
+ * @path:	object file's path for file-based filters
  * @offset:	filter range offset
  * @size:	filter range size (size==0 means single address trigger)
  * @action:	filter/start/stop
@@ -888,6 +887,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu);
 extern void perf_sched_cb_inc(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
+
+extern void perf_pmu_resched(struct pmu *pmu);
+
 extern int perf_event_refresh(struct perf_event *event, int refresh);
 extern void perf_event_update_userpage(struct perf_event *event);
 extern int perf_event_release_kernel(struct perf_event *event);
@@ -1055,12 +1057,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo
 #endif
 
 /*
- * Take a snapshot of the regs. Skip ip and frame pointer to
- * the nth caller. We only need a few of the regs:
+ * When generating a perf sample in-line, instead of from an interrupt /
+ * exception, we lack a pt_regs. This is typically used from software events
+ * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints.
+ *
+ * We typically don't need a full set, but (for x86) do require:
  * - ip for PERF_SAMPLE_IP
  * - cs for user_mode() tests
- * - bp for callchains
- * - eflags, for future purposes, just in case
+ * - sp for PERF_SAMPLE_CALLCHAIN
+ * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs())
+ *
+ * NOTE: assumes @regs is otherwise already 0 filled; this is important for
+ * things like PERF_SAMPLE_REGS_INTR.
  */
 static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f6165d304b4d..48841e5dab90 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1338,7 +1338,6 @@ static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info)
 	}
 
 	/* Let SB update */
-	mmiowb();
 	return rc;
 }
 
@@ -1374,7 +1373,6 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info,
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
 	 */
-	mmiowb();
 	barrier();
 }
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6cdb1db776cf..922bb6848813 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -878,9 +878,11 @@ static inline void rcu_head_init(struct rcu_head *rhp)
 static inline bool
 rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
 {
-	if (READ_ONCE(rhp->func) == f)
+	rcu_callback_t func = READ_ONCE(rhp->func);
+
+	if (func == f)
 		return true;
-	WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L);
+	WARN_ON_ONCE(func != (rcu_callback_t)~0L);
 	return false;
 }
 
diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h
index 90bfa3279a01..563290fc194f 100644
--- a/include/linux/rcuwait.h
+++ b/include/linux/rcuwait.h
@@ -18,7 +18,7 @@
  * awoken.
  */
 struct rcuwait {
-	struct task_struct *task;
+	struct task_struct __rcu *task;
 };
 
 #define __RCUWAIT_INITIALIZER(name)		\
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
deleted file mode 100644
index e47568363e5e..000000000000
--- a/include/linux/rwsem-spinlock.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* rwsem-spinlock.h: fallback C implementation
- *
- * Copyright (c) 2001   David Howells (dhowells@redhat.com).
- * - Derived partially from ideas by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-
-#ifndef _LINUX_RWSEM_SPINLOCK_H
-#define _LINUX_RWSEM_SPINLOCK_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-/*
- * the rw-semaphore definition
- * - if count is 0 then there are no active readers or writers
- * - if count is +ve then that is the number of active readers
- * - if count is -1 then there is one active writer
- * - if wait_list is not empty, then there are processes waiting for the semaphore
- */
-struct rw_semaphore {
-	__s32			count;
-	raw_spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-};
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-
-extern void __down_read(struct rw_semaphore *sem);
-extern int __must_check __down_read_killable(struct rw_semaphore *sem);
-extern int __down_read_trylock(struct rw_semaphore *sem);
-extern void __down_write(struct rw_semaphore *sem);
-extern int __must_check __down_write_killable(struct rw_semaphore *sem);
-extern int __down_write_trylock(struct rw_semaphore *sem);
-extern void __up_read(struct rw_semaphore *sem);
-extern void __up_write(struct rw_semaphore *sem);
-extern void __downgrade_write(struct rw_semaphore *sem);
-extern int rwsem_is_locked(struct rw_semaphore *sem);
-
-#endif /* __KERNEL__ */
-#endif /* _LINUX_RWSEM_SPINLOCK_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 67dbb57508b1..2ea18a3def04 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -20,25 +20,30 @@
 #include <linux/osq_lock.h>
 #endif
 
-struct rw_semaphore;
-
-#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
-#include <linux/rwsem-spinlock.h> /* use a generic implementation */
-#define __RWSEM_INIT_COUNT(name)	.count = RWSEM_UNLOCKED_VALUE
-#else
-/* All arch specific implementations share the same struct */
+/*
+ * For an uncontended rwsem, count and owner are the only fields a task
+ * needs to touch when acquiring the rwsem. So they are put next to each
+ * other to increase the chance that they will share the same cacheline.
+ *
+ * In a contended rwsem, the owner is likely the most frequently accessed
+ * field in the structure as the optimistic waiter that holds the osq lock
+ * will spin on owner. For an embedded rwsem, other hot fields in the
+ * containing structure should be moved further away from the rwsem to
+ * reduce the chance that they will share the same cacheline causing
+ * cacheline bouncing problem.
+ */
 struct rw_semaphore {
 	atomic_long_t count;
-	struct list_head wait_list;
-	raw_spinlock_t wait_lock;
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	struct optimistic_spin_queue osq; /* spinner MCS lock */
 	/*
 	 * Write owner. Used as a speculative check to see
 	 * if the owner is running on the cpu.
 	 */
 	struct task_struct *owner;
+	struct optimistic_spin_queue osq; /* spinner MCS lock */
 #endif
+	raw_spinlock_t wait_lock;
+	struct list_head wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -50,24 +55,14 @@ struct rw_semaphore {
  */
 #define RWSEM_OWNER_UNKNOWN	((struct task_struct *)-2L)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/* Include the arch specific part */
-#include <asm/rwsem.h>
-
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
 	return atomic_long_read(&sem->count) != 0;
 }
 
+#define RWSEM_UNLOCKED_VALUE		0L
 #define __RWSEM_INIT_COUNT(name)	.count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
-#endif
 
 /* Common initializer macros and functions */
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1549584a1538..50606a6e73d6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1057,7 +1057,6 @@ struct task_struct {
 
 #ifdef CONFIG_RSEQ
 	struct rseq __user *rseq;
-	u32 rseq_len;
 	u32 rseq_sig;
 	/*
 	 * RmW on rseq_event_mask must be performed atomically
@@ -1855,12 +1854,10 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 {
 	if (clone_flags & CLONE_THREAD) {
 		t->rseq = NULL;
-		t->rseq_len = 0;
 		t->rseq_sig = 0;
 		t->rseq_event_mask = 0;
 	} else {
 		t->rseq = current->rseq;
-		t->rseq_len = current->rseq_len;
 		t->rseq_sig = current->rseq_sig;
 		t->rseq_event_mask = current->rseq_event_mask;
 	}
@@ -1869,7 +1866,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 static inline void rseq_execve(struct task_struct *t)
 {
 	t->rseq = NULL;
-	t->rseq_len = 0;
 	t->rseq_sig = 0;
 	t->rseq_event_mask = 0;
 }
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 2e97a2227045..f1227f2c38a4 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -76,6 +76,7 @@ extern void exit_itimers(struct signal_struct *);
 extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
+struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 57c7ed3fe465..cfc0a89a7159 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -76,8 +76,8 @@ struct sched_domain_shared {
 
 struct sched_domain {
 	/* These fields must be setup */
-	struct sched_domain *parent;	/* top domain must be null terminated */
-	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_domain __rcu *parent;	/* top domain must be null terminated */
+	struct sched_domain __rcu *child;	/* bottom domain must be null terminated */
 	struct sched_group *groups;	/* the balancing groups of the domain */
 	unsigned long min_interval;	/* Minimum balance interval ms */
 	unsigned long max_interval;	/* Maximum balance interval ms */
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 2a986d282a97..b5071497b8cb 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -17,6 +17,17 @@ static inline int set_memory_x(unsigned long addr,  int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
+#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP
+static inline int set_direct_map_invalid_noflush(struct page *page)
+{
+	return 0;
+}
+static inline int set_direct_map_default_noflush(struct page *page)
+{
+	return 0;
+}
+#endif
+
 #ifndef set_mce_nospec
 static inline int set_mce_nospec(unsigned long pfn)
 {
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index d0884b525001..9d1bc65d226c 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -29,7 +29,7 @@ struct smpboot_thread_data;
  * @thread_comm:	The base name of the thread
  */
 struct smp_hotplug_thread {
-	struct task_struct __percpu	**store;
+	struct task_struct		* __percpu *store;
 	struct list_head		list;
 	int				(*thread_should_run)(unsigned int cpu);
 	void				(*thread_fn)(unsigned int cpu);
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index e089157dcf97..ed7c4d6b8235 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -57,6 +57,7 @@
 #include <linux/stringify.h>
 #include <linux/bottom_half.h>
 #include <asm/barrier.h>
+#include <asm/mmiowb.h>
 
 
 /*
@@ -178,6 +179,7 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 {
 	__acquire(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 }
 
 #ifndef arch_spin_lock_flags
@@ -189,15 +191,22 @@ do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lo
 {
 	__acquire(lock);
 	arch_spin_lock_flags(&lock->raw_lock, *flags);
+	mmiowb_spin_lock();
 }
 
 static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
-	return arch_spin_trylock(&(lock)->raw_lock);
+	int ret = arch_spin_trylock(&(lock)->raw_lock);
+
+	if (ret)
+		mmiowb_spin_lock();
+
+	return ret;
 }
 
 static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 {
+	mmiowb_spin_unlock();
 	arch_spin_unlock(&lock->raw_lock);
 	__release(lock);
 }
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index c495b2d51569..e432cc92c73d 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -56,45 +56,11 @@ struct srcu_struct { };
 
 void call_srcu(struct srcu_struct *ssp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head));
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced);
+void cleanup_srcu_struct(struct srcu_struct *ssp);
 int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp);
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
 void synchronize_srcu(struct srcu_struct *ssp);
 
-/**
- * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @ssp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
- */
-static inline void cleanup_srcu_struct(struct srcu_struct *ssp)
-{
-	_cleanup_srcu_struct(ssp, false);
-}
-
-/**
- * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
- * @ssp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.  Also,
- * all grace-period processing must have completed.
- *
- * "Completed" means that the last synchronize_srcu() and
- * synchronize_srcu_expedited() calls must have returned before the call
- * to cleanup_srcu_struct_quiesced().  It also means that the callback
- * from the last call_srcu() must have been invoked before the call to
- * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
- * with this last.  Violating these rules will get you a WARN_ON() splat
- * (with high probability, anyway), and will also cause the srcu_struct
- * to be leaked.
- */
-static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp)
-{
-	_cleanup_srcu_struct(ssp, true);
-}
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 /**
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 7978b3e2c1e1..0805dee1b6b8 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -23,10 +23,10 @@
 
 typedef u32 depot_stack_handle_t;
 
-struct stack_trace;
+depot_stack_handle_t stack_depot_save(unsigned long *entries,
+				      unsigned int nr_entries, gfp_t gfp_flags);
 
-depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags);
-
-void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace);
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+			       unsigned long **entries);
 
 #endif
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index ba29a0613e66..f0cfd12cb45e 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -3,11 +3,64 @@
 #define __LINUX_STACKTRACE_H
 
 #include <linux/types.h>
+#include <asm/errno.h>
 
 struct task_struct;
 struct pt_regs;
 
 #ifdef CONFIG_STACKTRACE
+void stack_trace_print(unsigned long *trace, unsigned int nr_entries,
+		       int spaces);
+int stack_trace_snprint(char *buf, size_t size, unsigned long *entries,
+			unsigned int nr_entries, int spaces);
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+			      unsigned int skipnr);
+unsigned int stack_trace_save_tsk(struct task_struct *task,
+				  unsigned long *store, unsigned int size,
+				  unsigned int skipnr);
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+				   unsigned int size, unsigned int skipnr);
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size);
+
+/* Internal interfaces. Do not use in generic code */
+#ifdef CONFIG_ARCH_STACKWALK
+
+/**
+ * stack_trace_consume_fn - Callback for arch_stack_walk()
+ * @cookie:	Caller supplied pointer handed back by arch_stack_walk()
+ * @addr:	The stack entry address to consume
+ * @reliable:	True when the stack entry is reliable. Required by
+ *		some printk based consumers.
+ *
+ * Return:	True, if the entry was consumed or skipped
+ *		False, if there is no space left to store
+ */
+typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr,
+				       bool reliable);
+/**
+ * arch_stack_walk - Architecture specific function to walk the stack
+ * @consume_entry:	Callback which is invoked by the architecture code for
+ *			each entry.
+ * @cookie:		Caller supplied pointer which is handed back to
+ *			@consume_entry
+ * @task:		Pointer to a task struct, can be NULL
+ * @regs:		Pointer to registers, can be NULL
+ *
+ * ============ ======= ============================================
+ * task	        regs
+ * ============ ======= ============================================
+ * task		NULL	Stack trace from task (can be current)
+ * current	regs	Stack trace starting on regs->stackpointer
+ * ============ ======= ============================================
+ */
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs);
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie,
+			     struct task_struct *task);
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+			  const struct pt_regs *regs);
+
+#else /* CONFIG_ARCH_STACKWALK */
 struct stack_trace {
 	unsigned int nr_entries, max_entries;
 	unsigned long *entries;
@@ -21,24 +74,20 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 extern int save_stack_trace_tsk_reliable(struct task_struct *tsk,
 					 struct stack_trace *trace);
-
-extern void print_stack_trace(struct stack_trace *trace, int spaces);
-extern int snprint_stack_trace(char *buf, size_t size,
-			struct stack_trace *trace, int spaces);
-
-#ifdef CONFIG_USER_STACKTRACE_SUPPORT
 extern void save_stack_trace_user(struct stack_trace *trace);
+#endif /* !CONFIG_ARCH_STACKWALK */
+#endif /* CONFIG_STACKTRACE */
+
+#if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE)
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size);
 #else
-# define save_stack_trace_user(trace)              do { } while (0)
+static inline int stack_trace_save_tsk_reliable(struct task_struct *tsk,
+						unsigned long *store,
+						unsigned int size)
+{
+	return -ENOSYS;
+}
 #endif
 
-#else /* !CONFIG_STACKTRACE */
-# define save_stack_trace(trace)			do { } while (0)
-# define save_stack_trace_tsk(tsk, trace)		do { } while (0)
-# define save_stack_trace_user(trace)			do { } while (0)
-# define print_stack_trace(trace, spaces)		do { } while (0)
-# define snprint_stack_trace(buf, size, trace, spaces)	do { } while (0)
-# define save_stack_trace_tsk_reliable(tsk, trace)	({ -ENOSYS; })
-#endif /* CONFIG_STACKTRACE */
-
 #endif /* __LINUX_STACKTRACE_H */
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 8891b5ac3e40..f92a10b5e112 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode);
 static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
 #endif /* BROADCAST */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_offline_cpu(unsigned int cpu);
+#else
+static inline void tick_offline_cpu(unsigned int cpu) { }
+#endif
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
 #else
diff --git a/include/linux/time64.h b/include/linux/time64.h
index f38d382ffec1..a620ee610b9f 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -33,6 +33,17 @@ struct itimerspec64 {
 #define KTIME_MAX			((s64)~((u64)1 << 63))
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
 
+/*
+ * Limits for settimeofday():
+ *
+ * To prevent setting the time close to the wraparound point time setting
+ * is limited so a reasonable uptime can be accomodated. Uptime of 30 years
+ * should be really sufficient, which means the cutoff is 2232. At that
+ * point the cutoff is just a small part of the larger problem.
+ */
+#define TIME_UPTIME_SEC_MAX		(30LL * 365 * 24 *3600)
+#define TIME_SETTOD_SEC_MAX		(KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX)
+
 static inline int timespec64_equal(const struct timespec64 *a,
 				   const struct timespec64 *b)
 {
@@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts)
 	return true;
 }
 
+static inline bool timespec64_valid_settod(const struct timespec64 *ts)
+{
+	if (!timespec64_valid(ts))
+		return false;
+	/* Disallow values which cause overflow issues vs. CLOCK_REALTIME */
+	if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX)
+		return false;
+	return true;
+}
+
 /**
  * timespec64_to_ns - Convert timespec64 to nanoseconds
  * @ts:		pointer to the timespec64 variable to be converted
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 37b226e8df13..2b70130af585 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -268,6 +268,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 #define user_access_end() do { } while (0)
 #define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
 #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
+static inline unsigned long user_access_save(void) { return 0UL; }
+static inline void user_access_restore(unsigned long flags) { }
 #endif
 
 #ifdef CONFIG_HARDENED_USERCOPY
diff --git a/include/linux/uio.h b/include/linux/uio.h
index f184af1999a8..2d0131ad4604 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -60,7 +60,7 @@ struct iov_iter {
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 {
-	return i->type & ~(READ | WRITE);
+	return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF);
 }
 
 static inline bool iter_is_iovec(const struct iov_iter *i)
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 103a48a48872..12bf0b68ed92 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -115,6 +115,7 @@ struct uprobes_state {
 	struct xol_area		*xol_area;
 };
 
+extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool is_swbp_insn(uprobe_opcode_t *insn);
@@ -154,6 +155,10 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 struct uprobes_state {
 };
 
+static inline void uprobes_init(void)
+{
+}
+
 #define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
 
 static inline int
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 5e49e82c4368..ff010d1fd1c7 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -200,7 +200,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt,
  * @dev: driver model's view of this device
  * @usb_dev: if an interface is bound to the USB major, this will point
  *	to the sysfs representation for that device.
- * @pm_usage_cnt: PM usage counter for this interface
  * @reset_ws: Used for scheduling resets from atomic context.
  * @resetting_device: USB core reset the device, so use alt setting 0 as
  *	current; needs bandwidth alloc after reset.
@@ -257,7 +256,6 @@ struct usb_interface {
 
 	struct device dev;		/* interface specific device info */
 	struct device *usb_dev;
-	atomic_t pm_usage_cnt;		/* usage counter for autosuspend */
 	struct work_struct reset_ws;	/* for resets in atomic context */
 };
 #define	to_usb_interface(d) container_of(d, struct usb_interface, dev)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 398e9c95cd61..c6eebb839552 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -21,6 +21,11 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+/*
+ * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
+ * vfree_atomic().
+ */
+#define VM_FLUSH_RESET_PERMS	0x00000100      /* Reset direct map and flush TLB on unmap */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
@@ -142,6 +147,13 @@ extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
 				    pgprot_t prot, struct page **pages);
 extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
 extern void unmap_kernel_range(unsigned long addr, unsigned long size);
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+	struct vm_struct *vm = find_vm_area(addr);
+
+	if (vm)
+		vm->flags |= VM_FLUSH_RESET_PERMS;
+}
 #else
 static inline int
 map_kernel_range_noflush(unsigned long start, unsigned long size,
@@ -157,6 +169,9 @@ static inline void
 unmap_kernel_range(unsigned long addr, unsigned long size)
 {
 }
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+}
 #endif
 
 /* Allocate/destroy a 'vmalloc' VM area. */
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 6640f84fe536..6d5beac29bc1 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -105,7 +105,6 @@ enum sctp_verb {
 	SCTP_CMD_T1_RETRAN,	 /* Mark for retransmission after T1 timeout  */
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
 	SCTP_CMD_SEND_MSG,	 /* Send the whole use message */
-	SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
 	SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
 	SCTP_CMD_SET_ASOC,	 /* Restore association context */
 	SCTP_CMD_LAST
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 85386becbaea..99f722c4d804 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -219,7 +219,7 @@ struct xfrm_state {
 	struct xfrm_stats	stats;
 
 	struct xfrm_lifetime_cur curlft;
-	struct tasklet_hrtimer	mtimer;
+	struct hrtimer		mtimer;
 
 	struct xfrm_state_offload xso;
 
@@ -295,7 +295,8 @@ struct xfrm_replay {
 };
 
 struct xfrm_if_cb {
-	struct xfrm_if	*(*decode_session)(struct sk_buff *skb);
+	struct xfrm_if	*(*decode_session)(struct sk_buff *skb,
+					   unsigned short family);
 };
 
 void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
@@ -1404,6 +1405,23 @@ static inline int xfrm_state_kern(const struct xfrm_state *x)
 	return atomic_read(&x->tunnel_users);
 }
 
+static inline bool xfrm_id_proto_valid(u8 proto)
+{
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+	case IPPROTO_COMP:
+#if IS_ENABLED(CONFIG_IPV6)
+	case IPPROTO_ROUTING:
+	case IPPROTO_DSTOPTS:
+#endif
+		return true;
+	default:
+		return false;
+	}
+}
+
+/* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */
 static inline int xfrm_id_proto_match(u8 proto, u8 userproto)
 {
 	return (!userproto || proto == userproto ||
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index a57e4ee989d6..b7a904825e7d 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -73,7 +73,7 @@ TRACE_EVENT(timer_start,
 		__entry->flags		= flags;
 	),
 
-	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
+	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
 		  __entry->timer, __entry->function, __entry->expires,
 		  (long)__entry->expires - __entry->now,
 		  __entry->flags & TIMER_CPUMASK,
@@ -89,23 +89,27 @@ TRACE_EVENT(timer_start,
  */
 TRACE_EVENT(timer_expire_entry,
 
-	TP_PROTO(struct timer_list *timer),
+	TP_PROTO(struct timer_list *timer, unsigned long baseclk),
 
-	TP_ARGS(timer),
+	TP_ARGS(timer, baseclk),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer	)
 		__field( unsigned long,	now	)
 		__field( void *,	function)
+		__field( unsigned long,	baseclk	)
 	),
 
 	TP_fast_assign(
 		__entry->timer		= timer;
 		__entry->now		= jiffies;
 		__entry->function	= timer->function;
+		__entry->baseclk	= baseclk;
 	),
 
-	TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now)
+	TP_printk("timer=%p function=%ps now=%lu baseclk=%lu",
+		  __entry->timer, __entry->function, __entry->now,
+		  __entry->baseclk)
 );
 
 /**
@@ -210,7 +214,7 @@ TRACE_EVENT(hrtimer_start,
 		__entry->mode		= mode;
 	),
 
-	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+	TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu "
 		  "mode=%s", __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->expires,
 		  (unsigned long long) __entry->softexpires,
@@ -243,7 +247,8 @@ TRACE_EVENT(hrtimer_expire_entry,
 		__entry->function	= hrtimer->function;
 	),
 
-	TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
+	TP_printk("hrtimer=%p function=%ps now=%llu",
+		  __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->now)
 );
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 02bb7ad6e986..8f10748dac79 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -353,6 +353,10 @@ struct vfio_region_gfx_edid {
 #define VFIO_DEVICE_GFX_LINK_STATE_DOWN  2
 };
 
+#define VFIO_REGION_TYPE_CCW			(2)
+/* ccw sub-types */
+#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD	(1)
+
 /*
  * 10de vendor sub-type
  *
diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h
index 2ec5f367ff78..cbecbf0cd54f 100644
--- a/include/uapi/linux/vfio_ccw.h
+++ b/include/uapi/linux/vfio_ccw.h
@@ -12,6 +12,7 @@
 
 #include <linux/types.h>
 
+/* used for START SUBCHANNEL, always present */
 struct ccw_io_region {
 #define ORB_AREA_SIZE 12
 	__u8	orb_area[ORB_AREA_SIZE];
@@ -22,4 +23,15 @@ struct ccw_io_region {
 	__u32	ret_code;
 } __packed;
 
+/*
+ * used for processing commands that trigger asynchronous actions
+ * Note: this is controlled by a capability
+ */
+#define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0)
+#define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1)
+struct ccw_cmd_region {
+	__u32 command;
+	__u32 ret_code;
+} __packed;
+
 #endif
diff --git a/init/main.c b/init/main.c
index 7d4025d665eb..9dc2f3b4f753 100644
--- a/init/main.c
+++ b/init/main.c
@@ -504,6 +504,10 @@ void __init __weak thread_stack_cache_init(void)
 
 void __init __weak mem_encrypt_init(void) { }
 
+void __init __weak poking_init(void) { }
+
+void __init __weak pgd_cache_init(void) { }
+
 bool initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
@@ -535,6 +539,7 @@ static void __init mm_init(void)
 	init_espfix_bsp();
 	/* Should be run after espfix64 is set up. */
 	pti_init();
+	pgd_cache_init();
 }
 
 void __init __weak arch_call_rest_init(void)
@@ -737,6 +742,7 @@ asmlinkage __visible void __init start_kernel(void)
 	taskstats_init_early();
 	delayacct_init();
 
+	poking_init();
 	check_bugs();
 
 	acpi_subsystem_init();
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index fbba478ae522..bf770d7556f7 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -229,7 +229,7 @@ config MUTEX_SPIN_ON_OWNER
 
 config RWSEM_SPIN_ON_OWNER
        def_bool y
-       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
+       depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
 
 config LOCK_SPIN_ON_OWNER
        def_bool y
@@ -251,3 +251,10 @@ config ARCH_USE_QUEUED_RWLOCKS
 config QUEUED_RWLOCKS
 	def_bool y if ARCH_USE_QUEUED_RWLOCKS
 	depends on SMP
+
+config ARCH_HAS_MMIOWB
+	bool
+
+config MMIOWB
+	def_bool y if ARCH_HAS_MMIOWB
+	depends on SMP
diff --git a/kernel/Makefile b/kernel/Makefile
index 6c57e78817da..62471e75a2b0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -30,6 +30,7 @@ KCOV_INSTRUMENT_extable.o := n
 # Don't self-instrument.
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
+CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 # cond_syscall is currently not LTO compatible
 CFLAGS_sys_ni.o = $(DISABLE_LTO)
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c
index 1323360d90e3..a563c8fdad0d 100644
--- a/kernel/backtracetest.c
+++ b/kernel/backtracetest.c
@@ -48,19 +48,14 @@ static void backtrace_test_irq(void)
 #ifdef CONFIG_STACKTRACE
 static void backtrace_test_saved(void)
 {
-	struct stack_trace trace;
 	unsigned long entries[8];
+	unsigned int nr_entries;
 
 	pr_info("Testing a saved backtrace.\n");
 	pr_info("The following trace is a kernel self test and not a bug!\n");
 
-	trace.nr_entries = 0;
-	trace.max_entries = ARRAY_SIZE(entries);
-	trace.entries = entries;
-	trace.skip = 0;
-
-	save_stack_trace(&trace);
-	print_stack_trace(&trace, 0);
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	stack_trace_print(entries, nr_entries, 0);
 }
 #else
 static void backtrace_test_saved(void)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ff09d32a8a1b..c605397c79f0 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -848,7 +848,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	if (fp->jited) {
 		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
 
-		bpf_jit_binary_unlock_ro(hdr);
 		bpf_jit_binary_free(hdr);
 
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6c5a41f7f338..09d5d972c9ff 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4138,15 +4138,35 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static void __find_good_pkt_pointers(struct bpf_func_state *state,
+				     struct bpf_reg_state *dst_reg,
+				     enum bpf_reg_type type, u16 new_range)
+{
+	struct bpf_reg_state *reg;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++) {
+		reg = &state->regs[i];
+		if (reg->type == type && reg->id == dst_reg->id)
+			/* keep the maximum range already checked */
+			reg->range = max(reg->range, new_range);
+	}
+
+	bpf_for_each_spilled_reg(i, state, reg) {
+		if (!reg)
+			continue;
+		if (reg->type == type && reg->id == dst_reg->id)
+			reg->range = max(reg->range, new_range);
+	}
+}
+
 static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 				   struct bpf_reg_state *dst_reg,
 				   enum bpf_reg_type type,
 				   bool range_right_open)
 {
-	struct bpf_func_state *state = vstate->frame[vstate->curframe];
-	struct bpf_reg_state *regs = state->regs, *reg;
 	u16 new_range;
-	int i, j;
+	int i;
 
 	if (dst_reg->off < 0 ||
 	    (dst_reg->off == 0 && range_right_open))
@@ -4211,20 +4231,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 	 * the range won't allow anything.
 	 * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
 	 */
-	for (i = 0; i < MAX_BPF_REG; i++)
-		if (regs[i].type == type && regs[i].id == dst_reg->id)
-			/* keep the maximum range already checked */
-			regs[i].range = max(regs[i].range, new_range);
-
-	for (j = 0; j <= vstate->curframe; j++) {
-		state = vstate->frame[j];
-		bpf_for_each_spilled_reg(i, state, reg) {
-			if (!reg)
-				continue;
-			if (reg->type == type && reg->id == dst_reg->id)
-				reg->range = max(reg->range, new_range);
-		}
-	}
+	for (i = 0; i <= vstate->curframe; i++)
+		__find_good_pkt_pointers(vstate->frame[i], dst_reg, type,
+					 new_range);
 }
 
 /* compute branch direction of the expression "if (reg opcode val) goto target;"
@@ -4698,6 +4707,22 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 	}
 }
 
+static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id,
+				    bool is_null)
+{
+	struct bpf_reg_state *reg;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++)
+		mark_ptr_or_null_reg(state, &state->regs[i], id, is_null);
+
+	bpf_for_each_spilled_reg(i, state, reg) {
+		if (!reg)
+			continue;
+		mark_ptr_or_null_reg(state, reg, id, is_null);
+	}
+}
+
 /* The logic is similar to find_good_pkt_pointers(), both could eventually
  * be folded together at some point.
  */
@@ -4705,10 +4730,10 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
 				  bool is_null)
 {
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
-	struct bpf_reg_state *reg, *regs = state->regs;
+	struct bpf_reg_state *regs = state->regs;
 	u32 ref_obj_id = regs[regno].ref_obj_id;
 	u32 id = regs[regno].id;
-	int i, j;
+	int i;
 
 	if (ref_obj_id && ref_obj_id == id && is_null)
 		/* regs[regno] is in the " == NULL" branch.
@@ -4717,17 +4742,8 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
 		 */
 		WARN_ON_ONCE(release_reference_state(state, id));
 
-	for (i = 0; i < MAX_BPF_REG; i++)
-		mark_ptr_or_null_reg(state, &regs[i], id, is_null);
-
-	for (j = 0; j <= vstate->curframe; j++) {
-		state = vstate->frame[j];
-		bpf_for_each_spilled_reg(i, state, reg) {
-			if (!reg)
-				continue;
-			mark_ptr_or_null_reg(state, reg, id, is_null);
-		}
-	}
+	for (i = 0; i <= vstate->curframe; i++)
+		__mark_ptr_or_null_regs(vstate->frame[i], id, is_null);
 }
 
 static bool try_match_pkt_pointers(const struct bpf_insn *insn,
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4834c4214e9c..6a1942ed781c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -740,11 +740,10 @@ static inline int nr_cpusets(void)
  * Must be called with cpuset_mutex held.
  *
  * The three key local variables below are:
- *    q  - a linked-list queue of cpuset pointers, used to implement a
- *	   top-down scan of all cpusets.  This scan loads a pointer
- *	   to each cpuset marked is_sched_load_balance into the
- *	   array 'csa'.  For our purposes, rebuilding the schedulers
- *	   sched domains, we can ignore !is_sched_load_balance cpusets.
+ *    cp - cpuset pointer, used (together with pos_css) to perform a
+ *	   top-down scan of all cpusets. For our purposes, rebuilding
+ *	   the schedulers sched domains, we can ignore !is_sched_load_
+ *	   balance cpusets.
  *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
  *	   that need to be load balanced, for convenient iterative
  *	   access by the subsequent code that finds the best partition,
@@ -775,7 +774,7 @@ static inline int nr_cpusets(void)
 static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
-	struct cpuset *cp;	/* scans q */
+	struct cpuset *cp;	/* top-down scan of cpusets */
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6754f3ecfd94..f2ef10460698 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -9,6 +9,7 @@
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/task.h>
 #include <linux/sched/smt.h>
 #include <linux/unistd.h>
@@ -860,6 +861,8 @@ static int take_cpu_down(void *_param)
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
+	/* Remove CPU from timer broadcasting */
+	tick_offline_cpu(cpu);
 	/* Park the stopper thread */
 	stop_machine_park(cpu);
 	return 0;
@@ -1199,8 +1202,15 @@ int freeze_secondary_cpus(int primary)
 	int cpu, error = 0;
 
 	cpu_maps_update_begin();
-	if (!cpu_online(primary))
+	if (primary == -1) {
 		primary = cpumask_first(cpu_online_mask);
+		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+	} else {
+		if (!cpu_online(primary))
+			primary = cpumask_first(cpu_online_mask);
+	}
+
 	/*
 	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
@@ -2033,19 +2043,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 
 #ifdef CONFIG_HOTPLUG_SMT
 
-static const char *smt_states[] = {
-	[CPU_SMT_ENABLED]		= "on",
-	[CPU_SMT_DISABLED]		= "off",
-	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
-	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
-};
-
-static ssize_t
-show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
-}
-
 static void cpuhp_offline_cpu_device(unsigned int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
@@ -2116,9 +2113,10 @@ static int cpuhp_smt_enable(void)
 	return ret;
 }
 
+
 static ssize_t
-store_smt_control(struct device *dev, struct device_attribute *attr,
-		  const char *buf, size_t count)
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+		    const char *buf, size_t count)
 {
 	int ctrlval, ret;
 
@@ -2156,14 +2154,44 @@ store_smt_control(struct device *dev, struct device_attribute *attr,
 	unlock_device_hotplug();
 	return ret ? ret : count;
 }
+
+#else /* !CONFIG_HOTPLUG_SMT */
+static ssize_t
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+		    const char *buf, size_t count)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_HOTPLUG_SMT */
+
+static const char *smt_states[] = {
+	[CPU_SMT_ENABLED]		= "on",
+	[CPU_SMT_DISABLED]		= "off",
+	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
+	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
+	[CPU_SMT_NOT_IMPLEMENTED]	= "notimplemented",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	const char *state = smt_states[cpu_smt_control];
+
+	return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	return __store_smt_control(dev, attr, buf, count);
+}
 static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
 
 static ssize_t
 show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	bool active = topology_max_smt_threads() > 1;
-
-	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+	return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active());
 }
 static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
 
@@ -2179,21 +2207,17 @@ static const struct attribute_group cpuhp_smt_attr_group = {
 	NULL
 };
 
-static int __init cpu_smt_state_init(void)
+static int __init cpu_smt_sysfs_init(void)
 {
 	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				  &cpuhp_smt_attr_group);
 }
 
-#else
-static inline int cpu_smt_state_init(void) { return 0; }
-#endif
-
 static int __init cpuhp_sysfs_init(void)
 {
 	int cpu, ret;
 
-	ret = cpu_smt_state_init();
+	ret = cpu_smt_sysfs_init();
 	if (ret)
 		return ret;
 
@@ -2214,7 +2238,7 @@ static int __init cpuhp_sysfs_init(void)
 	return 0;
 }
 device_initcall(cpuhp_sysfs_init);
-#endif
+#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */
 
 /*
  * cpu_bit_bitmap[] is a special, "compressed" data structure that
@@ -2304,3 +2328,18 @@ void __init boot_cpu_hotplug_init(void)
 #endif
 	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
+
+enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
+
+static int __init mitigations_parse_cmdline(char *arg)
+{
+	if (!strcmp(arg, "off"))
+		cpu_mitigations = CPU_MITIGATIONS_OFF;
+	else if (!strcmp(arg, "auto"))
+		cpu_mitigations = CPU_MITIGATIONS_AUTO;
+	else if (!strcmp(arg, "auto,nosmt"))
+		cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
+
+	return 0;
+}
+early_param("mitigations", mitigations_parse_cmdline);
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index a218e43cc382..badd77670d00 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -89,8 +89,8 @@ struct dma_debug_entry {
 	int		 sg_mapped_ents;
 	enum map_err_types  map_err_type;
 #ifdef CONFIG_STACKTRACE
-	struct		 stack_trace stacktrace;
-	unsigned long	 st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+	unsigned int	stack_len;
+	unsigned long	stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
 #endif
 };
 
@@ -174,7 +174,7 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry)
 #ifdef CONFIG_STACKTRACE
 	if (entry) {
 		pr_warning("Mapped at:\n");
-		print_stack_trace(&entry->stacktrace, 0);
+		stack_trace_print(entry->stack_entries, entry->stack_len, 0);
 	}
 #endif
 }
@@ -704,12 +704,10 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	spin_unlock_irqrestore(&free_entries_lock, flags);
 
 #ifdef CONFIG_STACKTRACE
-	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
-	entry->stacktrace.entries = entry->st_entries;
-	entry->stacktrace.skip = 1;
-	save_stack_trace(&entry->stacktrace);
+	entry->stack_len = stack_trace_save(entry->stack_entries,
+					    ARRAY_SIZE(entry->stack_entries),
+					    1);
 #endif
-
 	return entry;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dc7dead2d2cc..abbd4b3b96c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2478,6 +2478,16 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 	perf_pmu_enable(cpuctx->ctx.pmu);
 }
 
+void perf_pmu_resched(struct pmu *pmu)
+{
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+	struct perf_event_context *task_ctx = cpuctx->task_ctx;
+
+	perf_ctx_lock(cpuctx, task_ctx);
+	ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU);
+	perf_ctx_unlock(cpuctx, task_ctx);
+}
+
 /*
  * Cross CPU call to install and enable a performance event
  *
@@ -11917,7 +11927,7 @@ static void __init perf_event_init_all_cpus(void)
 	}
 }
 
-void perf_swevent_init_cpu(unsigned int cpu)
+static void perf_swevent_init_cpu(unsigned int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5eedb49a65ea..674b35383491 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -610,8 +610,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 	 * PMU requests more than one contiguous chunks of memory
 	 * for SW double buffering
 	 */
-	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
-	    !overwrite) {
+	if (!overwrite) {
 		if (!max_order)
 			return -EINVAL;
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c5cde87329c7..e6a0d6be87e3 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2294,16 +2294,14 @@ static struct notifier_block uprobe_exception_nb = {
 	.priority		= INT_MAX-1,	/* notified after kprobes, kgdb */
 };
 
-static int __init init_uprobes(void)
+void __init uprobes_init(void)
 {
 	int i;
 
 	for (i = 0; i < UPROBES_HASH_SZ; i++)
 		mutex_init(&uprobes_mmap_mutex[i]);
 
-	if (percpu_init_rwsem(&dup_mmap_sem))
-		return -ENOMEM;
+	BUG_ON(percpu_init_rwsem(&dup_mmap_sem));
 
-	return register_die_notifier(&uprobe_exception_nb);
+	BUG_ON(register_die_notifier(&uprobe_exception_nb));
 }
-__initcall(init_uprobes);
diff --git a/kernel/fork.c b/kernel/fork.c
index 9dcd18aa210b..fbe9dfcd8680 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -815,6 +815,7 @@ void __init fork_init(void)
 #endif
 
 	lockdep_init_task(&init_task);
+	uprobes_init();
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -1298,13 +1299,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 		complete_vfork_done(tsk);
 }
 
-/*
- * Allocate a new mm structure and copy contents from the
- * mm structure of the passed in task structure.
+/**
+ * dup_mm() - duplicates an existing mm structure
+ * @tsk: the task_struct with which the new mm will be associated.
+ * @oldmm: the mm to duplicate.
+ *
+ * Allocates a new mm structure and duplicates the provided @oldmm structure
+ * content into it.
+ *
+ * Return: the duplicated mm or NULL on failure.
  */
-static struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk,
+				struct mm_struct *oldmm)
 {
-	struct mm_struct *mm, *oldmm = current->mm;
+	struct mm_struct *mm;
 	int err;
 
 	mm = allocate_mm();
@@ -1371,7 +1379,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	}
 
 	retval = -ENOMEM;
-	mm = dup_mm(tsk);
+	mm = dup_mm(tsk, current->mm);
 	if (!mm)
 		goto fail_nomem;
 
@@ -2186,6 +2194,11 @@ struct task_struct *fork_idle(int cpu)
 	return task;
 }
 
+struct mm_struct *copy_init_mm(void)
+{
+	return dup_mm(NULL, &init_mm);
+}
+
 /*
  *  Ok, this is the main fork-routine.
  *
diff --git a/kernel/futex.c b/kernel/futex.c
index 9e40cf7be606..6262f1534ac9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1311,13 +1311,15 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
+	int err;
 	u32 uninitialized_var(curval);
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
+	err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (unlikely(err))
+		return err;
 
 	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
@@ -1502,10 +1504,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
-		ret = -EFAULT;
-
-	} else if (curval != uval) {
+	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (!ret && (curval != uval)) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
 		 * try the TID->0 transition) raced with a waiter setting the
@@ -1700,32 +1700,32 @@ retry_private:
 	double_lock_hb(hb1, hb2);
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
-
 		double_unlock_hb(hb1, hb2);
 
-#ifndef CONFIG_MMU
-		/*
-		 * we don't get EFAULT from MMU faults if we don't have an MMU,
-		 * but we might get them from range checking
-		 */
-		ret = op_ret;
-		goto out_put_keys;
-#endif
-
-		if (unlikely(op_ret != -EFAULT)) {
+		if (!IS_ENABLED(CONFIG_MMU) ||
+		    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+			/*
+			 * we don't get EFAULT from MMU faults if we don't have
+			 * an MMU, but we might get them from range checking
+			 */
 			ret = op_ret;
 			goto out_put_keys;
 		}
 
-		ret = fault_in_user_writeable(uaddr2);
-		if (ret)
-			goto out_put_keys;
+		if (op_ret == -EFAULT) {
+			ret = fault_in_user_writeable(uaddr2);
+			if (ret)
+				goto out_put_keys;
+		}
 
-		if (!(flags & FLAGS_SHARED))
+		if (!(flags & FLAGS_SHARED)) {
+			cond_resched();
 			goto retry_private;
+		}
 
 		put_futex_key(&key2);
 		put_futex_key(&key1);
+		cond_resched();
 		goto retry;
 	}
 
@@ -2350,7 +2350,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	u32 uval, uninitialized_var(curval), newval;
 	struct task_struct *oldowner, *newowner;
 	u32 newtid;
-	int ret;
+	int ret, err = 0;
 
 	lockdep_assert_held(q->lock_ptr);
 
@@ -2421,14 +2421,17 @@ retry:
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
 
-	if (get_futex_value_locked(&uval, uaddr))
-		goto handle_fault;
+	err = get_futex_value_locked(&uval, uaddr);
+	if (err)
+		goto handle_err;
 
 	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			goto handle_fault;
+		err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+		if (err)
+			goto handle_err;
+
 		if (curval == uval)
 			break;
 		uval = curval;
@@ -2456,23 +2459,37 @@ retry:
 	return 0;
 
 	/*
-	 * To handle the page fault we need to drop the locks here. That gives
-	 * the other task (either the highest priority waiter itself or the
-	 * task which stole the rtmutex) the chance to try the fixup of the
-	 * pi_state. So once we are back from handling the fault we need to
-	 * check the pi_state after reacquiring the locks and before trying to
-	 * do another fixup. When the fixup has been done already we simply
-	 * return.
+	 * In order to reschedule or handle a page fault, we need to drop the
+	 * locks here. In the case of a fault, this gives the other task
+	 * (either the highest priority waiter itself or the task which stole
+	 * the rtmutex) the chance to try the fixup of the pi_state. So once we
+	 * are back from handling the fault we need to check the pi_state after
+	 * reacquiring the locks and before trying to do another fixup. When
+	 * the fixup has been done already we simply return.
 	 *
 	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
 	 * drop hb->lock since the caller owns the hb -> futex_q relation.
 	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
-handle_fault:
+handle_err:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
-	ret = fault_in_user_writeable(uaddr);
+	switch (err) {
+	case -EFAULT:
+		ret = fault_in_user_writeable(uaddr);
+		break;
+
+	case -EAGAIN:
+		cond_resched();
+		ret = 0;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		ret = err;
+		break;
+	}
 
 	spin_lock(q->lock_ptr);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
@@ -3041,10 +3058,8 @@ retry:
 		 * A unconditional UNLOCK_PI op raced against a waiter
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
-		if (ret == -EAGAIN) {
-			put_futex_key(&key);
-			goto retry;
-		}
+		if (ret == -EAGAIN)
+			goto pi_retry;
 		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
@@ -3059,9 +3074,19 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+	if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
 		spin_unlock(&hb->lock);
-		goto pi_faulted;
+		switch (ret) {
+		case -EFAULT:
+			goto pi_faulted;
+
+		case -EAGAIN:
+			goto pi_retry;
+
+		default:
+			WARN_ON_ONCE(1);
+			goto out_putkey;
+		}
 	}
 
 	/*
@@ -3075,6 +3100,11 @@ out_putkey:
 	put_futex_key(&key);
 	return ret;
 
+pi_retry:
+	put_futex_key(&key);
+	cond_resched();
+	goto retry;
+
 pi_faulted:
 	put_futex_key(&key);
 
@@ -3435,6 +3465,7 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
 {
 	u32 uval, uninitialized_var(nval), mval;
+	int err;
 
 	/* Futex address must be 32bit aligned */
 	if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
@@ -3444,42 +3475,57 @@ retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
-	if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
-		/*
-		 * Ok, this dying thread is truly holding a futex
-		 * of interest. Set the OWNER_DIED bit atomically
-		 * via cmpxchg, and if the value had FUTEX_WAITERS
-		 * set, wake up a waiter (if any). (We have to do a
-		 * futex_wake() even if OWNER_DIED is already set -
-		 * to handle the rare but possible case of recursive
-		 * thread-death.) The rest of the cleanup is done in
-		 * userspace.
-		 */
-		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		/*
-		 * We are not holding a lock here, but we want to have
-		 * the pagefault_disable/enable() protection because
-		 * we want to handle the fault gracefully. If the
-		 * access fails we try to fault in the futex with R/W
-		 * verification via get_user_pages. get_user() above
-		 * does not guarantee R/W access. If that fails we
-		 * give up and leave the futex locked.
-		 */
-		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
+		return 0;
+
+	/*
+	 * Ok, this dying thread is truly holding a futex
+	 * of interest. Set the OWNER_DIED bit atomically
+	 * via cmpxchg, and if the value had FUTEX_WAITERS
+	 * set, wake up a waiter (if any). (We have to do a
+	 * futex_wake() even if OWNER_DIED is already set -
+	 * to handle the rare but possible case of recursive
+	 * thread-death.) The rest of the cleanup is done in
+	 * userspace.
+	 */
+	mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+
+	/*
+	 * We are not holding a lock here, but we want to have
+	 * the pagefault_disable/enable() protection because
+	 * we want to handle the fault gracefully. If the
+	 * access fails we try to fault in the futex with R/W
+	 * verification via get_user_pages. get_user() above
+	 * does not guarantee R/W access. If that fails we
+	 * give up and leave the futex locked.
+	 */
+	if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) {
+		switch (err) {
+		case -EFAULT:
 			if (fault_in_user_writeable(uaddr))
 				return -1;
 			goto retry;
-		}
-		if (nval != uval)
+
+		case -EAGAIN:
+			cond_resched();
 			goto retry;
 
-		/*
-		 * Wake robust non-PI futexes here. The wakeup of
-		 * PI futexes happens in exit_pi_state():
-		 */
-		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		default:
+			WARN_ON_ONCE(1);
+			return err;
+		}
 	}
+
+	if (nval != uval)
+		goto retry;
+
+	/*
+	 * Wake robust non-PI futexes here. The wakeup of
+	 * PI futexes happens in exit_pi_state():
+	 */
+	if (!pi && (uval & FUTEX_WAITERS))
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+
 	return 0;
 }
 
diff --git a/kernel/iomem.c b/kernel/iomem.c
index f7525e14ebc6..93c264444510 100644
--- a/kernel/iomem.c
+++ b/kernel/iomem.c
@@ -55,7 +55,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size,
  *
  * MEMREMAP_WB - matches the default mapping for System RAM on
  * the architecture.  This is usually a read-allocate write-back cache.
- * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
+ * Moreover, if MEMREMAP_WB is specified and the requested remap region is RAM
  * memremap() will bypass establishing a new mapping and instead return
  * a pointer into the direct map.
  *
@@ -86,7 +86,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 	/* Try all mapping types requested until one returns non-NULL */
 	if (flags & MEMREMAP_WB) {
 		/*
-		 * MEMREMAP_WB is special in that it can be satisifed
+		 * MEMREMAP_WB is special in that it can be satisfied
 		 * from the direct map.  Some archs depend on the
 		 * capability of memremap() to autodetect cases where
 		 * the requested range is potentially in System RAM.
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index f808c6a97dcc..f6e5515ee077 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -220,9 +220,8 @@ devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct,
 			    irq_flow_handler_t handler)
 {
 	struct irq_chip_generic *gc;
-	unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type);
 
-	gc = devm_kzalloc(dev, sz, GFP_KERNEL);
+	gc = devm_kzalloc(dev, struct_size(gc, chip_types, num_ct), GFP_KERNEL);
 	if (gc)
 		irq_init_generic_chip(gc, name, num_ct,
 				      irq_base, reg_base, handler);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1401afa0d58a..53a081392115 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -357,8 +357,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	desc->affinity_notify = notify;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
-	if (old_notify)
+	if (old_notify) {
+		cancel_work_sync(&old_notify->work);
 		kref_put(&old_notify->kref, old_notify->release);
+	}
 
 	return 0;
 }
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index 1e4cb63a5c82..90c735da15d0 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -9,6 +9,7 @@
 #include <linux/idr.h>
 #include <linux/irq.h>
 #include <linux/math64.h>
+#include <linux/log2.h>
 
 #include <trace/events/irq.h>
 
@@ -18,16 +19,6 @@ DEFINE_STATIC_KEY_FALSE(irq_timing_enabled);
 
 DEFINE_PER_CPU(struct irq_timings, irq_timings);
 
-struct irqt_stat {
-	u64	next_evt;
-	u64	last_ts;
-	u64	variance;
-	u32	avg;
-	u32	nr_samples;
-	int	anomalies;
-	int	valid;
-};
-
 static DEFINE_IDR(irqt_stats);
 
 void irq_timings_enable(void)
@@ -40,75 +31,360 @@ void irq_timings_disable(void)
 	static_branch_disable(&irq_timing_enabled);
 }
 
-/**
- * irqs_update - update the irq timing statistics with a new timestamp
+/*
+ * The main goal of this algorithm is to predict the next interrupt
+ * occurrence on the current CPU.
+ *
+ * Currently, the interrupt timings are stored in a circular array
+ * buffer every time there is an interrupt, as a tuple: the interrupt
+ * number and the associated timestamp when the event occurred <irq,
+ * timestamp>.
+ *
+ * For every interrupt occurring in a short period of time, we can
+ * measure the elapsed time between the occurrences for the same
+ * interrupt and we end up with a suite of intervals. The experience
+ * showed the interrupts are often coming following a periodic
+ * pattern.
+ *
+ * The objective of the algorithm is to find out this periodic pattern
+ * in a fastest way and use its period to predict the next irq event.
+ *
+ * When the next interrupt event is requested, we are in the situation
+ * where the interrupts are disabled and the circular buffer
+ * containing the timings is filled with the events which happened
+ * after the previous next-interrupt-event request.
+ *
+ * At this point, we read the circular buffer and we fill the irq
+ * related statistics structure. After this step, the circular array
+ * containing the timings is empty because all the values are
+ * dispatched in their corresponding buffers.
+ *
+ * Now for each interrupt, we can predict the next event by using the
+ * suffix array, log interval and exponential moving average
+ *
+ * 1. Suffix array
+ *
+ * Suffix array is an array of all the suffixes of a string. It is
+ * widely used as a data structure for compression, text search, ...
+ * For instance for the word 'banana', the suffixes will be: 'banana'
+ * 'anana' 'nana' 'ana' 'na' 'a'
+ *
+ * Usually, the suffix array is sorted but for our purpose it is
+ * not necessary and won't provide any improvement in the context of
+ * the solved problem where we clearly define the boundaries of the
+ * search by a max period and min period.
+ *
+ * The suffix array will build a suite of intervals of different
+ * length and will look for the repetition of each suite. If the suite
+ * is repeating then we have the period because it is the length of
+ * the suite whatever its position in the buffer.
+ *
+ * 2. Log interval
+ *
+ * We saw the irq timings allow to compute the interval of the
+ * occurrences for a specific interrupt. We can reasonibly assume the
+ * longer is the interval, the higher is the error for the next event
+ * and we can consider storing those interval values into an array
+ * where each slot in the array correspond to an interval at the power
+ * of 2 of the index. For example, index 12 will contain values
+ * between 2^11 and 2^12.
+ *
+ * At the end we have an array of values where at each index defines a
+ * [2^index - 1, 2 ^ index] interval values allowing to store a large
+ * number of values inside a small array.
+ *
+ * For example, if we have the value 1123, then we store it at
+ * ilog2(1123) = 10 index value.
+ *
+ * Storing those value at the specific index is done by computing an
+ * exponential moving average for this specific slot. For instance,
+ * for values 1800, 1123, 1453, ... fall under the same slot (10) and
+ * the exponential moving average is computed every time a new value
+ * is stored at this slot.
+ *
+ * 3. Exponential Moving Average
+ *
+ * The EMA is largely used to track a signal for stocks or as a low
+ * pass filter. The magic of the formula, is it is very simple and the
+ * reactivity of the average can be tuned with the factors called
+ * alpha.
+ *
+ * The higher the alphas are, the faster the average respond to the
+ * signal change. In our case, if a slot in the array is a big
+ * interval, we can have numbers with a big difference between
+ * them. The impact of those differences in the average computation
+ * can be tuned by changing the alpha value.
+ *
+ *
+ *  -- The algorithm --
+ *
+ * We saw the different processing above, now let's see how they are
+ * used together.
+ *
+ * For each interrupt:
+ *	For each interval:
+ *		Compute the index = ilog2(interval)
+ *		Compute a new_ema(buffer[index], interval)
+ *		Store the index in a circular buffer
+ *
+ *	Compute the suffix array of the indexes
+ *
+ *	For each suffix:
+ *		If the suffix is reverse-found 3 times
+ *			Return suffix
+ *
+ *	Return Not found
+ *
+ * However we can not have endless suffix array to be build, it won't
+ * make sense and it will add an extra overhead, so we can restrict
+ * this to a maximum suffix length of 5 and a minimum suffix length of
+ * 2. The experience showed 5 is the majority of the maximum pattern
+ * period found for different devices.
+ *
+ * The result is a pattern finding less than 1us for an interrupt.
  *
- * @irqs: an irqt_stat struct pointer
- * @ts: the new timestamp
+ * Example based on real values:
  *
- * The statistics are computed online, in other words, the code is
- * designed to compute the statistics on a stream of values rather
- * than doing multiple passes on the values to compute the average,
- * then the variance. The integer division introduces a loss of
- * precision but with an acceptable error margin regarding the results
- * we would have with the double floating precision: we are dealing
- * with nanosec, so big numbers, consequently the mantisse is
- * negligeable, especially when converting the time in usec
- * afterwards.
+ * Example 1 : MMC write/read interrupt interval:
  *
- * The computation happens at idle time. When the CPU is not idle, the
- * interrupts' timestamps are stored in the circular buffer, when the
- * CPU goes idle and this routine is called, all the buffer's values
- * are injected in the statistical model continuying to extend the
- * statistics from the previous busy-idle cycle.
+ *	223947, 1240, 1384, 1386, 1386,
+ *	217416, 1236, 1384, 1386, 1387,
+ *	214719, 1241, 1386, 1387, 1384,
+ *	213696, 1234, 1384, 1386, 1388,
+ *	219904, 1240, 1385, 1389, 1385,
+ *	212240, 1240, 1386, 1386, 1386,
+ *	214415, 1236, 1384, 1386, 1387,
+ *	214276, 1234, 1384, 1388, ?
  *
- * The observations showed a device will trigger a burst of periodic
- * interrupts followed by one or two peaks of longer time, for
- * instance when a SD card device flushes its cache, then the periodic
- * intervals occur again. A one second inactivity period resets the
- * stats, that gives us the certitude the statistical values won't
- * exceed 1x10^9, thus the computation won't overflow.
+ * For each element, apply ilog2(value)
  *
- * Basically, the purpose of the algorithm is to watch the periodic
- * interrupts and eliminate the peaks.
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, ?
  *
- * An interrupt is considered periodically stable if the interval of
- * its occurences follow the normal distribution, thus the values
- * comply with:
+ * Max period of 5, we take the last (max_period * 3) 15 elements as
+ * we can be confident if the pattern repeats itself three times it is
+ * a repeating pattern.
  *
- *      avg - 3 x stddev < value < avg + 3 x stddev
+ *	             8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, ?
  *
- * Which can be simplified to:
+ * Suffixes are:
  *
- *      -3 x stddev < value - avg < 3 x stddev
+ *  1) 8, 15, 8, 8, 8  <- max period
+ *  2) 8, 15, 8, 8
+ *  3) 8, 15, 8
+ *  4) 8, 15           <- min period
  *
- *      abs(value - avg) < 3 x stddev
+ * From there we search the repeating pattern for each suffix.
  *
- * In order to save a costly square root computation, we use the
- * variance. For the record, stddev = sqrt(variance). The equation
- * above becomes:
+ * buffer: 8, 15, 8, 8, 8, 8, 15, 8, 8, 8, 8, 15, 8, 8, 8
+ *         |   |  |  |  |  |   |  |  |  |  |   |  |  |  |
+ *         8, 15, 8, 8, 8  |   |  |  |  |  |   |  |  |  |
+ *                         8, 15, 8, 8, 8  |   |  |  |  |
+ *                                         8, 15, 8, 8, 8
  *
- *      abs(value - avg) < 3 x sqrt(variance)
+ * When moving the suffix, we found exactly 3 matches.
  *
- * And finally we square it:
+ * The first suffix with period 5 is repeating.
  *
- *      (value - avg) ^ 2 < (3 x sqrt(variance)) ^ 2
+ * The next event is (3 * max_period) % suffix_period
  *
- *      (value - avg) x (value - avg) < 9 x variance
+ * In this example, the result 0, so the next event is suffix[0] => 8
  *
- * Statistically speaking, any values out of this interval is
- * considered as an anomaly and is discarded. However, a normal
- * distribution appears when the number of samples is 30 (it is the
- * rule of thumb in statistics, cf. "30 samples" on Internet). When
- * there are three consecutive anomalies, the statistics are resetted.
+ * However, 8 is the index in the array of exponential moving average
+ * which was calculated on the fly when storing the values, so the
+ * interval is ema[8] = 1366
  *
+ *
+ * Example 2:
+ *
+ *	4, 3, 5, 100,
+ *	3, 3, 5, 117,
+ *	4, 4, 5, 112,
+ *	4, 3, 4, 110,
+ *	3, 5, 3, 117,
+ *	4, 4, 5, 112,
+ *	4, 3, 4, 110,
+ *	3, 4, 5, 112,
+ *	4, 3, 4, 110
+ *
+ * ilog2
+ *
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4
+ *
+ * Max period 5:
+ *	   0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4
+ *
+ * Suffixes:
+ *
+ *  1) 0, 0, 4, 0, 0
+ *  2) 0, 0, 4, 0
+ *  3) 0, 0, 4
+ *  4) 0, 0
+ *
+ * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4
+ *         |  |  |  |  |  |  X
+ *         0, 0, 4, 0, 0, |  X
+ *                        0, 0
+ *
+ * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4
+ *         |  |  |  |  |  |  |  |  |  |  |  |  |  |  |
+ *         0, 0, 4, 0, |  |  |  |  |  |  |  |  |  |  |
+ *                     0, 0, 4, 0, |  |  |  |  |  |  |
+ *                                 0, 0, 4, 0, |  |  |
+ *                                             0  0  4
+ *
+ * Pattern is found 3 times, the remaining is 1 which results from
+ * (max_period * 3) % suffix_period. This value is the index in the
+ * suffix arrays. The suffix array for a period 4 has the value 4
+ * at index 1.
+ */
+#define EMA_ALPHA_VAL		64
+#define EMA_ALPHA_SHIFT		7
+
+#define PREDICTION_PERIOD_MIN	2
+#define PREDICTION_PERIOD_MAX	5
+#define PREDICTION_FACTOR	4
+#define PREDICTION_MAX		10 /* 2 ^ PREDICTION_MAX useconds */
+#define PREDICTION_BUFFER_SIZE	16 /* slots for EMAs, hardly more than 16 */
+
+struct irqt_stat {
+	u64	last_ts;
+	u64	ema_time[PREDICTION_BUFFER_SIZE];
+	int	timings[IRQ_TIMINGS_SIZE];
+	int	circ_timings[IRQ_TIMINGS_SIZE];
+	int	count;
+};
+
+/*
+ * Exponential moving average computation
  */
-static void irqs_update(struct irqt_stat *irqs, u64 ts)
+static u64 irq_timings_ema_new(u64 value, u64 ema_old)
+{
+	s64 diff;
+
+	if (unlikely(!ema_old))
+		return value;
+
+	diff = (value - ema_old) * EMA_ALPHA_VAL;
+	/*
+	 * We can use a s64 type variable to be added with the u64
+	 * ema_old variable as this one will never have its topmost
+	 * bit set, it will be always smaller than 2^63 nanosec
+	 * interrupt interval (292 years).
+	 */
+	return ema_old + (diff >> EMA_ALPHA_SHIFT);
+}
+
+static int irq_timings_next_event_index(int *buffer, size_t len, int period_max)
+{
+	int i;
+
+	/*
+	 * The buffer contains the suite of intervals, in a ilog2
+	 * basis, we are looking for a repetition. We point the
+	 * beginning of the search three times the length of the
+	 * period beginning at the end of the buffer. We do that for
+	 * each suffix.
+	 */
+	for (i = period_max; i >= PREDICTION_PERIOD_MIN ; i--) {
+
+		int *begin = &buffer[len - (i * 3)];
+		int *ptr = begin;
+
+		/*
+		 * We look if the suite with period 'i' repeat
+		 * itself. If it is truncated at the end, as it
+		 * repeats we can use the period to find out the next
+		 * element.
+		 */
+		while (!memcmp(ptr, begin, i * sizeof(*ptr))) {
+			ptr += i;
+			if (ptr >= &buffer[len])
+				return begin[((i * 3) % i)];
+		}
+	}
+
+	return -1;
+}
+
+static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now)
+{
+	int index, i, period_max, count, start, min = INT_MAX;
+
+	if ((now - irqs->last_ts) >= NSEC_PER_SEC) {
+		irqs->count = irqs->last_ts = 0;
+		return U64_MAX;
+	}
+
+	/*
+	 * As we want to find three times the repetition, we need a
+	 * number of intervals greater or equal to three times the
+	 * maximum period, otherwise we truncate the max period.
+	 */
+	period_max = irqs->count > (3 * PREDICTION_PERIOD_MAX) ?
+		PREDICTION_PERIOD_MAX : irqs->count / 3;
+
+	/*
+	 * If we don't have enough irq timings for this prediction,
+	 * just bail out.
+	 */
+	if (period_max <= PREDICTION_PERIOD_MIN)
+		return U64_MAX;
+
+	/*
+	 * 'count' will depends if the circular buffer wrapped or not
+	 */
+	count = irqs->count < IRQ_TIMINGS_SIZE ?
+		irqs->count : IRQ_TIMINGS_SIZE;
+
+	start = irqs->count < IRQ_TIMINGS_SIZE ?
+		0 : (irqs->count & IRQ_TIMINGS_MASK);
+
+	/*
+	 * Copy the content of the circular buffer into another buffer
+	 * in order to linearize the buffer instead of dealing with
+	 * wrapping indexes and shifted array which will be prone to
+	 * error and extremelly difficult to debug.
+	 */
+	for (i = 0; i < count; i++) {
+		int index = (start + i) & IRQ_TIMINGS_MASK;
+
+		irqs->timings[i] = irqs->circ_timings[index];
+		min = min_t(int, irqs->timings[i], min);
+	}
+
+	index = irq_timings_next_event_index(irqs->timings, count, period_max);
+	if (index < 0)
+		return irqs->last_ts + irqs->ema_time[min];
+
+	return irqs->last_ts + irqs->ema_time[index];
+}
+
+static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
 {
 	u64 old_ts = irqs->last_ts;
-	u64 variance = 0;
 	u64 interval;
-	s64 diff;
+	int index;
 
 	/*
 	 * The timestamps are absolute time values, we need to compute
@@ -135,87 +411,28 @@ static void irqs_update(struct irqt_stat *irqs, u64 ts)
 	 * want as we need another timestamp to compute an interval.
 	 */
 	if (interval >= NSEC_PER_SEC) {
-		memset(irqs, 0, sizeof(*irqs));
-		irqs->last_ts = ts;
+		irqs->count = 0;
 		return;
 	}
 
 	/*
-	 * Pre-compute the delta with the average as the result is
-	 * used several times in this function.
-	 */
-	diff = interval - irqs->avg;
-
-	/*
-	 * Increment the number of samples.
-	 */
-	irqs->nr_samples++;
-
-	/*
-	 * Online variance divided by the number of elements if there
-	 * is more than one sample.  Normally the formula is division
-	 * by nr_samples - 1 but we assume the number of element will be
-	 * more than 32 and dividing by 32 instead of 31 is enough
-	 * precise.
-	 */
-	if (likely(irqs->nr_samples > 1))
-		variance = irqs->variance >> IRQ_TIMINGS_SHIFT;
-
-	/*
-	 * The rule of thumb in statistics for the normal distribution
-	 * is having at least 30 samples in order to have the model to
-	 * apply. Values outside the interval are considered as an
-	 * anomaly.
-	 */
-	if ((irqs->nr_samples >= 30) && ((diff * diff) > (9 * variance))) {
-		/*
-		 * After three consecutive anomalies, we reset the
-		 * stats as it is no longer stable enough.
-		 */
-		if (irqs->anomalies++ >= 3) {
-			memset(irqs, 0, sizeof(*irqs));
-			irqs->last_ts = ts;
-			return;
-		}
-	} else {
-		/*
-		 * The anomalies must be consecutives, so at this
-		 * point, we reset the anomalies counter.
-		 */
-		irqs->anomalies = 0;
-	}
-
-	/*
-	 * The interrupt is considered stable enough to try to predict
-	 * the next event on it.
+	 * Get the index in the ema table for this interrupt. The
+	 * PREDICTION_FACTOR increase the interval size for the array
+	 * of exponential average.
 	 */
-	irqs->valid = 1;
+	index = likely(interval) ?
+		ilog2((interval >> 10) / PREDICTION_FACTOR) : 0;
 
 	/*
-	 * Online average algorithm:
-	 *
-	 *  new_average = average + ((value - average) / count)
-	 *
-	 * The variance computation depends on the new average
-	 * to be computed here first.
-	 *
+	 * Store the index as an element of the pattern in another
+	 * circular array.
 	 */
-	irqs->avg = irqs->avg + (diff >> IRQ_TIMINGS_SHIFT);
+	irqs->circ_timings[irqs->count & IRQ_TIMINGS_MASK] = index;
 
-	/*
-	 * Online variance algorithm:
-	 *
-	 *  new_variance = variance + (value - average) x (value - new_average)
-	 *
-	 * Warning: irqs->avg is updated with the line above, hence
-	 * 'interval - irqs->avg' is no longer equal to 'diff'
-	 */
-	irqs->variance = irqs->variance + (diff * (interval - irqs->avg));
+	irqs->ema_time[index] = irq_timings_ema_new(interval,
+						    irqs->ema_time[index]);
 
-	/*
-	 * Update the next event
-	 */
-	irqs->next_evt = ts + irqs->avg;
+	irqs->count++;
 }
 
 /**
@@ -259,6 +476,9 @@ u64 irq_timings_next_event(u64 now)
 	 */
 	lockdep_assert_irqs_disabled();
 
+	if (!irqts->count)
+		return next_evt;
+
 	/*
 	 * Number of elements in the circular buffer: If it happens it
 	 * was flushed before, then the number of elements could be
@@ -269,21 +489,19 @@ u64 irq_timings_next_event(u64 now)
 	 * type but with the cost of extra computation in the
 	 * interrupt handler hot path. We choose efficiency.
 	 *
-	 * Inject measured irq/timestamp to the statistical model
-	 * while decrementing the counter because we consume the data
-	 * from our circular buffer.
+	 * Inject measured irq/timestamp to the pattern prediction
+	 * model while decrementing the counter because we consume the
+	 * data from our circular buffer.
 	 */
-	for (i = irqts->count & IRQ_TIMINGS_MASK,
-		     irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
-	     irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
 
-		irq = irq_timing_decode(irqts->values[i], &ts);
+	i = (irqts->count & IRQ_TIMINGS_MASK) - 1;
+	irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
 
+	for (; irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
+		irq = irq_timing_decode(irqts->values[i], &ts);
 		s = idr_find(&irqt_stats, irq);
-		if (s) {
-			irqs = this_cpu_ptr(s);
-			irqs_update(irqs, ts);
-		}
+		if (s)
+			irq_timings_store(irq, this_cpu_ptr(s), ts);
 	}
 
 	/*
@@ -294,26 +512,12 @@ u64 irq_timings_next_event(u64 now)
 
 		irqs = this_cpu_ptr(s);
 
-		if (!irqs->valid)
-			continue;
+		ts = __irq_timings_next_event(irqs, i, now);
+		if (ts <= now)
+			return now;
 
-		if (irqs->next_evt <= now) {
-			irq = i;
-			next_evt = now;
-
-			/*
-			 * This interrupt mustn't use in the future
-			 * until new events occur and update the
-			 * statistics.
-			 */
-			irqs->valid = 0;
-			break;
-		}
-
-		if (irqs->next_evt < next_evt) {
-			irq = i;
-			next_evt = irqs->next_evt;
-		}
+		if (ts < next_evt)
+			next_evt = ts;
 	}
 
 	return next_evt;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 6b7cdf17ccf8..73288914ed5e 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -56,61 +56,70 @@ void __weak arch_irq_work_raise(void)
 	 */
 }
 
-/*
- * Enqueue the irq_work @work on @cpu unless it's already pending
- * somewhere.
- *
- * Can be re-enqueued while the callback is still in progress.
- */
-bool irq_work_queue_on(struct irq_work *work, int cpu)
+/* Enqueue on current CPU, work must already be claimed and preempt disabled */
+static void __irq_work_queue_local(struct irq_work *work)
 {
-	/* All work should have been flushed before going offline */
-	WARN_ON_ONCE(cpu_is_offline(cpu));
-
-#ifdef CONFIG_SMP
-
-	/* Arch remote IPI send/receive backend aren't NMI safe */
-	WARN_ON_ONCE(in_nmi());
+	/* If the work is "lazy", handle it from next tick if any */
+	if (work->flags & IRQ_WORK_LAZY) {
+		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
+		    tick_nohz_tick_stopped())
+			arch_irq_work_raise();
+	} else {
+		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+			arch_irq_work_raise();
+	}
+}
 
+/* Enqueue the irq work @work on the current CPU */
+bool irq_work_queue(struct irq_work *work)
+{
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
 		return false;
 
-	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
-		arch_send_call_function_single_ipi(cpu);
-
-#else /* #ifdef CONFIG_SMP */
-	irq_work_queue(work);
-#endif /* #else #ifdef CONFIG_SMP */
+	/* Queue the entry and raise the IPI if needed. */
+	preempt_disable();
+	__irq_work_queue_local(work);
+	preempt_enable();
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(irq_work_queue);
 
-/* Enqueue the irq work @work on the current CPU */
-bool irq_work_queue(struct irq_work *work)
+/*
+ * Enqueue the irq_work @work on @cpu unless it's already pending
+ * somewhere.
+ *
+ * Can be re-enqueued while the callback is still in progress.
+ */
+bool irq_work_queue_on(struct irq_work *work, int cpu)
 {
+#ifndef CONFIG_SMP
+	return irq_work_queue(work);
+
+#else /* CONFIG_SMP: */
+	/* All work should have been flushed before going offline */
+	WARN_ON_ONCE(cpu_is_offline(cpu));
+
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
 		return false;
 
-	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
-
-	/* If the work is "lazy", handle it from next tick if any */
-	if (work->flags & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
-		    tick_nohz_tick_stopped())
-			arch_irq_work_raise();
+	if (cpu != smp_processor_id()) {
+		/* Arch remote IPI send/receive backend aren't NMI safe */
+		WARN_ON_ONCE(in_nmi());
+		if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+			arch_send_call_function_single_ipi(cpu);
 	} else {
-		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
-			arch_irq_work_raise();
+		__irq_work_queue_local(work);
 	}
-
 	preempt_enable();
 
 	return true;
+#endif /* CONFIG_SMP */
 }
-EXPORT_SYMBOL_GPL(irq_work_queue);
+
 
 bool irq_work_needs_cpu(void)
 {
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index bad96b476eb6..de6efdecc70d 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -202,11 +202,13 @@ void static_key_disable(struct static_key *key)
 }
 EXPORT_SYMBOL_GPL(static_key_disable);
 
-static void __static_key_slow_dec_cpuslocked(struct static_key *key,
-					   unsigned long rate_limit,
-					   struct delayed_work *work)
+static bool static_key_slow_try_dec(struct static_key *key)
 {
-	lockdep_assert_cpus_held();
+	int val;
+
+	val = atomic_fetch_add_unless(&key->enabled, -1, 1);
+	if (val == 1)
+		return false;
 
 	/*
 	 * The negative count check is valid even when a negative
@@ -215,63 +217,70 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key,
 	 * returns is unbalanced, because all other static_key_slow_inc()
 	 * instances block while the update is in progress.
 	 */
-	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
-		WARN(atomic_read(&key->enabled) < 0,
-		     "jump label: negative count!\n");
+	WARN(val < 0, "jump label: negative count!\n");
+	return true;
+}
+
+static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+{
+	lockdep_assert_cpus_held();
+
+	if (static_key_slow_try_dec(key))
 		return;
-	}
 
-	if (rate_limit) {
-		atomic_inc(&key->enabled);
-		schedule_delayed_work(work, rate_limit);
-	} else {
+	jump_label_lock();
+	if (atomic_dec_and_test(&key->enabled))
 		jump_label_update(key);
-	}
 	jump_label_unlock();
 }
 
-static void __static_key_slow_dec(struct static_key *key,
-				  unsigned long rate_limit,
-				  struct delayed_work *work)
+static void __static_key_slow_dec(struct static_key *key)
 {
 	cpus_read_lock();
-	__static_key_slow_dec_cpuslocked(key, rate_limit, work);
+	__static_key_slow_dec_cpuslocked(key);
 	cpus_read_unlock();
 }
 
-static void jump_label_update_timeout(struct work_struct *work)
+void jump_label_update_timeout(struct work_struct *work)
 {
 	struct static_key_deferred *key =
 		container_of(work, struct static_key_deferred, work.work);
-	__static_key_slow_dec(&key->key, 0, NULL);
+	__static_key_slow_dec(&key->key);
 }
+EXPORT_SYMBOL_GPL(jump_label_update_timeout);
 
 void static_key_slow_dec(struct static_key *key)
 {
 	STATIC_KEY_CHECK_USE(key);
-	__static_key_slow_dec(key, 0, NULL);
+	__static_key_slow_dec(key);
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec);
 
 void static_key_slow_dec_cpuslocked(struct static_key *key)
 {
 	STATIC_KEY_CHECK_USE(key);
-	__static_key_slow_dec_cpuslocked(key, 0, NULL);
+	__static_key_slow_dec_cpuslocked(key);
 }
 
-void static_key_slow_dec_deferred(struct static_key_deferred *key)
+void __static_key_slow_dec_deferred(struct static_key *key,
+				    struct delayed_work *work,
+				    unsigned long timeout)
 {
 	STATIC_KEY_CHECK_USE(key);
-	__static_key_slow_dec(&key->key, key->timeout, &key->work);
+
+	if (static_key_slow_try_dec(key))
+		return;
+
+	schedule_delayed_work(work, timeout);
 }
-EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
+EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred);
 
-void static_key_deferred_flush(struct static_key_deferred *key)
+void __static_key_deferred_flush(void *key, struct delayed_work *work)
 {
 	STATIC_KEY_CHECK_USE(key);
-	flush_delayed_work(&key->work);
+	flush_delayed_work(work);
 }
-EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+EXPORT_SYMBOL_GPL(__static_key_deferred_flush);
 
 void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index d7140447be75..fd5c95ff9251 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1150,7 +1150,7 @@ int kernel_kexec(void)
 		error = dpm_suspend_end(PMSG_FREEZE);
 		if (error)
 			goto Resume_devices;
-		error = disable_nonboot_cpus();
+		error = suspend_disable_secondary_cpus();
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
@@ -1183,7 +1183,7 @@ int kernel_kexec(void)
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
-		enable_nonboot_cpus();
+		suspend_enable_secondary_cpus();
 		dpm_resume_start(PMSG_RESTORE);
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 96b4179cee6a..99a5b5f46dc5 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -120,8 +120,8 @@ account_global_scheduler_latency(struct task_struct *tsk,
 				break;
 			}
 
-			/* 0 and ULONG_MAX entries mean end of backtrace: */
-			if (record == 0 || record == ULONG_MAX)
+			/* 0 entry marks end of backtrace: */
+			if (!record)
 				break;
 		}
 		if (same) {
@@ -141,20 +141,6 @@ account_global_scheduler_latency(struct task_struct *tsk,
 	memcpy(&latency_record[i], lat, sizeof(struct latency_record));
 }
 
-/*
- * Iterator to store a backtrace into a latency record entry
- */
-static inline void store_stacktrace(struct task_struct *tsk,
-					struct latency_record *lat)
-{
-	struct stack_trace trace;
-
-	memset(&trace, 0, sizeof(trace));
-	trace.max_entries = LT_BACKTRACEDEPTH;
-	trace.entries = &lat->backtrace[0];
-	save_stack_trace_tsk(tsk, &trace);
-}
-
 /**
  * __account_scheduler_latency - record an occurred latency
  * @tsk - the task struct of the task hitting the latency
@@ -191,7 +177,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 	lat.count = 1;
 	lat.time = usecs;
 	lat.max = usecs;
-	store_stacktrace(tsk, &lat);
+
+	stack_trace_save_tsk(tsk, lat.backtrace, LT_BACKTRACEDEPTH, 0);
 
 	raw_spin_lock_irqsave(&latency_lock, flags);
 
@@ -210,8 +197,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 				break;
 			}
 
-			/* 0 and ULONG_MAX entries mean end of backtrace: */
-			if (record == 0 || record == ULONG_MAX)
+			/* 0 entry is end of backtrace */
+			if (!record)
 				break;
 		}
 		if (same) {
@@ -252,10 +239,10 @@ static int lstats_show(struct seq_file *m, void *v)
 				   lr->count, lr->time, lr->max);
 			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 				unsigned long bt = lr->backtrace[q];
+
 				if (!bt)
 					break;
-				if (bt == ULONG_MAX)
-					break;
+
 				seq_printf(m, " %ps", (void *)bt);
 			}
 			seq_puts(m, "\n");
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 9c89ae8b337a..c53370d596be 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -202,15 +202,15 @@ void klp_update_patch_state(struct task_struct *task)
  * Determine whether the given stack trace includes any references to a
  * to-be-patched or to-be-unpatched function.
  */
-static int klp_check_stack_func(struct klp_func *func,
-				struct stack_trace *trace)
+static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
+				unsigned int nr_entries)
 {
 	unsigned long func_addr, func_size, address;
 	struct klp_ops *ops;
 	int i;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		address = trace->entries[i];
+	for (i = 0; i < nr_entries; i++) {
+		address = entries[i];
 
 		if (klp_target_state == KLP_UNPATCHED) {
 			 /*
@@ -254,29 +254,25 @@ static int klp_check_stack_func(struct klp_func *func,
 static int klp_check_stack(struct task_struct *task, char *err_buf)
 {
 	static unsigned long entries[MAX_STACK_ENTRIES];
-	struct stack_trace trace;
 	struct klp_object *obj;
 	struct klp_func *func;
-	int ret;
+	int ret, nr_entries;
 
-	trace.skip = 0;
-	trace.nr_entries = 0;
-	trace.max_entries = MAX_STACK_ENTRIES;
-	trace.entries = entries;
-	ret = save_stack_trace_tsk_reliable(task, &trace);
+	ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
 	WARN_ON_ONCE(ret == -ENOSYS);
-	if (ret) {
+	if (ret < 0) {
 		snprintf(err_buf, STACK_ERR_BUF_SIZE,
 			 "%s: %s:%d has an unreliable stack\n",
 			 __func__, task->comm, task->pid);
 		return ret;
 	}
+	nr_entries = ret;
 
 	klp_for_each_object(klp_transition_patch, obj) {
 		if (!obj->patched)
 			continue;
 		klp_for_each_func(obj, func) {
-			ret = klp_check_stack_func(func, &trace);
+			ret = klp_check_stack_func(func, entries, nr_entries);
 			if (ret) {
 				snprintf(err_buf, STACK_ERR_BUF_SIZE,
 					 "%s: %s:%d is sleeping on function %s\n",
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 392c7f23af76..6fe2f333aecb 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -3,7 +3,7 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
 
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o rwsem-xadd.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@@ -25,8 +25,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
-obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
 obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
+obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o
diff --git a/kernel/locking/lock_events.c b/kernel/locking/lock_events.c
new file mode 100644
index 000000000000..fa2c2f951c6b
--- /dev/null
+++ b/kernel/locking/lock_events.c
@@ -0,0 +1,179 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <waiman.long@hpe.com>
+ */
+
+/*
+ * Collect locking event counts
+ */
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/fs.h>
+
+#include "lock_events.h"
+
+#undef  LOCK_EVENT
+#define LOCK_EVENT(name)	[LOCKEVENT_ ## name] = #name,
+
+#define LOCK_EVENTS_DIR		"lock_event_counts"
+
+/*
+ * When CONFIG_LOCK_EVENT_COUNTS is enabled, event counts of different
+ * types of locks will be reported under the <debugfs>/lock_event_counts/
+ * directory. See lock_events_list.h for the list of available locking
+ * events.
+ *
+ * Writing to the special ".reset_counts" file will reset all the above
+ * locking event counts. This is a very slow operation and so should not
+ * be done frequently.
+ *
+ * These event counts are implemented as per-cpu variables which are
+ * summed and computed whenever the corresponding debugfs files are read. This
+ * minimizes added overhead making the counts usable even in a production
+ * environment.
+ */
+static const char * const lockevent_names[lockevent_num + 1] = {
+
+#include "lock_events_list.h"
+
+	[LOCKEVENT_reset_cnts] = ".reset_counts",
+};
+
+/*
+ * Per-cpu counts
+ */
+DEFINE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * The lockevent_read() function can be overridden.
+ */
+ssize_t __weak lockevent_read(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	char buf[64];
+	int cpu, id, len;
+	u64 sum = 0;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	id = (long)file_inode(file)->i_private;
+
+	if (id >= lockevent_num)
+		return -EBADF;
+
+	for_each_possible_cpu(cpu)
+		sum += per_cpu(lockevents[id], cpu);
+	len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+/*
+ * Function to handle write request
+ *
+ * When idx = reset_cnts, reset all the counts.
+ */
+static ssize_t lockevent_write(struct file *file, const char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	int cpu;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	if ((long)file_inode(file)->i_private != LOCKEVENT_reset_cnts)
+		return count;
+
+	for_each_possible_cpu(cpu) {
+		int i;
+		unsigned long *ptr = per_cpu_ptr(lockevents, cpu);
+
+		for (i = 0 ; i < lockevent_num; i++)
+			WRITE_ONCE(ptr[i], 0);
+	}
+	return count;
+}
+
+/*
+ * Debugfs data structures
+ */
+static const struct file_operations fops_lockevent = {
+	.read = lockevent_read,
+	.write = lockevent_write,
+	.llseek = default_llseek,
+};
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#include <asm/paravirt.h>
+
+static bool __init skip_lockevent(const char *name)
+{
+	static int pv_on __initdata = -1;
+
+	if (pv_on < 0)
+		pv_on = !pv_is_native_spin_unlock();
+	/*
+	 * Skip PV qspinlock events on bare metal.
+	 */
+	if (!pv_on && !memcmp(name, "pv_", 3))
+		return true;
+	return false;
+}
+#else
+static inline bool skip_lockevent(const char *name)
+{
+	return false;
+}
+#endif
+
+/*
+ * Initialize debugfs for the locking event counts.
+ */
+static int __init init_lockevent_counts(void)
+{
+	struct dentry *d_counts = debugfs_create_dir(LOCK_EVENTS_DIR, NULL);
+	int i;
+
+	if (!d_counts)
+		goto out;
+
+	/*
+	 * Create the debugfs files
+	 *
+	 * As reading from and writing to the stat files can be slow, only
+	 * root is allowed to do the read/write to limit impact to system
+	 * performance.
+	 */
+	for (i = 0; i < lockevent_num; i++) {
+		if (skip_lockevent(lockevent_names[i]))
+			continue;
+		if (!debugfs_create_file(lockevent_names[i], 0400, d_counts,
+					 (void *)(long)i, &fops_lockevent))
+			goto fail_undo;
+	}
+
+	if (!debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200,
+				 d_counts, (void *)(long)LOCKEVENT_reset_cnts,
+				 &fops_lockevent))
+		goto fail_undo;
+
+	return 0;
+fail_undo:
+	debugfs_remove_recursive(d_counts);
+out:
+	pr_warn("Could not create '%s' debugfs entries\n", LOCK_EVENTS_DIR);
+	return -ENOMEM;
+}
+fs_initcall(init_lockevent_counts);
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
new file mode 100644
index 000000000000..feb1acc54611
--- /dev/null
+++ b/kernel/locking/lock_events.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef __LOCKING_LOCK_EVENTS_H
+#define __LOCKING_LOCK_EVENTS_H
+
+enum lock_events {
+
+#include "lock_events_list.h"
+
+	lockevent_num,	/* Total number of lock event counts */
+	LOCKEVENT_reset_cnts = lockevent_num,
+};
+
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+/*
+ * Per-cpu counters
+ */
+DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * Increment the PV qspinlock statistical counters
+ */
+static inline void __lockevent_inc(enum lock_events event, bool cond)
+{
+	if (cond)
+		__this_cpu_inc(lockevents[event]);
+}
+
+#define lockevent_inc(ev)	  __lockevent_inc(LOCKEVENT_ ##ev, true)
+#define lockevent_cond_inc(ev, c) __lockevent_inc(LOCKEVENT_ ##ev, c)
+
+static inline void __lockevent_add(enum lock_events event, int inc)
+{
+	__this_cpu_add(lockevents[event], inc);
+}
+
+#define lockevent_add(ev, c)	__lockevent_add(LOCKEVENT_ ##ev, c)
+
+#else  /* CONFIG_LOCK_EVENT_COUNTS */
+
+#define lockevent_inc(ev)
+#define lockevent_add(ev, c)
+#define lockevent_cond_inc(ev, c)
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
+#endif /* __LOCKING_LOCK_EVENTS_H */
diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
new file mode 100644
index 000000000000..ad7668cfc9da
--- /dev/null
+++ b/kernel/locking/lock_events_list.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef LOCK_EVENT
+#define LOCK_EVENT(name)	LOCKEVENT_ ## name,
+#endif
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+/*
+ * Locking events for PV qspinlock.
+ */
+LOCK_EVENT(pv_hash_hops)	/* Average # of hops per hashing operation */
+LOCK_EVENT(pv_kick_unlock)	/* # of vCPU kicks issued at unlock time   */
+LOCK_EVENT(pv_kick_wake)	/* # of vCPU kicks for pv_latency_wake	   */
+LOCK_EVENT(pv_latency_kick)	/* Average latency (ns) of vCPU kick	   */
+LOCK_EVENT(pv_latency_wake)	/* Average latency (ns) of kick-to-wakeup  */
+LOCK_EVENT(pv_lock_stealing)	/* # of lock stealing operations	   */
+LOCK_EVENT(pv_spurious_wakeup)	/* # of spurious wakeups in non-head vCPUs */
+LOCK_EVENT(pv_wait_again)	/* # of wait's after queue head vCPU kick  */
+LOCK_EVENT(pv_wait_early)	/* # of early vCPU wait's		   */
+LOCK_EVENT(pv_wait_head)	/* # of vCPU wait's at the queue head	   */
+LOCK_EVENT(pv_wait_node)	/* # of vCPU wait's at non-head queue node */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+/*
+ * Locking events for qspinlock
+ *
+ * Subtracting lock_use_node[234] from lock_slowpath will give you
+ * lock_use_node1.
+ */
+LOCK_EVENT(lock_pending)	/* # of locking ops via pending code	     */
+LOCK_EVENT(lock_slowpath)	/* # of locking ops via MCS lock queue	     */
+LOCK_EVENT(lock_use_node2)	/* # of locking ops that use 2nd percpu node */
+LOCK_EVENT(lock_use_node3)	/* # of locking ops that use 3rd percpu node */
+LOCK_EVENT(lock_use_node4)	/* # of locking ops that use 4th percpu node */
+LOCK_EVENT(lock_no_node)	/* # of locking ops w/o using percpu node    */
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+/*
+ * Locking events for rwsem
+ */
+LOCK_EVENT(rwsem_sleep_reader)	/* # of reader sleeps			*/
+LOCK_EVENT(rwsem_sleep_writer)	/* # of writer sleeps			*/
+LOCK_EVENT(rwsem_wake_reader)	/* # of reader wakeups			*/
+LOCK_EVENT(rwsem_wake_writer)	/* # of writer wakeups			*/
+LOCK_EVENT(rwsem_opt_wlock)	/* # of write locks opt-spin acquired	*/
+LOCK_EVENT(rwsem_opt_fail)	/* # of failed opt-spinnings		*/
+LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
+LOCK_EVENT(rwsem_rlock_fast)	/* # of fast read locks acquired	*/
+LOCK_EVENT(rwsem_rlock_fail)	/* # of failed read lock acquisitions	*/
+LOCK_EVENT(rwsem_rtrylock)	/* # of read trylock calls		*/
+LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
+LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
+LOCK_EVENT(rwsem_wtrylock)	/* # of write trylock calls		*/
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e221be724fe8..d06190fa5082 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -434,29 +434,14 @@ static void print_lockdep_off(const char *bug_msg)
 #endif
 }
 
-static int save_trace(struct stack_trace *trace)
+static int save_trace(struct lock_trace *trace)
 {
-	trace->nr_entries = 0;
-	trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
-	trace->entries = stack_trace + nr_stack_trace_entries;
-
-	trace->skip = 3;
-
-	save_stack_trace(trace);
-
-	/*
-	 * Some daft arches put -1 at the end to indicate its a full trace.
-	 *
-	 * <rant> this is buggy anyway, since it takes a whole extra entry so a
-	 * complete trace that maxes out the entries provided will be reported
-	 * as incomplete, friggin useless </rant>
-	 */
-	if (trace->nr_entries != 0 &&
-	    trace->entries[trace->nr_entries-1] == ULONG_MAX)
-		trace->nr_entries--;
-
-	trace->max_entries = trace->nr_entries;
+	unsigned long *entries = stack_trace + nr_stack_trace_entries;
+	unsigned int max_entries;
 
+	trace->offset = nr_stack_trace_entries;
+	max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
+	trace->nr_entries = stack_trace_save(entries, max_entries, 3);
 	nr_stack_trace_entries += trace->nr_entries;
 
 	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
@@ -516,11 +501,11 @@ static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit)
 {
 	char c = '.';
 
-	if (class->usage_mask & lock_flag(bit + 2))
+	if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
 		c = '+';
 	if (class->usage_mask & lock_flag(bit)) {
 		c = '-';
-		if (class->usage_mask & lock_flag(bit + 2))
+		if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
 			c = '?';
 	}
 
@@ -649,6 +634,9 @@ static int static_obj(const void *obj)
 		      end   = (unsigned long) &_end,
 		      addr  = (unsigned long) obj;
 
+	if (arch_is_kernel_initmem_freed(addr))
+		return 0;
+
 	/*
 	 * static variable?
 	 */
@@ -1207,7 +1195,7 @@ static struct lock_list *alloc_list_entry(void)
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
 			    unsigned long ip, int distance,
-			    struct stack_trace *trace)
+			    struct lock_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -1426,6 +1414,13 @@ static inline int __bfs_backwards(struct lock_list *src_entry,
  * checking.
  */
 
+static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
+{
+	unsigned long *entries = stack_trace + trace->offset;
+
+	stack_trace_print(entries, trace->nr_entries, spaces);
+}
+
 /*
  * Print a dependency chain entry (this is only done when a deadlock
  * has been detected):
@@ -1438,8 +1433,7 @@ print_circular_bug_entry(struct lock_list *target, int depth)
 	printk("\n-> #%u", depth);
 	print_lock_name(target->class);
 	printk(KERN_CONT ":\n");
-	print_stack_trace(&target->trace, 6);
-
+	print_lock_trace(&target->trace, 6);
 	return 0;
 }
 
@@ -1533,10 +1527,9 @@ static inline int class_equal(struct lock_list *entry, void *data)
 }
 
 static noinline int print_circular_bug(struct lock_list *this,
-				struct lock_list *target,
-				struct held_lock *check_src,
-				struct held_lock *check_tgt,
-				struct stack_trace *trace)
+				       struct lock_list *target,
+				       struct held_lock *check_src,
+				       struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
 	struct lock_list *parent;
@@ -1676,19 +1669,25 @@ check_redundant(struct lock_list *root, struct lock_class *target,
 }
 
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+
+static inline int usage_accumulate(struct lock_list *entry, void *mask)
+{
+	*(unsigned long *)mask |= entry->class->usage_mask;
+
+	return 0;
+}
+
 /*
  * Forwards and backwards subgraph searching, for the purposes of
  * proving that two subgraphs can be connected by a new dependency
  * without creating any illegal irq-safe -> irq-unsafe lock dependency.
  */
 
-static inline int usage_match(struct lock_list *entry, void *bit)
+static inline int usage_match(struct lock_list *entry, void *mask)
 {
-	return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit);
+	return entry->class->usage_mask & *(unsigned long *)mask;
 }
 
-
-
 /*
  * Find a node in the forwards-direction dependency sub-graph starting
  * at @root->class that matches @bit.
@@ -1700,14 +1699,14 @@ static inline int usage_match(struct lock_list *entry, void *bit)
  * Return <0 on error.
  */
 static int
-find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_forwards(struct lock_list *root, unsigned long usage_mask,
 			struct lock_list **target_entry)
 {
 	int result;
 
 	debug_atomic_inc(nr_find_usage_forwards_checks);
 
-	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
+	result = __bfs_forwards(root, &usage_mask, usage_match, target_entry);
 
 	return result;
 }
@@ -1723,14 +1722,14 @@ find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
  * Return <0 on error.
  */
 static int
-find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_backwards(struct lock_list *root, unsigned long usage_mask,
 			struct lock_list **target_entry)
 {
 	int result;
 
 	debug_atomic_inc(nr_find_usage_backwards_checks);
 
-	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
+	result = __bfs_backwards(root, &usage_mask, usage_match, target_entry);
 
 	return result;
 }
@@ -1752,7 +1751,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 
 			len += printk("%*s   %s", depth, "", usage_str[bit]);
 			len += printk(KERN_CONT " at:\n");
-			print_stack_trace(class->usage_traces + bit, len);
+			print_lock_trace(class->usage_traces + bit, len);
 		}
 	}
 	printk("%*s }\n", depth, "");
@@ -1777,7 +1776,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf,
 	do {
 		print_lock_class_header(entry->class, depth);
 		printk("%*s ... acquired at:\n", depth, "");
-		print_stack_trace(&entry->trace, 2);
+		print_lock_trace(&entry->trace, 2);
 		printk("\n");
 
 		if (depth == 0 && (entry != root)) {
@@ -1890,14 +1889,14 @@ print_bad_irq_dependency(struct task_struct *curr,
 	print_lock_name(backwards_entry->class);
 	pr_warn("\n... which became %s-irq-safe at:\n", irqclass);
 
-	print_stack_trace(backwards_entry->class->usage_traces + bit1, 1);
+	print_lock_trace(backwards_entry->class->usage_traces + bit1, 1);
 
 	pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass);
 	print_lock_name(forwards_entry->class);
 	pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass);
 	pr_warn("...");
 
-	print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
+	print_lock_trace(forwards_entry->class->usage_traces + bit2, 1);
 
 	pr_warn("\nother info that might help us debug this:\n\n");
 	print_irq_lock_scenario(backwards_entry, forwards_entry,
@@ -1922,39 +1921,6 @@ print_bad_irq_dependency(struct task_struct *curr,
 	return 0;
 }
 
-static int
-check_usage(struct task_struct *curr, struct held_lock *prev,
-	    struct held_lock *next, enum lock_usage_bit bit_backwards,
-	    enum lock_usage_bit bit_forwards, const char *irqclass)
-{
-	int ret;
-	struct lock_list this, that;
-	struct lock_list *uninitialized_var(target_entry);
-	struct lock_list *uninitialized_var(target_entry1);
-
-	this.parent = NULL;
-
-	this.class = hlock_class(prev);
-	ret = find_usage_backwards(&this, bit_backwards, &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
-	if (ret == 1)
-		return ret;
-
-	that.parent = NULL;
-	that.class = hlock_class(next);
-	ret = find_usage_forwards(&that, bit_forwards, &target_entry1);
-	if (ret < 0)
-		return print_bfs_bug(ret);
-	if (ret == 1)
-		return ret;
-
-	return print_bad_irq_dependency(curr, &this, &that,
-			target_entry, target_entry1,
-			prev, next,
-			bit_backwards, bit_forwards, irqclass);
-}
-
 static const char *state_names[] = {
 #define LOCKDEP_STATE(__STATE) \
 	__stringify(__STATE),
@@ -1971,9 +1937,19 @@ static const char *state_rnames[] = {
 
 static inline const char *state_name(enum lock_usage_bit bit)
 {
-	return (bit & LOCK_USAGE_READ_MASK) ? state_rnames[bit >> 2] : state_names[bit >> 2];
+	if (bit & LOCK_USAGE_READ_MASK)
+		return state_rnames[bit >> LOCK_USAGE_DIR_MASK];
+	else
+		return state_names[bit >> LOCK_USAGE_DIR_MASK];
 }
 
+/*
+ * The bit number is encoded like:
+ *
+ *  bit0: 0 exclusive, 1 read lock
+ *  bit1: 0 used in irq, 1 irq enabled
+ *  bit2-n: state
+ */
 static int exclusive_bit(int new_bit)
 {
 	int state = new_bit & LOCK_USAGE_STATE_MASK;
@@ -1985,45 +1961,160 @@ static int exclusive_bit(int new_bit)
 	return state | (dir ^ LOCK_USAGE_DIR_MASK);
 }
 
+/*
+ * Observe that when given a bitmask where each bitnr is encoded as above, a
+ * right shift of the mask transforms the individual bitnrs as -1 and
+ * conversely, a left shift transforms into +1 for the individual bitnrs.
+ *
+ * So for all bits whose number have LOCK_ENABLED_* set (bitnr1 == 1), we can
+ * create the mask with those bit numbers using LOCK_USED_IN_* (bitnr1 == 0)
+ * instead by subtracting the bit number by 2, or shifting the mask right by 2.
+ *
+ * Similarly, bitnr1 == 0 becomes bitnr1 == 1 by adding 2, or shifting left 2.
+ *
+ * So split the mask (note that LOCKF_ENABLED_IRQ_ALL|LOCKF_USED_IN_IRQ_ALL is
+ * all bits set) and recompose with bitnr1 flipped.
+ */
+static unsigned long invert_dir_mask(unsigned long mask)
+{
+	unsigned long excl = 0;
+
+	/* Invert dir */
+	excl |= (mask & LOCKF_ENABLED_IRQ_ALL) >> LOCK_USAGE_DIR_MASK;
+	excl |= (mask & LOCKF_USED_IN_IRQ_ALL) << LOCK_USAGE_DIR_MASK;
+
+	return excl;
+}
+
+/*
+ * As above, we clear bitnr0 (LOCK_*_READ off) with bitmask ops. First, for all
+ * bits with bitnr0 set (LOCK_*_READ), add those with bitnr0 cleared (LOCK_*).
+ * And then mask out all bitnr0.
+ */
+static unsigned long exclusive_mask(unsigned long mask)
+{
+	unsigned long excl = invert_dir_mask(mask);
+
+	/* Strip read */
+	excl |= (excl & LOCKF_IRQ_READ) >> LOCK_USAGE_READ_MASK;
+	excl &= ~LOCKF_IRQ_READ;
+
+	return excl;
+}
+
+/*
+ * Retrieve the _possible_ original mask to which @mask is
+ * exclusive. Ie: this is the opposite of exclusive_mask().
+ * Note that 2 possible original bits can match an exclusive
+ * bit: one has LOCK_USAGE_READ_MASK set, the other has it
+ * cleared. So both are returned for each exclusive bit.
+ */
+static unsigned long original_mask(unsigned long mask)
+{
+	unsigned long excl = invert_dir_mask(mask);
+
+	/* Include read in existing usages */
+	excl |= (excl & LOCKF_IRQ) << LOCK_USAGE_READ_MASK;
+
+	return excl;
+}
+
+/*
+ * Find the first pair of bit match between an original
+ * usage mask and an exclusive usage mask.
+ */
+static int find_exclusive_match(unsigned long mask,
+				unsigned long excl_mask,
+				enum lock_usage_bit *bitp,
+				enum lock_usage_bit *excl_bitp)
+{
+	int bit, excl;
+
+	for_each_set_bit(bit, &mask, LOCK_USED) {
+		excl = exclusive_bit(bit);
+		if (excl_mask & lock_flag(excl)) {
+			*bitp = bit;
+			*excl_bitp = excl;
+			return 0;
+		}
+	}
+	return -1;
+}
+
+/*
+ * Prove that the new dependency does not connect a hardirq-safe(-read)
+ * lock with a hardirq-unsafe lock - to achieve this we search
+ * the backwards-subgraph starting at <prev>, and the
+ * forwards-subgraph starting at <next>:
+ */
 static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
-			   struct held_lock *next, enum lock_usage_bit bit)
+			   struct held_lock *next)
 {
+	unsigned long usage_mask = 0, forward_mask, backward_mask;
+	enum lock_usage_bit forward_bit = 0, backward_bit = 0;
+	struct lock_list *uninitialized_var(target_entry1);
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list this, that;
+	int ret;
+
 	/*
-	 * Prove that the new dependency does not connect a hardirq-safe
-	 * lock with a hardirq-unsafe lock - to achieve this we search
-	 * the backwards-subgraph starting at <prev>, and the
-	 * forwards-subgraph starting at <next>:
+	 * Step 1: gather all hard/soft IRQs usages backward in an
+	 * accumulated usage mask.
 	 */
-	if (!check_usage(curr, prev, next, bit,
-			   exclusive_bit(bit), state_name(bit)))
-		return 0;
+	this.parent = NULL;
+	this.class = hlock_class(prev);
 
-	bit++; /* _READ */
+	ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+
+	usage_mask &= LOCKF_USED_IN_IRQ_ALL;
+	if (!usage_mask)
+		return 1;
 
 	/*
-	 * Prove that the new dependency does not connect a hardirq-safe-read
-	 * lock with a hardirq-unsafe lock - to achieve this we search
-	 * the backwards-subgraph starting at <prev>, and the
-	 * forwards-subgraph starting at <next>:
+	 * Step 2: find exclusive uses forward that match the previous
+	 * backward accumulated mask.
 	 */
-	if (!check_usage(curr, prev, next, bit,
-			   exclusive_bit(bit), state_name(bit)))
-		return 0;
+	forward_mask = exclusive_mask(usage_mask);
 
-	return 1;
-}
+	that.parent = NULL;
+	that.class = hlock_class(next);
 
-static int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
-		struct held_lock *next)
-{
-#define LOCKDEP_STATE(__STATE)						\
-	if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE))	\
-		return 0;
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
+	ret = find_usage_forwards(&that, forward_mask, &target_entry1);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
+		return ret;
 
-	return 1;
+	/*
+	 * Step 3: we found a bad match! Now retrieve a lock from the backward
+	 * list whose usage mask matches the exclusive usage mask from the
+	 * lock found on the forward list.
+	 */
+	backward_mask = original_mask(target_entry1->class->usage_mask);
+
+	ret = find_usage_backwards(&this, backward_mask, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (DEBUG_LOCKS_WARN_ON(ret == 1))
+		return 1;
+
+	/*
+	 * Step 4: narrow down to a pair of incompatible usage bits
+	 * and report it.
+	 */
+	ret = find_exclusive_match(target_entry->class->usage_mask,
+				   target_entry1->class->usage_mask,
+				   &backward_bit, &forward_bit);
+	if (DEBUG_LOCKS_WARN_ON(ret == -1))
+		return 1;
+
+	return print_bad_irq_dependency(curr, &this, &that,
+			target_entry, target_entry1,
+			prev, next,
+			backward_bit, forward_bit,
+			state_name(backward_bit));
 }
 
 static void inc_chains(void)
@@ -2040,9 +2131,8 @@ static void inc_chains(void)
 
 #else
 
-static inline int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
-		struct held_lock *next)
+static inline int check_irq_usage(struct task_struct *curr,
+				  struct held_lock *prev, struct held_lock *next)
 {
 	return 1;
 }
@@ -2170,8 +2260,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance, struct stack_trace *trace,
-	       int (*save)(struct stack_trace *trace))
+	       struct held_lock *next, int distance, struct lock_trace *trace)
 {
 	struct lock_list *uninitialized_var(target_entry);
 	struct lock_list *entry;
@@ -2209,20 +2298,20 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	this.parent = NULL;
 	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
 	if (unlikely(!ret)) {
-		if (!trace->entries) {
+		if (!trace->nr_entries) {
 			/*
-			 * If @save fails here, the printing might trigger
-			 * a WARN but because of the !nr_entries it should
-			 * not do bad things.
+			 * If save_trace fails here, the printing might
+			 * trigger a WARN but because of the !nr_entries it
+			 * should not do bad things.
 			 */
-			save(trace);
+			save_trace(trace);
 		}
-		return print_circular_bug(&this, target_entry, next, prev, trace);
+		return print_circular_bug(&this, target_entry, next, prev);
 	}
 	else if (unlikely(ret < 0))
 		return print_bfs_bug(ret);
 
-	if (!check_prev_add_irq(curr, prev, next))
+	if (!check_irq_usage(curr, prev, next))
 		return 0;
 
 	/*
@@ -2265,7 +2354,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		return print_bfs_bug(ret);
 
 
-	if (!trace->entries && !save(trace))
+	if (!trace->nr_entries && !save_trace(trace))
 		return 0;
 
 	/*
@@ -2297,14 +2386,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 static int
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
+	struct lock_trace trace = { .nr_entries = 0 };
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.max_entries = 0,
-		.entries = NULL,
-		.skip = 0,
-	};
 
 	/*
 	 * Debugging checks.
@@ -2330,7 +2414,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		 * added:
 		 */
 		if (hlock->read != 2 && hlock->check) {
-			int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace);
+			int ret = check_prev_add(curr, hlock, next, distance,
+						 &trace);
 			if (!ret)
 				return 0;
 
@@ -2731,6 +2816,10 @@ static inline int validate_chain(struct task_struct *curr,
 {
 	return 1;
 }
+
+static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
+{
+}
 #endif
 
 /*
@@ -2784,6 +2873,12 @@ static void check_chain_key(struct task_struct *curr)
 #endif
 }
 
+static int mark_lock(struct task_struct *curr, struct held_lock *this,
+		     enum lock_usage_bit new_bit);
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+
+
 static void
 print_usage_bug_scenario(struct held_lock *lock)
 {
@@ -2827,7 +2922,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 	print_lock(this);
 
 	pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]);
-	print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
+	print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1);
 
 	print_irqtrace_events(curr);
 	pr_warn("\nother info that might help us debug this:\n");
@@ -2853,10 +2948,6 @@ valid_state(struct task_struct *curr, struct held_lock *this,
 	return 1;
 }
 
-static int mark_lock(struct task_struct *curr, struct held_lock *this,
-		     enum lock_usage_bit new_bit);
-
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 
 /*
  * print irq inversion bug:
@@ -2936,7 +3027,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
-	ret = find_usage_forwards(&root, bit, &target_entry);
+	ret = find_usage_forwards(&root, lock_flag(bit), &target_entry);
 	if (ret < 0)
 		return print_bfs_bug(ret);
 	if (ret == 1)
@@ -2960,7 +3051,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
-	ret = find_usage_backwards(&root, bit, &target_entry);
+	ret = find_usage_backwards(&root, lock_flag(bit), &target_entry);
 	if (ret < 0)
 		return print_bfs_bug(ret);
 	if (ret == 1)
@@ -3015,7 +3106,7 @@ static int (*state_verbose_f[])(struct lock_class *class) = {
 static inline int state_verbose(enum lock_usage_bit bit,
 				struct lock_class *class)
 {
-	return state_verbose_f[bit >> 2](class);
+	return state_verbose_f[bit >> LOCK_USAGE_DIR_MASK](class);
 }
 
 typedef int (*check_usage_f)(struct task_struct *, struct held_lock *,
@@ -3157,7 +3248,7 @@ void lockdep_hardirqs_on(unsigned long ip)
 	/*
 	 * See the fine text that goes along with this variable definition.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled)))
+	if (DEBUG_LOCKS_WARN_ON(early_boot_irqs_disabled))
 		return;
 
 	/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index d4c197425f68..150ec3f0c5b5 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -42,13 +42,35 @@ enum {
 	__LOCKF(USED)
 };
 
-#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ)
-#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
+static const unsigned long LOCKF_ENABLED_IRQ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE |
+static const unsigned long LOCKF_USED_IN_IRQ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE##_READ |
+static const unsigned long LOCKF_ENABLED_IRQ_READ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE##_READ |
+static const unsigned long LOCKF_USED_IN_IRQ_READ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ)
+#define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ)
 
-#define LOCKF_ENABLED_IRQ_READ \
-		(LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ)
-#define LOCKF_USED_IN_IRQ_READ \
-		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
+#define LOCKF_IRQ (LOCKF_ENABLED_IRQ | LOCKF_USED_IN_IRQ)
+#define LOCKF_IRQ_READ (LOCKF_ENABLED_IRQ_READ | LOCKF_USED_IN_IRQ_READ)
 
 /*
  * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index ad40a2617063..80a463d31a8d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -829,7 +829,9 @@ static void lock_torture_cleanup(void)
 						"End of test: SUCCESS");
 
 	kfree(cxt.lwsa);
+	cxt.lwsa = NULL;
 	kfree(cxt.lrsa);
+	cxt.lrsa = NULL;
 
 end:
 	torture_cleanup_end();
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 883cf1b92d90..f17dad99eec8 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -7,6 +7,8 @@
 #include <linux/sched.h>
 #include <linux/errno.h>
 
+#include "rwsem.h"
+
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
 			const char *name, struct lock_class_key *rwsem_key)
 {
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 5e9247dc2515..e14b32c69639 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -395,7 +395,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * 0,1,0 -> 0,0,1
 	 */
 	clear_pending_set_locked(lock);
-	qstat_inc(qstat_lock_pending, true);
+	lockevent_inc(lock_pending);
 	return;
 
 	/*
@@ -403,7 +403,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * queuing.
 	 */
 queue:
-	qstat_inc(qstat_lock_slowpath, true);
+	lockevent_inc(lock_slowpath);
 pv_queue:
 	node = this_cpu_ptr(&qnodes[0].mcs);
 	idx = node->count++;
@@ -419,7 +419,7 @@ pv_queue:
 	 * simple enough.
 	 */
 	if (unlikely(idx >= MAX_NODES)) {
-		qstat_inc(qstat_lock_no_node, true);
+		lockevent_inc(lock_no_node);
 		while (!queued_spin_trylock(lock))
 			cpu_relax();
 		goto release;
@@ -430,7 +430,7 @@ pv_queue:
 	/*
 	 * Keep counts of non-zero index values:
 	 */
-	qstat_inc(qstat_lock_use_node2 + idx - 1, idx);
+	lockevent_cond_inc(lock_use_node2 + idx - 1, idx);
 
 	/*
 	 * Ensure that we increment the head node->count before initialising
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 8f36c27c1794..89bab079e7a4 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -89,7 +89,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
 		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
-			qstat_inc(qstat_pv_lock_stealing, true);
+			lockevent_inc(pv_lock_stealing);
 			return true;
 		}
 		if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
@@ -219,7 +219,7 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
 		hopcnt++;
 		if (!cmpxchg(&he->lock, NULL, lock)) {
 			WRITE_ONCE(he->node, node);
-			qstat_hop(hopcnt);
+			lockevent_pv_hop(hopcnt);
 			return &he->lock;
 		}
 	}
@@ -320,8 +320,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 		smp_store_mb(pn->state, vcpu_halted);
 
 		if (!READ_ONCE(node->locked)) {
-			qstat_inc(qstat_pv_wait_node, true);
-			qstat_inc(qstat_pv_wait_early, wait_early);
+			lockevent_inc(pv_wait_node);
+			lockevent_cond_inc(pv_wait_early, wait_early);
 			pv_wait(&pn->state, vcpu_halted);
 		}
 
@@ -339,7 +339,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 		 * So it is better to spin for a while in the hope that the
 		 * MCS lock will be released soon.
 		 */
-		qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked));
+		lockevent_cond_inc(pv_spurious_wakeup,
+				  !READ_ONCE(node->locked));
 	}
 
 	/*
@@ -416,7 +417,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	/*
 	 * Tracking # of slowpath locking operations
 	 */
-	qstat_inc(qstat_lock_slowpath, true);
+	lockevent_inc(lock_slowpath);
 
 	for (;; waitcnt++) {
 		/*
@@ -464,8 +465,8 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 			}
 		}
 		WRITE_ONCE(pn->state, vcpu_hashed);
-		qstat_inc(qstat_pv_wait_head, true);
-		qstat_inc(qstat_pv_wait_again, waitcnt);
+		lockevent_inc(pv_wait_head);
+		lockevent_cond_inc(pv_wait_again, waitcnt);
 		pv_wait(&lock->locked, _Q_SLOW_VAL);
 
 		/*
@@ -528,7 +529,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	 * vCPU is harmless other than the additional latency in completing
 	 * the unlock.
 	 */
-	qstat_inc(qstat_pv_kick_unlock, true);
+	lockevent_inc(pv_kick_unlock);
 	pv_kick(node->cpu);
 }
 
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index d73f85388d5c..54152670ff24 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -9,262 +9,105 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * Authors: Waiman Long <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
  */
 
-/*
- * When queued spinlock statistical counters are enabled, the following
- * debugfs files will be created for reporting the counter values:
- *
- * <debugfs>/qlockstat/
- *   pv_hash_hops	- average # of hops per hashing operation
- *   pv_kick_unlock	- # of vCPU kicks issued at unlock time
- *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
- *   pv_latency_kick	- average latency (ns) of vCPU kick operation
- *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
- *   pv_lock_stealing	- # of lock stealing operations
- *   pv_spurious_wakeup	- # of spurious wakeups in non-head vCPUs
- *   pv_wait_again	- # of wait's after a queue head vCPU kick
- *   pv_wait_early	- # of early vCPU wait's
- *   pv_wait_head	- # of vCPU wait's at the queue head
- *   pv_wait_node	- # of vCPU wait's at a non-head queue node
- *   lock_pending	- # of locking operations via pending code
- *   lock_slowpath	- # of locking operations via MCS lock queue
- *   lock_use_node2	- # of locking operations that use 2nd per-CPU node
- *   lock_use_node3	- # of locking operations that use 3rd per-CPU node
- *   lock_use_node4	- # of locking operations that use 4th per-CPU node
- *   lock_no_node	- # of locking operations without using per-CPU node
- *
- * Subtracting lock_use_node[234] from lock_slowpath will give you
- * lock_use_node1.
- *
- * Writing to the "reset_counters" file will reset all the above counter
- * values.
- *
- * These statistical counters are implemented as per-cpu variables which are
- * summed and computed whenever the corresponding debugfs files are read. This
- * minimizes added overhead making the counters usable even in a production
- * environment.
- *
- * There may be slight difference between pv_kick_wake and pv_kick_unlock.
- */
-enum qlock_stats {
-	qstat_pv_hash_hops,
-	qstat_pv_kick_unlock,
-	qstat_pv_kick_wake,
-	qstat_pv_latency_kick,
-	qstat_pv_latency_wake,
-	qstat_pv_lock_stealing,
-	qstat_pv_spurious_wakeup,
-	qstat_pv_wait_again,
-	qstat_pv_wait_early,
-	qstat_pv_wait_head,
-	qstat_pv_wait_node,
-	qstat_lock_pending,
-	qstat_lock_slowpath,
-	qstat_lock_use_node2,
-	qstat_lock_use_node3,
-	qstat_lock_use_node4,
-	qstat_lock_no_node,
-	qstat_num,	/* Total number of statistical counters */
-	qstat_reset_cnts = qstat_num,
-};
+#include "lock_events.h"
 
-#ifdef CONFIG_QUEUED_LOCK_STAT
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
 /*
- * Collect pvqspinlock statistics
+ * Collect pvqspinlock locking event counts
  */
-#include <linux/debugfs.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/fs.h>
 
-static const char * const qstat_names[qstat_num + 1] = {
-	[qstat_pv_hash_hops]	   = "pv_hash_hops",
-	[qstat_pv_kick_unlock]     = "pv_kick_unlock",
-	[qstat_pv_kick_wake]       = "pv_kick_wake",
-	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
-	[qstat_pv_latency_kick]	   = "pv_latency_kick",
-	[qstat_pv_latency_wake]    = "pv_latency_wake",
-	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
-	[qstat_pv_wait_again]      = "pv_wait_again",
-	[qstat_pv_wait_early]      = "pv_wait_early",
-	[qstat_pv_wait_head]       = "pv_wait_head",
-	[qstat_pv_wait_node]       = "pv_wait_node",
-	[qstat_lock_pending]       = "lock_pending",
-	[qstat_lock_slowpath]      = "lock_slowpath",
-	[qstat_lock_use_node2]	   = "lock_use_node2",
-	[qstat_lock_use_node3]	   = "lock_use_node3",
-	[qstat_lock_use_node4]	   = "lock_use_node4",
-	[qstat_lock_no_node]	   = "lock_no_node",
-	[qstat_reset_cnts]         = "reset_counters",
-};
+#define EVENT_COUNT(ev)	lockevents[LOCKEVENT_ ## ev]
 
 /*
- * Per-cpu counters
+ * PV specific per-cpu counter
  */
-static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]);
 static DEFINE_PER_CPU(u64, pv_kick_time);
 
 /*
- * Function to read and return the qlock statistical counter values
+ * Function to read and return the PV qspinlock counts.
  *
  * The following counters are handled specially:
- * 1. qstat_pv_latency_kick
+ * 1. pv_latency_kick
  *    Average kick latency (ns) = pv_latency_kick/pv_kick_unlock
- * 2. qstat_pv_latency_wake
+ * 2. pv_latency_wake
  *    Average wake latency (ns) = pv_latency_wake/pv_kick_wake
- * 3. qstat_pv_hash_hops
+ * 3. pv_hash_hops
  *    Average hops/hash = pv_hash_hops/pv_kick_unlock
  */
-static ssize_t qstat_read(struct file *file, char __user *user_buf,
-			  size_t count, loff_t *ppos)
+ssize_t lockevent_read(struct file *file, char __user *user_buf,
+		       size_t count, loff_t *ppos)
 {
 	char buf[64];
-	int cpu, counter, len;
-	u64 stat = 0, kicks = 0;
+	int cpu, id, len;
+	u64 sum = 0, kicks = 0;
 
 	/*
 	 * Get the counter ID stored in file->f_inode->i_private
 	 */
-	counter = (long)file_inode(file)->i_private;
+	id = (long)file_inode(file)->i_private;
 
-	if (counter >= qstat_num)
+	if (id >= lockevent_num)
 		return -EBADF;
 
 	for_each_possible_cpu(cpu) {
-		stat += per_cpu(qstats[counter], cpu);
+		sum += per_cpu(lockevents[id], cpu);
 		/*
-		 * Need to sum additional counter for some of them
+		 * Need to sum additional counters for some of them
 		 */
-		switch (counter) {
+		switch (id) {
 
-		case qstat_pv_latency_kick:
-		case qstat_pv_hash_hops:
-			kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu);
+		case LOCKEVENT_pv_latency_kick:
+		case LOCKEVENT_pv_hash_hops:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_unlock), cpu);
 			break;
 
-		case qstat_pv_latency_wake:
-			kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu);
+		case LOCKEVENT_pv_latency_wake:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_wake), cpu);
 			break;
 		}
 	}
 
-	if (counter == qstat_pv_hash_hops) {
+	if (id == LOCKEVENT_pv_hash_hops) {
 		u64 frac = 0;
 
 		if (kicks) {
-			frac = 100ULL * do_div(stat, kicks);
+			frac = 100ULL * do_div(sum, kicks);
 			frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
 		}
 
 		/*
 		 * Return a X.XX decimal number
 		 */
-		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac);
+		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n",
+			       sum, frac);
 	} else {
 		/*
 		 * Round to the nearest ns
 		 */
-		if ((counter == qstat_pv_latency_kick) ||
-		    (counter == qstat_pv_latency_wake)) {
+		if ((id == LOCKEVENT_pv_latency_kick) ||
+		    (id == LOCKEVENT_pv_latency_wake)) {
 			if (kicks)
-				stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
+				sum = DIV_ROUND_CLOSEST_ULL(sum, kicks);
 		}
-		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat);
+		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
 	}
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
 /*
- * Function to handle write request
- *
- * When counter = reset_cnts, reset all the counter values.
- * Since the counter updates aren't atomic, the resetting is done twice
- * to make sure that the counters are very likely to be all cleared.
- */
-static ssize_t qstat_write(struct file *file, const char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	int cpu;
-
-	/*
-	 * Get the counter ID stored in file->f_inode->i_private
-	 */
-	if ((long)file_inode(file)->i_private != qstat_reset_cnts)
-		return count;
-
-	for_each_possible_cpu(cpu) {
-		int i;
-		unsigned long *ptr = per_cpu_ptr(qstats, cpu);
-
-		for (i = 0 ; i < qstat_num; i++)
-			WRITE_ONCE(ptr[i], 0);
-	}
-	return count;
-}
-
-/*
- * Debugfs data structures
- */
-static const struct file_operations fops_qstat = {
-	.read = qstat_read,
-	.write = qstat_write,
-	.llseek = default_llseek,
-};
-
-/*
- * Initialize debugfs for the qspinlock statistical counters
- */
-static int __init init_qspinlock_stat(void)
-{
-	struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL);
-	int i;
-
-	if (!d_qstat)
-		goto out;
-
-	/*
-	 * Create the debugfs files
-	 *
-	 * As reading from and writing to the stat files can be slow, only
-	 * root is allowed to do the read/write to limit impact to system
-	 * performance.
-	 */
-	for (i = 0; i < qstat_num; i++)
-		if (!debugfs_create_file(qstat_names[i], 0400, d_qstat,
-					 (void *)(long)i, &fops_qstat))
-			goto fail_undo;
-
-	if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
-				 (void *)(long)qstat_reset_cnts, &fops_qstat))
-		goto fail_undo;
-
-	return 0;
-fail_undo:
-	debugfs_remove_recursive(d_qstat);
-out:
-	pr_warn("Could not create 'qlockstat' debugfs entries\n");
-	return -ENOMEM;
-}
-fs_initcall(init_qspinlock_stat);
-
-/*
- * Increment the PV qspinlock statistical counters
- */
-static inline void qstat_inc(enum qlock_stats stat, bool cond)
-{
-	if (cond)
-		this_cpu_inc(qstats[stat]);
-}
-
-/*
  * PV hash hop count
  */
-static inline void qstat_hop(int hopcnt)
+static inline void lockevent_pv_hop(int hopcnt)
 {
-	this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt);
+	this_cpu_add(EVENT_COUNT(pv_hash_hops), hopcnt);
 }
 
 /*
@@ -276,7 +119,7 @@ static inline void __pv_kick(int cpu)
 
 	per_cpu(pv_kick_time, cpu) = start;
 	pv_kick(cpu);
-	this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start);
+	this_cpu_add(EVENT_COUNT(pv_latency_kick), sched_clock() - start);
 }
 
 /*
@@ -289,18 +132,19 @@ static inline void __pv_wait(u8 *ptr, u8 val)
 	*pkick_time = 0;
 	pv_wait(ptr, val);
 	if (*pkick_time) {
-		this_cpu_add(qstats[qstat_pv_latency_wake],
+		this_cpu_add(EVENT_COUNT(pv_latency_wake),
 			     sched_clock() - *pkick_time);
-		qstat_inc(qstat_pv_kick_wake, true);
+		lockevent_inc(pv_kick_wake);
 	}
 }
 
 #define pv_kick(c)	__pv_kick(c)
 #define pv_wait(p, v)	__pv_wait(p, v)
 
-#else /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_LOCK_EVENT_COUNTS */
 
-static inline void qstat_inc(enum qlock_stats stat, bool cond)	{ }
-static inline void qstat_hop(int hopcnt)			{ }
+static inline void lockevent_pv_hop(int hopcnt)	{ }
 
-#endif /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
deleted file mode 100644
index a7ffb2a96ede..000000000000
--- a/kernel/locking/rwsem-spinlock.c
+++ /dev/null
@@ -1,339 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
- * generic spinlock implementation
- *
- * Copyright (c) 2001   David Howells (dhowells@redhat.com).
- * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-#include <linux/rwsem.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/debug.h>
-#include <linux/export.h>
-
-enum rwsem_waiter_type {
-	RWSEM_WAITING_FOR_WRITE,
-	RWSEM_WAITING_FOR_READ
-};
-
-struct rwsem_waiter {
-	struct list_head list;
-	struct task_struct *task;
-	enum rwsem_waiter_type type;
-};
-
-int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	int ret = 1;
-	unsigned long flags;
-
-	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
-		ret = (sem->count != 0);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(rwsem_is_locked);
-
-/*
- * initialise the semaphore
- */
-void __init_rwsem(struct rw_semaphore *sem, const char *name,
-		  struct lock_class_key *key)
-{
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	/*
-	 * Make sure we are not reinitializing a held semaphore:
-	 */
-	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
-	lockdep_init_map(&sem->dep_map, name, key, 0);
-#endif
-	sem->count = 0;
-	raw_spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-EXPORT_SYMBOL(__init_rwsem);
-
-/*
- * handle the lock release when processes blocked on it that can now run
- * - if we come here, then:
- *   - the 'active count' _reached_ zero
- *   - the 'waiting count' is non-zero
- * - the spinlock must be held by the caller
- * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if wakewrite is non-zero
- */
-static inline struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
-{
-	struct rwsem_waiter *waiter;
-	struct task_struct *tsk;
-	int woken;
-
-	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-
-	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
-		if (wakewrite)
-			/* Wake up a writer. Note that we do not grant it the
-			 * lock - it will have to acquire it when it runs. */
-			wake_up_process(waiter->task);
-		goto out;
-	}
-
-	/* grant an infinite number of read locks to the front of the queue */
-	woken = 0;
-	do {
-		struct list_head *next = waiter->list.next;
-
-		list_del(&waiter->list);
-		tsk = waiter->task;
-		/*
-		 * Make sure we do not wakeup the next reader before
-		 * setting the nil condition to grant the next reader;
-		 * otherwise we could miss the wakeup on the other
-		 * side and end up sleeping again. See the pairing
-		 * in rwsem_down_read_failed().
-		 */
-		smp_mb();
-		waiter->task = NULL;
-		wake_up_process(tsk);
-		put_task_struct(tsk);
-		woken++;
-		if (next == &sem->wait_list)
-			break;
-		waiter = list_entry(next, struct rwsem_waiter, list);
-	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
-
-	sem->count += woken;
-
- out:
-	return sem;
-}
-
-/*
- * wake a single writer
- */
-static inline struct rw_semaphore *
-__rwsem_wake_one_writer(struct rw_semaphore *sem)
-{
-	struct rwsem_waiter *waiter;
-
-	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-	wake_up_process(waiter->task);
-
-	return sem;
-}
-
-/*
- * get a read lock on the semaphore
- */
-int __sched __down_read_common(struct rw_semaphore *sem, int state)
-{
-	struct rwsem_waiter waiter;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
-		/* granted */
-		sem->count++;
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		goto out;
-	}
-
-	/* set up my own style of waitqueue */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-	get_task_struct(current);
-
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* wait to be given the lock */
-	for (;;) {
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current))
-			goto out_nolock;
-		set_current_state(state);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		schedule();
-		raw_spin_lock_irqsave(&sem->wait_lock, flags);
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- out:
-	return 0;
-
-out_nolock:
-	/*
-	 * We didn't take the lock, so that there is a writer, which
-	 * is owner or the first waiter of the sem. If it's a waiter,
-	 * it will be woken by current owner. Not need to wake anybody.
-	 */
-	list_del(&waiter.list);
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	return -EINTR;
-}
-
-void __sched __down_read(struct rw_semaphore *sem)
-{
-	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_read_killable(struct rw_semaphore *sem)
-{
-	return __down_read_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-int __down_read_trylock(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	int ret = 0;
-
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
-		/* granted */
-		sem->count++;
-		ret = 1;
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-}
-
-/*
- * get a write lock on the semaphore
- */
-int __sched __down_write_common(struct rw_semaphore *sem, int state)
-{
-	struct rwsem_waiter waiter;
-	unsigned long flags;
-	int ret = 0;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	/* set up my own style of waitqueue */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_WRITE;
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* wait for someone to release the lock */
-	for (;;) {
-		/*
-		 * That is the key to support write lock stealing: allows the
-		 * task already on CPU to get the lock soon rather than put
-		 * itself into sleep and waiting for system woke it or someone
-		 * else in the head of the wait list up.
-		 */
-		if (sem->count == 0)
-			break;
-		if (signal_pending_state(state, current))
-			goto out_nolock;
-
-		set_current_state(state);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		schedule();
-		raw_spin_lock_irqsave(&sem->wait_lock, flags);
-	}
-	/* got the lock */
-	sem->count = -1;
-	list_del(&waiter.list);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-
-out_nolock:
-	list_del(&waiter.list);
-	if (!list_empty(&sem->wait_list) && sem->count >= 0)
-		__rwsem_do_wake(sem, 0);
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return -EINTR;
-}
-
-void __sched __down_write(struct rw_semaphore *sem)
-{
-	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_write_killable(struct rw_semaphore *sem)
-{
-	return __down_write_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-int __down_write_trylock(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count == 0) {
-		/* got the lock */
-		sem->count = -1;
-		ret = 1;
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-}
-
-/*
- * release a read lock on the semaphore
- */
-void __up_read(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (--sem->count == 0 && !list_empty(&sem->wait_list))
-		sem = __rwsem_wake_one_writer(sem);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * release a write lock on the semaphore
- */
-void __up_write(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	sem->count = 0;
-	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, 1);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * downgrade a write lock into a read lock
- * - just wake up any readers at the front of the queue
- */
-void __downgrade_write(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	sem->count = 1;
-	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, 0);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index fbe96341beee..6b3ee9948bf1 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -147,6 +147,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 			 * will notice the queued writer.
 			 */
 			wake_q_add(wake_q, waiter->task);
+			lockevent_inc(rwsem_wake_writer);
 		}
 
 		return;
@@ -176,9 +177,8 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 			goto try_reader_grant;
 		}
 		/*
-		 * It is not really necessary to set it to reader-owned here,
-		 * but it gives the spinners an early indication that the
-		 * readers now have the lock.
+		 * Set it to reader-owned to give spinners an early
+		 * indication that readers now have the lock.
 		 */
 		__rwsem_set_reader_owned(sem, waiter->task);
 	}
@@ -215,6 +215,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 	}
 
 	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+	lockevent_cond_inc(rwsem_wake_reader, woken);
 	if (list_empty(&sem->wait_list)) {
 		/* hit end of list above */
 		adjustment -= RWSEM_WAITING_BIAS;
@@ -225,92 +226,6 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 }
 
 /*
- * Wait for the read lock to be granted
- */
-static inline struct rw_semaphore __sched *
-__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
-	struct rwsem_waiter waiter;
-	DEFINE_WAKE_Q(wake_q);
-
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-
-	raw_spin_lock_irq(&sem->wait_lock);
-	if (list_empty(&sem->wait_list)) {
-		/*
-		 * In case the wait queue is empty and the lock isn't owned
-		 * by a writer, this reader can exit the slowpath and return
-		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
-		 * been set in the count.
-		 */
-		if (atomic_long_read(&sem->count) >= 0) {
-			raw_spin_unlock_irq(&sem->wait_lock);
-			return sem;
-		}
-		adjustment += RWSEM_WAITING_BIAS;
-	}
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* we're now waiting on the lock, but no longer actively locking */
-	count = atomic_long_add_return(adjustment, &sem->count);
-
-	/*
-	 * If there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (count == RWSEM_WAITING_BIAS ||
-	    (count > RWSEM_WAITING_BIAS &&
-	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-
-	/* wait to be given the lock */
-	while (true) {
-		set_current_state(state);
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current)) {
-			raw_spin_lock_irq(&sem->wait_lock);
-			if (waiter.task)
-				goto out_nolock;
-			raw_spin_unlock_irq(&sem->wait_lock);
-			break;
-		}
-		schedule();
-	}
-
-	__set_current_state(TASK_RUNNING);
-	return sem;
-out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	__set_current_state(TASK_RUNNING);
-	return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed_killable);
-
-/*
  * This function must be called with the sem->wait_lock held to prevent
  * race conditions between checking the rwsem wait list and setting the
  * sem->count accordingly.
@@ -346,21 +261,17 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
  */
 static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 {
-	long old, count = atomic_long_read(&sem->count);
-
-	while (true) {
-		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
-			return false;
+	long count = atomic_long_read(&sem->count);
 
-		old = atomic_long_cmpxchg_acquire(&sem->count, count,
-				      count + RWSEM_ACTIVE_WRITE_BIAS);
-		if (old == count) {
+	while (!count || count == RWSEM_WAITING_BIAS) {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
+					count + RWSEM_ACTIVE_WRITE_BIAS)) {
 			rwsem_set_owner(sem);
+			lockevent_inc(rwsem_opt_wlock);
 			return true;
 		}
-
-		count = old;
 	}
+	return false;
 }
 
 static inline bool owner_on_cpu(struct task_struct *owner)
@@ -481,6 +392,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	osq_unlock(&sem->osq);
 done:
 	preempt_enable();
+	lockevent_cond_inc(rwsem_opt_fail, !taken);
 	return taken;
 }
 
@@ -505,6 +417,97 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
 #endif
 
 /*
+ * Wait for the read lock to be granted
+ */
+static inline struct rw_semaphore __sched *
+__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
+{
+	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+	struct rwsem_waiter waiter;
+	DEFINE_WAKE_Q(wake_q);
+
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list)) {
+		/*
+		 * In case the wait queue is empty and the lock isn't owned
+		 * by a writer, this reader can exit the slowpath and return
+		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
+		 * been set in the count.
+		 */
+		if (atomic_long_read(&sem->count) >= 0) {
+			raw_spin_unlock_irq(&sem->wait_lock);
+			rwsem_set_reader_owned(sem);
+			lockevent_inc(rwsem_rlock_fast);
+			return sem;
+		}
+		adjustment += RWSEM_WAITING_BIAS;
+	}
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	count = atomic_long_add_return(adjustment, &sem->count);
+
+	/*
+	 * If there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (count == RWSEM_WAITING_BIAS ||
+	    (count > RWSEM_WAITING_BIAS &&
+	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
+		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+
+	/* wait to be given the lock */
+	while (true) {
+		set_current_state(state);
+		if (!waiter.task)
+			break;
+		if (signal_pending_state(state, current)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (waiter.task)
+				goto out_nolock;
+			raw_spin_unlock_irq(&sem->wait_lock);
+			break;
+		}
+		schedule();
+		lockevent_inc(rwsem_sleep_reader);
+	}
+
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock);
+	return sem;
+out_nolock:
+	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list))
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock_fail);
+	return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed);
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed_killable(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed_killable);
+
+/*
  * Wait until we successfully acquire the write lock
  */
 static inline struct rw_semaphore *
@@ -580,6 +583,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 				goto out_nolock;
 
 			schedule();
+			lockevent_inc(rwsem_sleep_writer);
 			set_current_state(state);
 		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
 
@@ -588,6 +592,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	__set_current_state(TASK_RUNNING);
 	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
+	lockevent_inc(rwsem_wlock);
 
 	return ret;
 
@@ -601,6 +606,7 @@ out_nolock:
 		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	wake_up_q(&wake_q);
+	lockevent_inc(rwsem_wlock_fail);
 
 	return ERR_PTR(-EINTR);
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index e586f0d03ad3..ccbf18f560ff 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -24,7 +24,6 @@ void __sched down_read(struct rw_semaphore *sem)
 	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
-	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read);
@@ -39,7 +38,6 @@ int __sched down_read_killable(struct rw_semaphore *sem)
 		return -EINTR;
 	}
 
-	rwsem_set_reader_owned(sem);
 	return 0;
 }
 
@@ -52,10 +50,8 @@ int down_read_trylock(struct rw_semaphore *sem)
 {
 	int ret = __down_read_trylock(sem);
 
-	if (ret == 1) {
+	if (ret == 1)
 		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
-		rwsem_set_reader_owned(sem);
-	}
 	return ret;
 }
 
@@ -70,7 +66,6 @@ void __sched down_write(struct rw_semaphore *sem)
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write);
@@ -88,7 +83,6 @@ int __sched down_write_killable(struct rw_semaphore *sem)
 		return -EINTR;
 	}
 
-	rwsem_set_owner(sem);
 	return 0;
 }
 
@@ -101,10 +95,8 @@ int down_write_trylock(struct rw_semaphore *sem)
 {
 	int ret = __down_write_trylock(sem);
 
-	if (ret == 1) {
+	if (ret == 1)
 		rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);
-		rwsem_set_owner(sem);
-	}
 
 	return ret;
 }
@@ -117,9 +109,7 @@ EXPORT_SYMBOL(down_write_trylock);
 void up_read(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
 
-	rwsem_clear_reader_owned(sem);
 	__up_read(sem);
 }
 
@@ -131,9 +121,7 @@ EXPORT_SYMBOL(up_read);
 void up_write(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current);
 
-	rwsem_clear_owner(sem);
 	__up_write(sem);
 }
 
@@ -145,9 +133,7 @@ EXPORT_SYMBOL(up_write);
 void downgrade_write(struct rw_semaphore *sem)
 {
 	lock_downgrade(&sem->dep_map, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current);
 
-	rwsem_set_reader_owned(sem);
 	__downgrade_write(sem);
 }
 
@@ -161,7 +147,6 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
-	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read_nested);
@@ -172,7 +157,6 @@ void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(_down_write_nest_lock);
@@ -193,7 +177,6 @@ void down_write_nested(struct rw_semaphore *sem, int subclass)
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write_nested);
@@ -208,7 +191,6 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
 		return -EINTR;
 	}
 
-	rwsem_set_owner(sem);
 	return 0;
 }
 
@@ -216,7 +198,8 @@ EXPORT_SYMBOL(down_write_killable_nested);
 
 void up_read_non_owner(struct rw_semaphore *sem)
 {
-	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
+	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
+				sem);
 	__up_read(sem);
 }
 
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index bad2bca0268b..64877f5294e3 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -23,15 +23,44 @@
  * is involved. Ideally we would like to track all the readers that own
  * a rwsem, but the overhead is simply too big.
  */
+#include "lock_events.h"
+
 #define RWSEM_READER_OWNED	(1UL << 0)
 #define RWSEM_ANONYMOUSLY_OWNED	(1UL << 1)
 
 #ifdef CONFIG_DEBUG_RWSEMS
-# define DEBUG_RWSEMS_WARN_ON(c)	DEBUG_LOCKS_WARN_ON(c)
+# define DEBUG_RWSEMS_WARN_ON(c, sem)	do {			\
+	if (!debug_locks_silent &&				\
+	    WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
+		#c, atomic_long_read(&(sem)->count),		\
+		(long)((sem)->owner), (long)current,		\
+		list_empty(&(sem)->wait_list) ? "" : "not "))	\
+			debug_locks_off();			\
+	} while (0)
+#else
+# define DEBUG_RWSEMS_WARN_ON(c, sem)
+#endif
+
+/*
+ * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
+ * Adapted largely from include/asm-i386/rwsem.h
+ * by Paul Mackerras <paulus@samba.org>.
+ */
+
+/*
+ * the semaphore definition
+ */
+#ifdef CONFIG_64BIT
+# define RWSEM_ACTIVE_MASK		0xffffffffL
 #else
-# define DEBUG_RWSEMS_WARN_ON(c)
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
 #endif
 
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
+#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
  * All writes to owner are protected by WRITE_ONCE() to make sure that
@@ -132,3 +161,144 @@ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
 {
 }
 #endif
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+		rwsem_down_read_failed(sem);
+		DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
+					RWSEM_READER_OWNED), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+		DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
+					RWSEM_READER_OWNED), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+	return 0;
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	/*
+	 * Optimize for the case when the rwsem is not locked at all.
+	 */
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	lockevent_inc(rwsem_rtrylock);
+	do {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					tmp + RWSEM_ACTIVE_READ_BIAS)) {
+			rwsem_set_reader_owned(sem);
+			return 1;
+		}
+	} while (tmp >= 0);
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+					     &sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		rwsem_down_write_failed(sem);
+	rwsem_set_owner(sem);
+}
+
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+					     &sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+	rwsem_set_owner(sem);
+	return 0;
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	lockevent_inc(rwsem_wtrylock);
+	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+		      RWSEM_ACTIVE_WRITE_BIAS);
+	if (tmp == RWSEM_UNLOCKED_VALUE) {
+		rwsem_set_owner(sem);
+		return true;
+	}
+	return false;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
+				sem);
+	rwsem_clear_reader_owned(sem);
+	tmp = atomic_long_dec_return_release(&sem->count);
+	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
+	rwsem_clear_owner(sem);
+	if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
+						    &sem->count) < 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	/*
+	 * When downgrading from exclusive to shared ownership,
+	 * anything inside the write-locked region cannot leak
+	 * into the read side. In contrast, anything in the
+	 * read-locked region is ok to be re-ordered into the
+	 * write side. As such, rely on RELEASE semantics.
+	 */
+	DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
+	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
+	rwsem_set_reader_owned(sem);
+	if (tmp < 0)
+		rwsem_downgrade_wake(sem);
+}
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 936f3d14dd6b..0ff08380f531 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -22,6 +22,13 @@
 #include <linux/debug_locks.h>
 #include <linux/export.h>
 
+#ifdef CONFIG_MMIOWB
+#ifndef arch_mmiowb_state
+DEFINE_PER_CPU(struct mmiowb_state, __mmiowb_state);
+EXPORT_PER_CPU_SYMBOL(__mmiowb_state);
+#endif
+#endif
+
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
  * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 9aa0fccd5d43..399669f7eba8 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -111,6 +111,7 @@ void do_raw_spin_lock(raw_spinlock_t *lock)
 {
 	debug_spin_lock_before(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 	debug_spin_lock_after(lock);
 }
 
@@ -118,8 +119,10 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
 	int ret = arch_spin_trylock(&lock->raw_lock);
 
-	if (ret)
+	if (ret) {
+		mmiowb_spin_lock();
 		debug_spin_lock_after(lock);
+	}
 #ifndef CONFIG_SMP
 	/*
 	 * Must not happen on UP:
@@ -131,6 +134,7 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 
 void do_raw_spin_unlock(raw_spinlock_t *lock)
 {
+	mmiowb_spin_unlock();
 	debug_spin_unlock(lock);
 	arch_spin_unlock(&lock->raw_lock);
 }
diff --git a/kernel/module.c b/kernel/module.c
index 0b9aa8ab89f0..a9020bdd4cf6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -98,6 +98,10 @@ DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
+/* Work queue for freeing init sections in success case */
+static struct work_struct init_free_wq;
+static struct llist_head init_free_list;
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*
@@ -1949,9 +1953,16 @@ void module_enable_ro(const struct module *mod, bool after_init)
 	if (!rodata_enabled)
 		return;
 
+	set_vm_flush_reset_perms(mod->core_layout.base);
+	set_vm_flush_reset_perms(mod->init_layout.base);
 	frob_text(&mod->core_layout, set_memory_ro);
+	frob_text(&mod->core_layout, set_memory_x);
+
 	frob_rodata(&mod->core_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
+	frob_text(&mod->init_layout, set_memory_x);
+
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)
@@ -1967,15 +1978,6 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
-static void module_disable_nx(const struct module *mod)
-{
-	frob_rodata(&mod->core_layout, set_memory_x);
-	frob_ro_after_init(&mod->core_layout, set_memory_x);
-	frob_writable_data(&mod->core_layout, set_memory_x);
-	frob_rodata(&mod->init_layout, set_memory_x);
-	frob_writable_data(&mod->init_layout, set_memory_x);
-}
-
 /* Iterate through all modules and set each module's text as RW */
 void set_all_modules_text_rw(void)
 {
@@ -2019,23 +2021,8 @@ void set_all_modules_text_ro(void)
 	}
 	mutex_unlock(&module_mutex);
 }
-
-static void disable_ro_nx(const struct module_layout *layout)
-{
-	if (rodata_enabled) {
-		frob_text(layout, set_memory_rw);
-		frob_rodata(layout, set_memory_rw);
-		frob_ro_after_init(layout, set_memory_rw);
-	}
-	frob_rodata(layout, set_memory_x);
-	frob_ro_after_init(layout, set_memory_x);
-	frob_writable_data(layout, set_memory_x);
-}
-
 #else
-static void disable_ro_nx(const struct module_layout *layout) { }
 static void module_enable_nx(const struct module *mod) { }
-static void module_disable_nx(const struct module *mod) { }
 #endif
 
 #ifdef CONFIG_LIVEPATCH
@@ -2115,6 +2102,11 @@ static void free_module_elf(struct module *mod)
 
 void __weak module_memfree(void *module_region)
 {
+	/*
+	 * This memory may be RO, and freeing RO memory in an interrupt is not
+	 * supported by vmalloc.
+	 */
+	WARN_ON(in_interrupt());
 	vfree(module_region);
 }
 
@@ -2166,7 +2158,6 @@ static void free_module(struct module *mod)
 	mutex_unlock(&module_mutex);
 
 	/* This may be empty, but that's OK */
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	kfree(mod->args);
@@ -2176,7 +2167,6 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
 
 	/* Finally, free the core (containing the module structure) */
-	disable_ro_nx(&mod->core_layout);
 	module_memfree(mod->core_layout.base);
 }
 
@@ -3415,17 +3405,34 @@ static void do_mod_ctors(struct module *mod)
 
 /* For freeing module_init on success, in case kallsyms traversing */
 struct mod_initfree {
-	struct rcu_head rcu;
+	struct llist_node node;
 	void *module_init;
 };
 
-static void do_free_init(struct rcu_head *head)
+static void do_free_init(struct work_struct *w)
 {
-	struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
-	module_memfree(m->module_init);
-	kfree(m);
+	struct llist_node *pos, *n, *list;
+	struct mod_initfree *initfree;
+
+	list = llist_del_all(&init_free_list);
+
+	synchronize_rcu();
+
+	llist_for_each_safe(pos, n, list) {
+		initfree = container_of(pos, struct mod_initfree, node);
+		module_memfree(initfree->module_init);
+		kfree(initfree);
+	}
 }
 
+static int __init modules_wq_init(void)
+{
+	INIT_WORK(&init_free_wq, do_free_init);
+	init_llist_head(&init_free_list);
+	return 0;
+}
+module_init(modules_wq_init);
+
 /*
  * This is where the real work happens.
  *
@@ -3502,7 +3509,6 @@ static noinline int do_init_module(struct module *mod)
 #endif
 	module_enable_ro(mod, true);
 	mod_tree_remove_init(mod);
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	mod->init_layout.base = NULL;
 	mod->init_layout.size = 0;
@@ -3513,14 +3519,18 @@ static noinline int do_init_module(struct module *mod)
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_rcu(), but we don't want to slow down the success
-	 * path, so use actual RCU here.
+	 * path. module_memfree() cannot be called in an interrupt, so do the
+	 * work and call synchronize_rcu() in a work queue.
+	 *
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work - ie
 	 * rcu_barrier()
 	 */
-	call_rcu(&freeinit->rcu, do_free_init);
+	if (llist_add(&freeinit->node, &init_free_list))
+		schedule_work(&init_free_wq);
+
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
@@ -3817,10 +3827,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* we can't deallocate the module until we clear memory protection */
-	module_disable_ro(mod);
-	module_disable_nx(mod);
-
  ddebug_cleanup:
 	ftrace_release_mod(mod);
 	dynamic_debug_remove(mod, info->debug);
diff --git a/kernel/panic.c b/kernel/panic.c
index 0ae0d7332f12..c1fcaad337b7 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -318,12 +318,7 @@ void panic(const char *fmt, ...)
 	}
 #endif
 #if defined(CONFIG_S390)
-	{
-		unsigned long caller;
-
-		caller = (unsigned long)__builtin_return_address(0);
-		disabled_wait(caller);
-	}
+	disabled_wait();
 #endif
 	pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf);
 	local_irq_enable();
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index f8fe57d1022e..9bbaaab14b36 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -114,6 +114,15 @@ config PM_SLEEP_SMP
 	depends on PM_SLEEP
 	select HOTPLUG_CPU
 
+config PM_SLEEP_SMP_NONZERO_CPU
+	def_bool y
+	depends on PM_SLEEP_SMP
+	depends on ARCH_SUSPEND_NONZERO_CPU
+	---help---
+	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+	will allow nohz_full mask to include CPU0.
+
 config PM_AUTOSLEEP
 	bool "Opportunistic sleep"
 	depends on PM_SLEEP
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index cc105ecd9c07..c8c272df7154 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -280,7 +280,7 @@ static int create_image(int platform_mode)
 	if (error || hibernation_test(TEST_PLATFORM))
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || hibernation_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -322,7 +322,7 @@ static int create_image(int platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	platform_finish(platform_mode);
@@ -416,7 +416,7 @@ int hibernation_snapshot(int platform_mode)
 
 int __weak hibernate_resume_nonboot_cpu_disable(void)
 {
-	return disable_nonboot_cpus();
+	return suspend_disable_secondary_cpus();
 }
 
 /**
@@ -485,7 +485,7 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Cleanup:
 	platform_restore_cleanup(platform_mode);
@@ -563,7 +563,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error)
 		goto Enable_cpus;
 
@@ -585,7 +585,7 @@ int hibernation_platform_enter(void)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	hibernation_ops->finish();
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index f08a1e4ee1d4..bc9558ab1e5b 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1342,8 +1342,9 @@ static inline void do_copy_page(long *dst, long *src)
  * safe_copy_page - Copy a page in a safe way.
  *
  * Check if the page we are going to copy is marked as present in the kernel
- * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set
- * and in that case kernel_page_present() always returns 'true').
+ * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or
+ * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present()
+ * always returns 'true'.
  */
 static void safe_copy_page(void *dst, struct page *s_page)
 {
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index e39059dea38b..ef908c134b34 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -427,7 +427,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (suspend_test(TEST_PLATFORM))
 		goto Platform_wake;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || suspend_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -457,7 +457,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	BUG_ON(irqs_disabled());
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_wake:
 	platform_resume_noirq(state);
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index acee72c0b24b..4b58c907b4b7 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -233,6 +233,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_suppress;
+extern int rcu_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
 
 #define rcu_ftrace_dump_stall_suppress() \
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index c29761152874..7a6890b23c5f 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -494,6 +494,10 @@ rcu_perf_cleanup(void)
 
 	if (torture_cleanup_begin())
 		return;
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
@@ -614,6 +618,7 @@ rcu_perf_init(void)
 		pr_cont("\n");
 		WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
 		firsterr = -EINVAL;
+		cur_ops = NULL;
 		goto unwind;
 	}
 	if (cur_ops->init)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f14d1b18a74f..efaa5b3f4d3f 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -299,7 +299,6 @@ struct rcu_torture_ops {
 	int irq_capable;
 	int can_boost;
 	int extendables;
-	int ext_irq_conflict;
 	const char *name;
 };
 
@@ -592,12 +591,7 @@ static void srcu_torture_init(void)
 
 static void srcu_torture_cleanup(void)
 {
-	static DEFINE_TORTURE_RANDOM(rand);
-
-	if (torture_random(&rand) & 0x800)
-		cleanup_srcu_struct(&srcu_ctld);
-	else
-		cleanup_srcu_struct_quiesced(&srcu_ctld);
+	cleanup_srcu_struct(&srcu_ctld);
 	srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
 }
 
@@ -1160,7 +1154,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	unsigned long randmask2 = randmask1 >> 3;
 
 	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
-	/* Most of the time lots of bits, half the time only one bit. */
+	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
 	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
 	else
@@ -1170,10 +1164,6 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	    ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
 	     (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
 		mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
-	if ((mask & RCUTORTURE_RDR_IRQ) &&
-	    !(mask & cur_ops->ext_irq_conflict) &&
-	    (oldmask & cur_ops->ext_irq_conflict))
-		mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
 	return mask ?: RCUTORTURE_RDR_RCU;
 }
 
@@ -1848,7 +1838,7 @@ static int rcutorture_oom_notify(struct notifier_block *self,
 	WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
 	     __func__);
 	rcu_torture_fwd_cb_hist();
-	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
+	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2);
 	WRITE_ONCE(rcu_fwd_emergency_stop, true);
 	smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
 	pr_info("%s: Freed %lu RCU callbacks.\n",
@@ -2094,6 +2084,10 @@ rcu_torture_cleanup(void)
 			cur_ops->cb_barrier();
 		return;
 	}
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
 
 	rcu_torture_barrier_cleanup();
 	torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
@@ -2267,6 +2261,7 @@ rcu_torture_init(void)
 		pr_cont("\n");
 		WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST));
 		firsterr = -EINVAL;
+		cur_ops = NULL;
 		goto unwind;
 	}
 	if (cur_ops->fqs == NULL && fqs_duration != 0) {
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 5d4a39a6505a..44d6606b8325 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -76,19 +76,16 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
  * Must invoke this after you are finished using a given srcu_struct that
  * was initialized via init_srcu_struct(), else you leak memory.
  */
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
+void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
-	if (quiesced)
-		WARN_ON(work_pending(&ssp->srcu_work));
-	else
-		flush_work(&ssp->srcu_work);
+	flush_work(&ssp->srcu_work);
 	WARN_ON(ssp->srcu_gp_running);
 	WARN_ON(ssp->srcu_gp_waiting);
 	WARN_ON(ssp->srcu_cb_head);
 	WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
 }
-EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Removes the count for the old reader from the appropriate element of
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index a60b8ba9e1ac..9b761e546de8 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -360,8 +360,14 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 	return SRCU_INTERVAL;
 }
 
-/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @ssp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	int cpu;
 
@@ -369,24 +375,14 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
 		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(ssp)))
 		return; /* Just leak it! */
-	if (quiesced) {
-		if (WARN_ON(delayed_work_pending(&ssp->work)))
-			return; /* Just leak it! */
-	} else {
-		flush_delayed_work(&ssp->work);
-	}
+	flush_delayed_work(&ssp->work);
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		if (quiesced) {
-			if (WARN_ON(timer_pending(&sdp->delay_work)))
-				return; /* Just leak it! */
-			if (WARN_ON(work_pending(&sdp->work)))
-				return; /* Just leak it! */
-		} else {
-			del_timer_sync(&sdp->delay_work);
-			flush_work(&sdp->work);
-		}
+		del_timer_sync(&sdp->delay_work);
+		flush_work(&sdp->work);
+		if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist)))
+			return; /* Forgot srcu_barrier(), so just leak it! */
 	}
 	if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(ssp))) {
@@ -397,7 +393,7 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
 	free_percpu(ssp->sda);
 	ssp->sda = NULL;
 }
-EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 911bd9076d43..477b4eb44af5 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -52,7 +52,7 @@ void rcu_qs(void)
 	local_irq_save(flags);
 	if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
 		rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
-		raise_softirq(RCU_SOFTIRQ);
+		raise_softirq_irqoff(RCU_SOFTIRQ);
 	}
 	local_irq_restore(flags);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index acd6ccf56faf..ec77ec336f58 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -102,11 +102,6 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
 /* Number of rcu_nodes at specified level. */
 int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
 int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
-/* panic() on RCU Stall sysctl. */
-int sysctl_panic_on_rcu_stall __read_mostly;
-/* Commandeer a sysrq key to dump RCU's tree. */
-static bool sysrq_rcu;
-module_param(sysrq_rcu, bool, 0444);
 
 /*
  * The rcu_scheduler_active variable is initialized to the value
@@ -149,7 +144,7 @@ static void sync_sched_exp_online_cleanup(int cpu);
 
 /* rcuc/rcub kthread realtime priority */
 static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
-module_param(kthread_prio, int, 0644);
+module_param(kthread_prio, int, 0444);
 
 /* Delay in jiffies for grace-period initialization delays, debug only. */
 
@@ -406,7 +401,7 @@ static bool rcu_kick_kthreads;
  */
 static ulong jiffies_till_sched_qs = ULONG_MAX;
 module_param(jiffies_till_sched_qs, ulong, 0444);
-static ulong jiffies_to_sched_qs; /* Adjusted version of above if not default */
+static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
 module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
 
 /*
@@ -424,6 +419,7 @@ static void adjust_jiffies_till_sched_qs(void)
 		WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
 		return;
 	}
+	/* Otherwise, set to third fqs scan, but bound below on large system. */
 	j = READ_ONCE(jiffies_till_first_fqs) +
 		      2 * READ_ONCE(jiffies_till_next_fqs);
 	if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
@@ -513,74 +509,6 @@ static const char *gp_state_getname(short gs)
 }
 
 /*
- * Show the state of the grace-period kthreads.
- */
-void show_rcu_gp_kthreads(void)
-{
-	int cpu;
-	unsigned long j;
-	unsigned long ja;
-	unsigned long jr;
-	unsigned long jw;
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-
-	j = jiffies;
-	ja = j - READ_ONCE(rcu_state.gp_activity);
-	jr = j - READ_ONCE(rcu_state.gp_req_activity);
-	jw = j - READ_ONCE(rcu_state.gp_wake_time);
-	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
-		rcu_state.name, gp_state_getname(rcu_state.gp_state),
-		rcu_state.gp_state,
-		rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
-		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
-		(long)READ_ONCE(rcu_state.gp_seq),
-		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
-		READ_ONCE(rcu_state.gp_flags));
-	rcu_for_each_node_breadth_first(rnp) {
-		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
-			continue;
-		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
-			(long)rnp->gp_seq_needed);
-		if (!rcu_is_leaf_node(rnp))
-			continue;
-		for_each_leaf_node_possible_cpu(rnp, cpu) {
-			rdp = per_cpu_ptr(&rcu_data, cpu);
-			if (rdp->gpwrap ||
-			    ULONG_CMP_GE(rcu_state.gp_seq,
-					 rdp->gp_seq_needed))
-				continue;
-			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)rdp->gp_seq_needed);
-		}
-	}
-	/* sched_show_task(rcu_state.gp_kthread); */
-}
-EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
-
-/* Dump grace-period-request information due to commandeered sysrq. */
-static void sysrq_show_rcu(int key)
-{
-	show_rcu_gp_kthreads();
-}
-
-static struct sysrq_key_op sysrq_rcudump_op = {
-	.handler = sysrq_show_rcu,
-	.help_msg = "show-rcu(y)",
-	.action_msg = "Show RCU tree",
-	.enable_mask = SYSRQ_ENABLE_DUMP,
-};
-
-static int __init rcu_sysrq_init(void)
-{
-	if (sysrq_rcu)
-		return register_sysrq_key('y', &sysrq_rcudump_op);
-	return 0;
-}
-early_initcall(rcu_sysrq_init);
-
-/*
  * Send along grace-period-related data for rcutorture diagnostics.
  */
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
@@ -1034,27 +962,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 }
 
 /*
- * Handler for the irq_work request posted when a grace period has
- * gone on for too long, but not yet long enough for an RCU CPU
- * stall warning.  Set state appropriately, but just complain if
- * there is unexpected state on entry.
- */
-static void rcu_iw_handler(struct irq_work *iwp)
-{
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-
-	rdp = container_of(iwp, struct rcu_data, rcu_iw);
-	rnp = rdp->mynode;
-	raw_spin_lock_rcu_node(rnp);
-	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
-		rdp->rcu_iw_gp_seq = rnp->gp_seq;
-		rdp->rcu_iw_pending = false;
-	}
-	raw_spin_unlock_rcu_node(rnp);
-}
-
-/*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
@@ -1167,295 +1074,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	return 0;
 }
 
-static void record_gp_stall_check_time(void)
-{
-	unsigned long j = jiffies;
-	unsigned long j1;
-
-	rcu_state.gp_start = j;
-	j1 = rcu_jiffies_till_stall_check();
-	/* Record ->gp_start before ->jiffies_stall. */
-	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
-	rcu_state.jiffies_resched = j + j1 / 2;
-	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
-}
-
-/*
- * Complain about starvation of grace-period kthread.
- */
-static void rcu_check_gp_kthread_starvation(void)
-{
-	struct task_struct *gpk = rcu_state.gp_kthread;
-	unsigned long j;
-
-	j = jiffies - READ_ONCE(rcu_state.gp_activity);
-	if (j > 2 * HZ) {
-		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
-		       rcu_state.name, j,
-		       (long)rcu_seq_current(&rcu_state.gp_seq),
-		       READ_ONCE(rcu_state.gp_flags),
-		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
-		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
-		if (gpk) {
-			pr_err("RCU grace-period kthread stack dump:\n");
-			sched_show_task(gpk);
-			wake_up_process(gpk);
-		}
-	}
-}
-
-/*
- * Dump stacks of all tasks running on stalled CPUs.  First try using
- * NMIs, but fall back to manual remote stack tracing on architectures
- * that don't support NMI-based stack dumps.  The NMI-triggered stack
- * traces are more accurate because they are printed by the target CPU.
- */
-static void rcu_dump_cpu_stacks(void)
-{
-	int cpu;
-	unsigned long flags;
-	struct rcu_node *rnp;
-
-	rcu_for_each_leaf_node(rnp) {
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		for_each_leaf_node_possible_cpu(rnp, cpu)
-			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
-				if (!trigger_single_cpu_backtrace(cpu))
-					dump_cpu_task(cpu);
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	}
-}
-
-/*
- * If too much time has passed in the current grace period, and if
- * so configured, go kick the relevant kthreads.
- */
-static void rcu_stall_kick_kthreads(void)
-{
-	unsigned long j;
-
-	if (!rcu_kick_kthreads)
-		return;
-	j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
-	if (time_after(jiffies, j) && rcu_state.gp_kthread &&
-	    (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
-		WARN_ONCE(1, "Kicking %s grace-period kthread\n",
-			  rcu_state.name);
-		rcu_ftrace_dump(DUMP_ALL);
-		wake_up_process(rcu_state.gp_kthread);
-		WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
-	}
-}
-
-static void panic_on_rcu_stall(void)
-{
-	if (sysctl_panic_on_rcu_stall)
-		panic("RCU Stall\n");
-}
-
-static void print_other_cpu_stall(unsigned long gp_seq)
-{
-	int cpu;
-	unsigned long flags;
-	unsigned long gpa;
-	unsigned long j;
-	int ndetected = 0;
-	struct rcu_node *rnp = rcu_get_root();
-	long totqlen = 0;
-
-	/* Kick and suppress, if so configured. */
-	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
-		return;
-
-	/*
-	 * OK, time to rat on our buddy...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
-	 * RCU CPU stall warnings.
-	 */
-	pr_err("INFO: %s detected stalls on CPUs/tasks:", rcu_state.name);
-	print_cpu_stall_info_begin();
-	rcu_for_each_leaf_node(rnp) {
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		ndetected += rcu_print_task_stall(rnp);
-		if (rnp->qsmask != 0) {
-			for_each_leaf_node_possible_cpu(rnp, cpu)
-				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
-					print_cpu_stall_info(cpu);
-					ndetected++;
-				}
-		}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	}
-
-	print_cpu_stall_info_end();
-	for_each_possible_cpu(cpu)
-		totqlen += rcu_get_n_cbs_cpu(cpu);
-	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
-	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
-	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
-	if (ndetected) {
-		rcu_dump_cpu_stacks();
-
-		/* Complain about tasks blocking the grace period. */
-		rcu_print_detail_task_stall();
-	} else {
-		if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
-			pr_err("INFO: Stall ended before state dump start\n");
-		} else {
-			j = jiffies;
-			gpa = READ_ONCE(rcu_state.gp_activity);
-			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
-			       rcu_state.name, j - gpa, j, gpa,
-			       READ_ONCE(jiffies_till_next_fqs),
-			       rcu_get_root()->qsmask);
-			/* In this case, the current CPU might be at fault. */
-			sched_show_task(current);
-		}
-	}
-	/* Rewrite if needed in case of slow consoles. */
-	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
-		WRITE_ONCE(rcu_state.jiffies_stall,
-			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-
-	rcu_check_gp_kthread_starvation();
-
-	panic_on_rcu_stall();
-
-	rcu_force_quiescent_state();  /* Kick them all. */
-}
-
-static void print_cpu_stall(void)
-{
-	int cpu;
-	unsigned long flags;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	struct rcu_node *rnp = rcu_get_root();
-	long totqlen = 0;
-
-	/* Kick and suppress, if so configured. */
-	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
-		return;
-
-	/*
-	 * OK, time to rat on ourselves...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
-	 * RCU CPU stall warnings.
-	 */
-	pr_err("INFO: %s self-detected stall on CPU", rcu_state.name);
-	print_cpu_stall_info_begin();
-	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
-	print_cpu_stall_info(smp_processor_id());
-	raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
-	print_cpu_stall_info_end();
-	for_each_possible_cpu(cpu)
-		totqlen += rcu_get_n_cbs_cpu(cpu);
-	pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
-		jiffies - rcu_state.gp_start,
-		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
-
-	rcu_check_gp_kthread_starvation();
-
-	rcu_dump_cpu_stacks();
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	/* Rewrite if needed in case of slow consoles. */
-	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
-		WRITE_ONCE(rcu_state.jiffies_stall,
-			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
-	panic_on_rcu_stall();
-
-	/*
-	 * Attempt to revive the RCU machinery by forcing a context switch.
-	 *
-	 * A context switch would normally allow the RCU state machine to make
-	 * progress and it could be we're stuck in kernel space without context
-	 * switches for an entirely unreasonable amount of time.
-	 */
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
-}
-
-static void check_cpu_stall(struct rcu_data *rdp)
-{
-	unsigned long gs1;
-	unsigned long gs2;
-	unsigned long gps;
-	unsigned long j;
-	unsigned long jn;
-	unsigned long js;
-	struct rcu_node *rnp;
-
-	if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
-	    !rcu_gp_in_progress())
-		return;
-	rcu_stall_kick_kthreads();
-	j = jiffies;
-
-	/*
-	 * Lots of memory barriers to reject false positives.
-	 *
-	 * The idea is to pick up rcu_state.gp_seq, then
-	 * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
-	 * another copy of rcu_state.gp_seq.  These values are updated in
-	 * the opposite order with memory barriers (or equivalent) during
-	 * grace-period initialization and cleanup.  Now, a false positive
-	 * can occur if we get an new value of rcu_state.gp_start and a old
-	 * value of rcu_state.jiffies_stall.  But given the memory barriers,
-	 * the only way that this can happen is if one grace period ends
-	 * and another starts between these two fetches.  This is detected
-	 * by comparing the second fetch of rcu_state.gp_seq with the
-	 * previous fetch from rcu_state.gp_seq.
-	 *
-	 * Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
-	 * and rcu_state.gp_start suffice to forestall false positives.
-	 */
-	gs1 = READ_ONCE(rcu_state.gp_seq);
-	smp_rmb(); /* Pick up ->gp_seq first... */
-	js = READ_ONCE(rcu_state.jiffies_stall);
-	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
-	gps = READ_ONCE(rcu_state.gp_start);
-	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
-	gs2 = READ_ONCE(rcu_state.gp_seq);
-	if (gs1 != gs2 ||
-	    ULONG_CMP_LT(j, js) ||
-	    ULONG_CMP_GE(gps, js))
-		return; /* No stall or GP completed since entering function. */
-	rnp = rdp->mynode;
-	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
-	if (rcu_gp_in_progress() &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
-	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
-		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall();
-
-	} else if (rcu_gp_in_progress() &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
-		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
-		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(gs2);
-	}
-}
-
-/**
- * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
- *
- * Set the stall-warning timeout way off into the future, thus preventing
- * any RCU CPU stall-warning messages from appearing in the current set of
- * RCU grace periods.
- *
- * The caller must disable hard irqs.
- */
-void rcu_cpu_stall_reset(void)
-{
-	WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
-}
-
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			      unsigned long gp_seq_req, const char *s)
@@ -1585,7 +1203,7 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 static void rcu_gp_kthread_wake(void)
 {
 	if ((current == rcu_state.gp_kthread &&
-	     !in_interrupt() && !in_serving_softirq()) ||
+	     !in_irq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) ||
 	    !rcu_state.gp_kthread)
 		return;
@@ -2295,11 +1913,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
+	rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
-		rdp->core_needs_qs = false;
-
 		/*
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
@@ -2548,11 +2165,11 @@ void rcu_sched_clock_irq(int user)
 }
 
 /*
- * Scan the leaf rcu_node structures, processing dyntick state for any that
- * have not yet encountered a quiescent state, using the function specified.
- * Also initiate boosting for any threads blocked on the root rcu_node.
- *
- * The caller must have suppressed start of new grace periods.
+ * Scan the leaf rcu_node structures.  For each structure on which all
+ * CPUs have reported a quiescent state and on which there are tasks
+ * blocking the current grace period, initiate RCU priority boosting.
+ * Otherwise, invoke the specified function to check dyntick state for
+ * each CPU that has not yet reported a quiescent state.
  */
 static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 {
@@ -2635,101 +2252,6 @@ void rcu_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
-/*
- * This function checks for grace-period requests that fail to motivate
- * RCU to come out of its idle mode.
- */
-void
-rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
-			 const unsigned long gpssdelay)
-{
-	unsigned long flags;
-	unsigned long j;
-	struct rcu_node *rnp_root = rcu_get_root();
-	static atomic_t warned = ATOMIC_INIT(0);
-
-	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
-		return;
-	j = jiffies; /* Expensive access, and in common case don't get here. */
-	if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
-	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
-	    atomic_read(&warned))
-		return;
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	j = jiffies;
-	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
-	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
-	    atomic_read(&warned)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	/* Hold onto the leaf lock to make others see warned==1. */
-
-	if (rnp_root != rnp)
-		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
-	j = jiffies;
-	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
-	    time_before(j, rcu_state.gp_activity + gpssdelay) ||
-	    atomic_xchg(&warned, 1)) {
-		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	WARN_ON(1);
-	if (rnp_root != rnp)
-		raw_spin_unlock_rcu_node(rnp_root);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	show_rcu_gp_kthreads();
-}
-
-/*
- * Do a forward-progress check for rcutorture.  This is normally invoked
- * due to an OOM event.  The argument "j" gives the time period during
- * which rcutorture would like progress to have been made.
- */
-void rcu_fwd_progress_check(unsigned long j)
-{
-	unsigned long cbs;
-	int cpu;
-	unsigned long max_cbs = 0;
-	int max_cpu = -1;
-	struct rcu_data *rdp;
-
-	if (rcu_gp_in_progress()) {
-		pr_info("%s: GP age %lu jiffies\n",
-			__func__, jiffies - rcu_state.gp_start);
-		show_rcu_gp_kthreads();
-	} else {
-		pr_info("%s: Last GP end %lu jiffies ago\n",
-			__func__, jiffies - rcu_state.gp_end);
-		preempt_disable();
-		rdp = this_cpu_ptr(&rcu_data);
-		rcu_check_gp_start_stall(rdp->mynode, rdp, j);
-		preempt_enable();
-	}
-	for_each_possible_cpu(cpu) {
-		cbs = rcu_get_n_cbs_cpu(cpu);
-		if (!cbs)
-			continue;
-		if (max_cpu < 0)
-			pr_info("%s: callbacks", __func__);
-		pr_cont(" %d: %lu", cpu, cbs);
-		if (cbs <= max_cbs)
-			continue;
-		max_cbs = cbs;
-		max_cpu = cpu;
-	}
-	if (max_cpu >= 0)
-		pr_cont("\n");
-}
-EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
-
 /* Perform RCU core processing work for the current CPU.  */
 static __latent_entropy void rcu_core(struct softirq_action *unused)
 {
@@ -3559,13 +3081,11 @@ static int rcu_pm_notify(struct notifier_block *self,
 	switch (action) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
-		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
-			rcu_expedite_gp();
+		rcu_expedite_gp();
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
-		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
-			rcu_unexpedite_gp();
+		rcu_unexpedite_gp();
 		break;
 	default:
 		break;
@@ -3742,8 +3262,7 @@ static void __init rcu_init_geometry(void)
 		jiffies_till_first_fqs = d;
 	if (jiffies_till_next_fqs == ULONG_MAX)
 		jiffies_till_next_fqs = d;
-	if (jiffies_till_sched_qs == ULONG_MAX)
-		adjust_jiffies_till_sched_qs();
+	adjust_jiffies_till_sched_qs();
 
 	/* If the compile-time values are accurate, just leave. */
 	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
@@ -3858,5 +3377,6 @@ void __init rcu_init(void)
 	srcu_init();
 }
 
+#include "tree_stall.h"
 #include "tree_exp.h"
 #include "tree_plugin.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bb4f995f2d3f..e253d11af3c4 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -393,15 +393,13 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
 
 int rcu_dynticks_snap(struct rcu_data *rdp);
 
-/* Forward declarations for rcutree_plugin.h */
+/* Forward declarations for tree_plugin.h */
 static void rcu_bootup_announce(void);
 static void rcu_qs(void);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_print_detail_task_stall(void);
-static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 static void rcu_flavor_sched_clock_irq(int user);
@@ -418,9 +416,6 @@ static void rcu_prepare_for_idle(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
-static void print_cpu_stall_info_begin(void);
-static void print_cpu_stall_info(int cpu);
-static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static bool rcu_nocb_cpu_needs_barrier(int cpu);
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
@@ -445,3 +440,10 @@ static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
+
+/* Forward declarations for tree_stall.h */
+static void record_gp_stall_check_time(void);
+static void rcu_iw_handler(struct irq_work *iwp);
+static void check_cpu_stall(struct rcu_data *rdp);
+static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+				     const unsigned long gpssdelay);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 4c2a0189e748..9c990df880d1 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -10,6 +10,7 @@
 #include <linux/lockdep.h>
 
 static void rcu_exp_handler(void *unused);
+static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 
 /*
  * Record the start of an expedited grace period.
@@ -633,7 +634,7 @@ static void rcu_exp_handler(void *unused)
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
 			rdp->deferred_qs = true;
-			WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
+			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
@@ -648,7 +649,7 @@ static void rcu_exp_handler(void *unused)
 	 *
 	 * If the CPU is fully enabled (or if some buggy RCU-preempt
 	 * read-side critical section is being used from idle), just
-	 * invoke rcu_preempt_defer_qs() to immediately report the
+	 * invoke rcu_preempt_deferred_qs() to immediately report the
 	 * quiescent state.  We cannot use rcu_read_unlock_special()
 	 * because we are in an interrupt handler, which will cause that
 	 * function to take an early exit without doing anything.
@@ -670,6 +671,27 @@ static void sync_sched_exp_online_cleanup(int cpu)
 {
 }
 
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each that is blocking the current
+ * expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+	int ndetected = 0;
+
+	if (!rnp->exp_tasks)
+		return 0;
+	t = list_entry(rnp->exp_tasks->prev,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		pr_cont(" P%d", t->pid);
+		ndetected++;
+	}
+	return ndetected;
+}
+
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 /* Invoked on each online non-idle CPU for expedited quiescent state. */
@@ -709,6 +731,16 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	WARN_ON_ONCE(ret);
 }
 
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections that are
+ * blocking the current expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+	return 0;
+}
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /**
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 97dba50f6fb2..1102765f91fd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -285,7 +285,7 @@ static void rcu_qs(void)
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
-		current->rcu_read_unlock_special.b.need_qs = false;
+		WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false);
 	}
 }
 
@@ -643,100 +643,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 }
 
 /*
- * Dump detailed information for all tasks blocking the current RCU
- * grace period on the specified rcu_node structure.
- */
-static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
-{
-	unsigned long flags;
-	struct task_struct *t;
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	t = list_entry(rnp->gp_tasks->prev,
-		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		/*
-		 * We could be printing a lot while holding a spinlock.
-		 * Avoid triggering hard lockup.
-		 */
-		touch_nmi_watchdog();
-		sched_show_task(t);
-	}
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-}
-
-/*
- * Dump detailed information for all tasks blocking the current RCU
- * grace period.
- */
-static void rcu_print_detail_task_stall(void)
-{
-	struct rcu_node *rnp = rcu_get_root();
-
-	rcu_print_detail_task_stall_rnp(rnp);
-	rcu_for_each_leaf_node(rnp)
-		rcu_print_detail_task_stall_rnp(rnp);
-}
-
-static void rcu_print_task_stall_begin(struct rcu_node *rnp)
-{
-	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
-	       rnp->level, rnp->grplo, rnp->grphi);
-}
-
-static void rcu_print_task_stall_end(void)
-{
-	pr_cont("\n");
-}
-
-/*
- * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
- */
-static int rcu_print_task_stall(struct rcu_node *rnp)
-{
-	struct task_struct *t;
-	int ndetected = 0;
-
-	if (!rcu_preempt_blocked_readers_cgp(rnp))
-		return 0;
-	rcu_print_task_stall_begin(rnp);
-	t = list_entry(rnp->gp_tasks->prev,
-		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
-		ndetected++;
-	}
-	rcu_print_task_stall_end();
-	return ndetected;
-}
-
-/*
- * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each that is blocking the current
- * expedited grace period.
- */
-static int rcu_print_task_exp_stall(struct rcu_node *rnp)
-{
-	struct task_struct *t;
-	int ndetected = 0;
-
-	if (!rnp->exp_tasks)
-		return 0;
-	t = list_entry(rnp->exp_tasks->prev,
-		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
-		ndetected++;
-	}
-	return ndetected;
-}
-
-/*
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
@@ -804,19 +710,25 @@ static void rcu_flavor_sched_clock_irq(int user)
 
 /*
  * Check for a task exiting while in a preemptible-RCU read-side
- * critical section, clean up if so.  No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
+ * critical section, clean up if so.  No need to issue warnings, as
+ * debug_check_no_locks_held() already does this if lockdep is enabled.
+ * Besides, if this function does anything other than just immediately
+ * return, there was a bug of some sort.  Spewing warnings from this
+ * function is like as not to simply obscure important prior warnings.
  */
 void exit_rcu(void)
 {
 	struct task_struct *t = current;
 
-	if (likely(list_empty(&current->rcu_node_entry)))
+	if (unlikely(!list_empty(&current->rcu_node_entry))) {
+		t->rcu_read_lock_nesting = 1;
+		barrier();
+		WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true);
+	} else if (unlikely(t->rcu_read_lock_nesting)) {
+		t->rcu_read_lock_nesting = 1;
+	} else {
 		return;
-	t->rcu_read_lock_nesting = 1;
-	barrier();
-	t->rcu_read_unlock_special.b.blocked = true;
+	}
 	__rcu_read_unlock();
 	rcu_preempt_deferred_qs(current);
 }
@@ -980,33 +892,6 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 static void rcu_preempt_deferred_qs(struct task_struct *t) { }
 
 /*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections.
- */
-static void rcu_print_detail_task_stall(void)
-{
-}
-
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections.
- */
-static int rcu_print_task_stall(struct rcu_node *rnp)
-{
-	return 0;
-}
-
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections that are
- * blocking the current expedited grace period.
- */
-static int rcu_print_task_exp_stall(struct rcu_node *rnp)
-{
-	return 0;
-}
-
-/*
  * Because there is no preemptible RCU, there can be no readers blocked,
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
@@ -1185,8 +1070,6 @@ static int rcu_boost_kthread(void *arg)
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
-	struct task_struct *t;
-
 	raw_lockdep_assert_held_rcu_node(rnp);
 	if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -1200,9 +1083,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 		if (rnp->exp_tasks == NULL)
 			rnp->boost_tasks = rnp->gp_tasks;
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		t = rnp->boost_kthread_task;
-		if (t)
-			rcu_wake_cond(t, rnp->boost_kthread_status);
+		rcu_wake_cond(rnp->boost_kthread_task,
+			      rnp->boost_kthread_status);
 	} else {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
@@ -1649,98 +1531,6 @@ static void rcu_cleanup_after_idle(void)
 
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
-#ifdef CONFIG_RCU_FAST_NO_HZ
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-
-	sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
-		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-		".l"[rdp->all_lazy],
-		".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
-		".D"[!rdp->tick_nohz_enabled_snap]);
-}
-
-#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	*cp = '\0';
-}
-
-#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-/* Initiate the stall-info list. */
-static void print_cpu_stall_info_begin(void)
-{
-	pr_cont("\n");
-}
-
-/*
- * Print out diagnostic information for the specified stalled CPU.
- *
- * If the specified CPU is aware of the current RCU grace period, then
- * print the number of scheduling clock interrupts the CPU has taken
- * during the time that it has been aware.  Otherwise, print the number
- * of RCU grace periods that this CPU is ignorant of, for example, "1"
- * if the CPU was aware of the previous grace period.
- *
- * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
- */
-static void print_cpu_stall_info(int cpu)
-{
-	unsigned long delta;
-	char fast_no_hz[72];
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-	char *ticks_title;
-	unsigned long ticks_value;
-
-	/*
-	 * We could be printing a lot while holding a spinlock.  Avoid
-	 * triggering hard lockup.
-	 */
-	touch_nmi_watchdog();
-
-	ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
-	if (ticks_value) {
-		ticks_title = "GPs behind";
-	} else {
-		ticks_title = "ticks this GP";
-		ticks_value = rdp->ticks_this_gp;
-	}
-	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
-	       cpu,
-	       "O."[!!cpu_online(cpu)],
-	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
-	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
-	       !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
-			rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
-				"!."[!delta],
-	       ticks_value, ticks_title,
-	       rcu_dynticks_snap(rdp) & 0xfff,
-	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
-	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz);
-}
-
-/* Terminate the stall-info list. */
-static void print_cpu_stall_info_end(void)
-{
-	pr_err("\t");
-}
-
-/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
-static void zero_cpu_stall_ticks(struct rcu_data *rdp)
-{
-	rdp->ticks_this_gp = 0;
-	rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
-	WRITE_ONCE(rdp->last_fqs_resched, jiffies);
-}
-
 #ifdef CONFIG_RCU_NOCB_CPU
 
 /*
@@ -1766,11 +1556,22 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp)
  */
 
 
-/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */
+/*
+ * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
+ * The string after the "rcu_nocbs=" is either "all" for all CPUs, or a
+ * comma-separated list of CPUs and/or CPU ranges.  If an invalid list is
+ * given, a warning is emitted and all CPUs are offloaded.
+ */
 static int __init rcu_nocb_setup(char *str)
 {
 	alloc_bootmem_cpumask_var(&rcu_nocb_mask);
-	cpulist_parse(str, rcu_nocb_mask);
+	if (!strcasecmp(str, "all"))
+		cpumask_setall(rcu_nocb_mask);
+	else
+		if (cpulist_parse(str, rcu_nocb_mask)) {
+			pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
+			cpumask_setall(rcu_nocb_mask);
+		}
 	return 1;
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
new file mode 100644
index 000000000000..f65a73a97323
--- /dev/null
+++ b/kernel/rcu/tree_stall.h
@@ -0,0 +1,709 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * RCU CPU stall warnings for normal RCU grace periods
+ *
+ * Copyright IBM Corporation, 2019
+ *
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
+ */
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Controlling CPU stall warnings, including delay calculation.
+
+/* panic() on RCU Stall sysctl. */
+int sysctl_panic_on_rcu_stall __read_mostly;
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA	       0
+#endif
+
+/* Limit-check stall timeouts specified at boottime and runtime. */
+int rcu_jiffies_till_stall_check(void)
+{
+	int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
+
+	/*
+	 * Limit check must be consistent with the Kconfig limits
+	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
+	 */
+	if (till_stall_check < 3) {
+		WRITE_ONCE(rcu_cpu_stall_timeout, 3);
+		till_stall_check = 3;
+	} else if (till_stall_check > 300) {
+		WRITE_ONCE(rcu_cpu_stall_timeout, 300);
+		till_stall_check = 300;
+	}
+	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
+}
+EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
+
+/* Don't do RCU CPU stall warnings during long sysrq printouts. */
+void rcu_sysrq_start(void)
+{
+	if (!rcu_cpu_stall_suppress)
+		rcu_cpu_stall_suppress = 2;
+}
+
+void rcu_sysrq_end(void)
+{
+	if (rcu_cpu_stall_suppress == 2)
+		rcu_cpu_stall_suppress = 0;
+}
+
+/* Don't print RCU CPU stall warnings during a kernel panic. */
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+	rcu_cpu_stall_suppress = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+	.notifier_call = rcu_panic,
+};
+
+static int __init check_cpu_stall_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+	return 0;
+}
+early_initcall(check_cpu_stall_init);
+
+/* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
+static void panic_on_rcu_stall(void)
+{
+	if (sysctl_panic_on_rcu_stall)
+		panic("RCU Stall\n");
+}
+
+/**
+ * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
+ *
+ * Set the stall-warning timeout way off into the future, thus preventing
+ * any RCU CPU stall-warning messages from appearing in the current set of
+ * RCU grace periods.
+ *
+ * The caller must disable hard irqs.
+ */
+void rcu_cpu_stall_reset(void)
+{
+	WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Interaction with RCU grace periods
+
+/* Start of new grace period, so record stall time (and forcing times). */
+static void record_gp_stall_check_time(void)
+{
+	unsigned long j = jiffies;
+	unsigned long j1;
+
+	rcu_state.gp_start = j;
+	j1 = rcu_jiffies_till_stall_check();
+	/* Record ->gp_start before ->jiffies_stall. */
+	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+	rcu_state.jiffies_resched = j + j1 / 2;
+	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
+}
+
+/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
+static void zero_cpu_stall_ticks(struct rcu_data *rdp)
+{
+	rdp->ticks_this_gp = 0;
+	rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
+	WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+}
+
+/*
+ * If too much time has passed in the current grace period, and if
+ * so configured, go kick the relevant kthreads.
+ */
+static void rcu_stall_kick_kthreads(void)
+{
+	unsigned long j;
+
+	if (!rcu_kick_kthreads)
+		return;
+	j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
+	if (time_after(jiffies, j) && rcu_state.gp_kthread &&
+	    (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
+		WARN_ONCE(1, "Kicking %s grace-period kthread\n",
+			  rcu_state.name);
+		rcu_ftrace_dump(DUMP_ALL);
+		wake_up_process(rcu_state.gp_kthread);
+		WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
+	}
+}
+
+/*
+ * Handler for the irq_work request posted about halfway into the RCU CPU
+ * stall timeout, and used to detect excessive irq disabling.  Set state
+ * appropriately, but just complain if there is unexpected state on entry.
+ */
+static void rcu_iw_handler(struct irq_work *iwp)
+{
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	rdp = container_of(iwp, struct rcu_data, rcu_iw);
+	rnp = rdp->mynode;
+	raw_spin_lock_rcu_node(rnp);
+	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
+		rdp->rcu_iw_gp_seq = rnp->gp_seq;
+		rdp->rcu_iw_pending = false;
+	}
+	raw_spin_unlock_rcu_node(rnp);
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Printing RCU CPU stall warnings
+
+#ifdef CONFIG_PREEMPT
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period on the specified rcu_node structure.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	struct task_struct *t;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	t = list_entry(rnp->gp_tasks->prev,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		/*
+		 * We could be printing a lot while holding a spinlock.
+		 * Avoid triggering hard lockup.
+		 */
+		touch_nmi_watchdog();
+		sched_show_task(t);
+	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each.
+ */
+static int rcu_print_task_stall(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+	int ndetected = 0;
+
+	if (!rcu_preempt_blocked_readers_cgp(rnp))
+		return 0;
+	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
+	       rnp->level, rnp->grplo, rnp->grphi);
+	t = list_entry(rnp->gp_tasks->prev,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		pr_cont(" P%d", t->pid);
+		ndetected++;
+	}
+	pr_cont("\n");
+	return ndetected;
+}
+
+#else /* #ifdef CONFIG_PREEMPT */
+
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static int rcu_print_task_stall(struct rcu_node *rnp)
+{
+	return 0;
+}
+#endif /* #else #ifdef CONFIG_PREEMPT */
+
+/*
+ * Dump stacks of all tasks running on stalled CPUs.  First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps.  The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
+ */
+static void rcu_dump_cpu_stacks(void)
+{
+	int cpu;
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	rcu_for_each_leaf_node(rnp) {
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		for_each_leaf_node_possible_cpu(rnp, cpu)
+			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+				if (!trigger_single_cpu_backtrace(cpu))
+					dump_cpu_task(cpu);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+}
+
+#ifdef CONFIG_RCU_FAST_NO_HZ
+
+static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+
+	sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
+		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
+		".l"[rdp->all_lazy],
+		".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
+		".D"[!!rdp->tick_nohz_enabled_snap]);
+}
+
+#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+
+static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
+{
+	*cp = '\0';
+}
+
+#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
+
+/*
+ * Print out diagnostic information for the specified stalled CPU.
+ *
+ * If the specified CPU is aware of the current RCU grace period, then
+ * print the number of scheduling clock interrupts the CPU has taken
+ * during the time that it has been aware.  Otherwise, print the number
+ * of RCU grace periods that this CPU is ignorant of, for example, "1"
+ * if the CPU was aware of the previous grace period.
+ *
+ * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
+ */
+static void print_cpu_stall_info(int cpu)
+{
+	unsigned long delta;
+	char fast_no_hz[72];
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	char *ticks_title;
+	unsigned long ticks_value;
+
+	/*
+	 * We could be printing a lot while holding a spinlock.  Avoid
+	 * triggering hard lockup.
+	 */
+	touch_nmi_watchdog();
+
+	ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
+	if (ticks_value) {
+		ticks_title = "GPs behind";
+	} else {
+		ticks_title = "ticks this GP";
+		ticks_value = rdp->ticks_this_gp;
+	}
+	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
+	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+	       cpu,
+	       "O."[!!cpu_online(cpu)],
+	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
+	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
+	       !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
+			rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
+				"!."[!delta],
+	       ticks_value, ticks_title,
+	       rcu_dynticks_snap(rdp) & 0xfff,
+	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
+	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
+	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+	       fast_no_hz);
+}
+
+/* Complain about starvation of grace-period kthread.  */
+static void rcu_check_gp_kthread_starvation(void)
+{
+	struct task_struct *gpk = rcu_state.gp_kthread;
+	unsigned long j;
+
+	j = jiffies - READ_ONCE(rcu_state.gp_activity);
+	if (j > 2 * HZ) {
+		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+		       rcu_state.name, j,
+		       (long)rcu_seq_current(&rcu_state.gp_seq),
+		       READ_ONCE(rcu_state.gp_flags),
+		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
+		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
+		if (gpk) {
+			pr_err("RCU grace-period kthread stack dump:\n");
+			sched_show_task(gpk);
+			wake_up_process(gpk);
+		}
+	}
+}
+
+static void print_other_cpu_stall(unsigned long gp_seq)
+{
+	int cpu;
+	unsigned long flags;
+	unsigned long gpa;
+	unsigned long j;
+	int ndetected = 0;
+	struct rcu_node *rnp;
+	long totqlen = 0;
+
+	/* Kick and suppress, if so configured. */
+	rcu_stall_kick_kthreads();
+	if (rcu_cpu_stall_suppress)
+		return;
+
+	/*
+	 * OK, time to rat on our buddy...
+	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * RCU CPU stall warnings.
+	 */
+	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
+	rcu_for_each_leaf_node(rnp) {
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		ndetected += rcu_print_task_stall(rnp);
+		if (rnp->qsmask != 0) {
+			for_each_leaf_node_possible_cpu(rnp, cpu)
+				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
+					print_cpu_stall_info(cpu);
+					ndetected++;
+				}
+		}
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+
+	for_each_possible_cpu(cpu)
+		totqlen += rcu_get_n_cbs_cpu(cpu);
+	pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
+	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
+	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+	if (ndetected) {
+		rcu_dump_cpu_stacks();
+
+		/* Complain about tasks blocking the grace period. */
+		rcu_for_each_leaf_node(rnp)
+			rcu_print_detail_task_stall_rnp(rnp);
+	} else {
+		if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
+			pr_err("INFO: Stall ended before state dump start\n");
+		} else {
+			j = jiffies;
+			gpa = READ_ONCE(rcu_state.gp_activity);
+			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
+			       rcu_state.name, j - gpa, j, gpa,
+			       READ_ONCE(jiffies_till_next_fqs),
+			       rcu_get_root()->qsmask);
+			/* In this case, the current CPU might be at fault. */
+			sched_show_task(current);
+		}
+	}
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
+		WRITE_ONCE(rcu_state.jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+
+	rcu_check_gp_kthread_starvation();
+
+	panic_on_rcu_stall();
+
+	rcu_force_quiescent_state();  /* Kick them all. */
+}
+
+static void print_cpu_stall(void)
+{
+	int cpu;
+	unsigned long flags;
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+	struct rcu_node *rnp = rcu_get_root();
+	long totqlen = 0;
+
+	/* Kick and suppress, if so configured. */
+	rcu_stall_kick_kthreads();
+	if (rcu_cpu_stall_suppress)
+		return;
+
+	/*
+	 * OK, time to rat on ourselves...
+	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * RCU CPU stall warnings.
+	 */
+	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
+	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
+	print_cpu_stall_info(smp_processor_id());
+	raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
+	for_each_possible_cpu(cpu)
+		totqlen += rcu_get_n_cbs_cpu(cpu);
+	pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
+		jiffies - rcu_state.gp_start,
+		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+
+	rcu_check_gp_kthread_starvation();
+
+	rcu_dump_cpu_stacks();
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
+		WRITE_ONCE(rcu_state.jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+	panic_on_rcu_stall();
+
+	/*
+	 * Attempt to revive the RCU machinery by forcing a context switch.
+	 *
+	 * A context switch would normally allow the RCU state machine to make
+	 * progress and it could be we're stuck in kernel space without context
+	 * switches for an entirely unreasonable amount of time.
+	 */
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
+}
+
+static void check_cpu_stall(struct rcu_data *rdp)
+{
+	unsigned long gs1;
+	unsigned long gs2;
+	unsigned long gps;
+	unsigned long j;
+	unsigned long jn;
+	unsigned long js;
+	struct rcu_node *rnp;
+
+	if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+	    !rcu_gp_in_progress())
+		return;
+	rcu_stall_kick_kthreads();
+	j = jiffies;
+
+	/*
+	 * Lots of memory barriers to reject false positives.
+	 *
+	 * The idea is to pick up rcu_state.gp_seq, then
+	 * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
+	 * another copy of rcu_state.gp_seq.  These values are updated in
+	 * the opposite order with memory barriers (or equivalent) during
+	 * grace-period initialization and cleanup.  Now, a false positive
+	 * can occur if we get an new value of rcu_state.gp_start and a old
+	 * value of rcu_state.jiffies_stall.  But given the memory barriers,
+	 * the only way that this can happen is if one grace period ends
+	 * and another starts between these two fetches.  This is detected
+	 * by comparing the second fetch of rcu_state.gp_seq with the
+	 * previous fetch from rcu_state.gp_seq.
+	 *
+	 * Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
+	 * and rcu_state.gp_start suffice to forestall false positives.
+	 */
+	gs1 = READ_ONCE(rcu_state.gp_seq);
+	smp_rmb(); /* Pick up ->gp_seq first... */
+	js = READ_ONCE(rcu_state.jiffies_stall);
+	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
+	gps = READ_ONCE(rcu_state.gp_start);
+	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+	gs2 = READ_ONCE(rcu_state.gp_seq);
+	if (gs1 != gs2 ||
+	    ULONG_CMP_LT(j, js) ||
+	    ULONG_CMP_GE(gps, js))
+		return; /* No stall or GP completed since entering function. */
+	rnp = rdp->mynode;
+	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+	if (rcu_gp_in_progress() &&
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+
+		/* We haven't checked in, so go dump stack. */
+		print_cpu_stall();
+
+	} else if (rcu_gp_in_progress() &&
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+
+		/* They had a few time units to dump stack, so complain. */
+		print_other_cpu_stall(gs2);
+	}
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// RCU forward-progress mechanisms, including of callback invocation.
+
+
+/*
+ * Show the state of the grace-period kthreads.
+ */
+void show_rcu_gp_kthreads(void)
+{
+	int cpu;
+	unsigned long j;
+	unsigned long ja;
+	unsigned long jr;
+	unsigned long jw;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	j = jiffies;
+	ja = j - READ_ONCE(rcu_state.gp_activity);
+	jr = j - READ_ONCE(rcu_state.gp_req_activity);
+	jw = j - READ_ONCE(rcu_state.gp_wake_time);
+	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
+		rcu_state.name, gp_state_getname(rcu_state.gp_state),
+		rcu_state.gp_state,
+		rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
+		(long)READ_ONCE(rcu_state.gp_seq),
+		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
+		READ_ONCE(rcu_state.gp_flags));
+	rcu_for_each_node_breadth_first(rnp) {
+		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
+			continue;
+		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
+			rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
+			(long)rnp->gp_seq_needed);
+		if (!rcu_is_leaf_node(rnp))
+			continue;
+		for_each_leaf_node_possible_cpu(rnp, cpu) {
+			rdp = per_cpu_ptr(&rcu_data, cpu);
+			if (rdp->gpwrap ||
+			    ULONG_CMP_GE(rcu_state.gp_seq,
+					 rdp->gp_seq_needed))
+				continue;
+			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
+				cpu, (long)rdp->gp_seq_needed);
+		}
+	}
+	/* sched_show_task(rcu_state.gp_kthread); */
+}
+EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+
+/*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+				     const unsigned long gpssdelay)
+{
+	unsigned long flags;
+	unsigned long j;
+	struct rcu_node *rnp_root = rcu_get_root();
+	static atomic_t warned = ATOMIC_INIT(0);
+
+	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+		return;
+	j = jiffies; /* Expensive access, and in common case don't get here. */
+	if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
+	    atomic_read(&warned))
+		return;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	j = jiffies;
+	if (rcu_gp_in_progress() ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
+	    atomic_read(&warned)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	/* Hold onto the leaf lock to make others see warned==1. */
+
+	if (rnp_root != rnp)
+		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+	j = jiffies;
+	if (rcu_gp_in_progress() ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
+	    time_before(j, rcu_state.gp_activity + gpssdelay) ||
+	    atomic_xchg(&warned, 1)) {
+		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	WARN_ON(1);
+	if (rnp_root != rnp)
+		raw_spin_unlock_rcu_node(rnp_root);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	show_rcu_gp_kthreads();
+}
+
+/*
+ * Do a forward-progress check for rcutorture.  This is normally invoked
+ * due to an OOM event.  The argument "j" gives the time period during
+ * which rcutorture would like progress to have been made.
+ */
+void rcu_fwd_progress_check(unsigned long j)
+{
+	unsigned long cbs;
+	int cpu;
+	unsigned long max_cbs = 0;
+	int max_cpu = -1;
+	struct rcu_data *rdp;
+
+	if (rcu_gp_in_progress()) {
+		pr_info("%s: GP age %lu jiffies\n",
+			__func__, jiffies - rcu_state.gp_start);
+		show_rcu_gp_kthreads();
+	} else {
+		pr_info("%s: Last GP end %lu jiffies ago\n",
+			__func__, jiffies - rcu_state.gp_end);
+		preempt_disable();
+		rdp = this_cpu_ptr(&rcu_data);
+		rcu_check_gp_start_stall(rdp->mynode, rdp, j);
+		preempt_enable();
+	}
+	for_each_possible_cpu(cpu) {
+		cbs = rcu_get_n_cbs_cpu(cpu);
+		if (!cbs)
+			continue;
+		if (max_cpu < 0)
+			pr_info("%s: callbacks", __func__);
+		pr_cont(" %d: %lu", cpu, cbs);
+		if (cbs <= max_cbs)
+			continue;
+		max_cbs = cbs;
+		max_cpu = cpu;
+	}
+	if (max_cpu >= 0)
+		pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
+
+/* Commandeer a sysrq key to dump RCU's tree. */
+static bool sysrq_rcu;
+module_param(sysrq_rcu, bool, 0444);
+
+/* Dump grace-period-request information due to commandeered sysrq. */
+static void sysrq_show_rcu(int key)
+{
+	show_rcu_gp_kthreads();
+}
+
+static struct sysrq_key_op sysrq_rcudump_op = {
+	.handler = sysrq_show_rcu,
+	.help_msg = "show-rcu(y)",
+	.action_msg = "Show RCU tree",
+	.enable_mask = SYSRQ_ENABLE_DUMP,
+};
+
+static int __init rcu_sysrq_init(void)
+{
+	if (sysrq_rcu)
+		return register_sysrq_key('y', &sysrq_rcudump_op);
+	return 0;
+}
+early_initcall(rcu_sysrq_init);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index cbaa976c5945..c3bf44ba42e5 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -424,68 +424,11 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 #endif
 
 #ifdef CONFIG_RCU_STALL_COMMON
-
-#ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
-#else
-#define RCU_STALL_DELAY_DELTA	       0
-#endif
-
 int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
-static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
-
 module_param(rcu_cpu_stall_suppress, int, 0644);
+int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 module_param(rcu_cpu_stall_timeout, int, 0644);
-
-int rcu_jiffies_till_stall_check(void)
-{
-	int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
-
-	/*
-	 * Limit check must be consistent with the Kconfig limits
-	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
-	 */
-	if (till_stall_check < 3) {
-		WRITE_ONCE(rcu_cpu_stall_timeout, 3);
-		till_stall_check = 3;
-	} else if (till_stall_check > 300) {
-		WRITE_ONCE(rcu_cpu_stall_timeout, 300);
-		till_stall_check = 300;
-	}
-	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
-}
-EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
-
-void rcu_sysrq_start(void)
-{
-	if (!rcu_cpu_stall_suppress)
-		rcu_cpu_stall_suppress = 2;
-}
-
-void rcu_sysrq_end(void)
-{
-	if (rcu_cpu_stall_suppress == 2)
-		rcu_cpu_stall_suppress = 0;
-}
-
-static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
-{
-	rcu_cpu_stall_suppress = 1;
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block rcu_panic_block = {
-	.notifier_call = rcu_panic,
-};
-
-static int __init check_cpu_stall_init(void)
-{
-	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
-	return 0;
-}
-early_initcall(check_cpu_stall_init);
-
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
 #ifdef CONFIG_TASKS_RCU
diff --git a/kernel/resource.c b/kernel/resource.c
index 92190f62ebc5..8c15f846e8ef 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -520,21 +520,20 @@ EXPORT_SYMBOL_GPL(page_is_ram);
 int region_intersects(resource_size_t start, size_t size, unsigned long flags,
 		      unsigned long desc)
 {
-	resource_size_t end = start + size - 1;
+	struct resource res;
 	int type = 0; int other = 0;
 	struct resource *p;
 
+	res.start = start;
+	res.end = start + size - 1;
+
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
 		bool is_type = (((p->flags & flags) == flags) &&
 				((desc == IORES_DESC_NONE) ||
 				 (desc == p->desc)));
 
-		if (start >= p->start && start <= p->end)
-			is_type ? type++ : other++;
-		if (end >= p->start && end <= p->end)
-			is_type ? type++ : other++;
-		if (p->start >= start && p->end <= end)
+		if (resource_overlaps(p, &res))
 			is_type ? type++ : other++;
 	}
 	read_unlock(&resource_lock);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 25e9a7b60eba..9424ee90589e 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -254,8 +254,7 @@ static int rseq_ip_fixup(struct pt_regs *regs)
  * - signal delivery,
  * and return to user-space.
  *
- * This is how we can ensure that the entire rseq critical section,
- * consisting of both the C part and the assembly instruction sequence,
+ * This is how we can ensure that the entire rseq critical section
  * will issue the commit instruction only if executed atomically with
  * respect to other threads scheduled on the same CPU, and with respect
  * to signal handlers.
@@ -314,7 +313,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		/* Unregister rseq for current thread. */
 		if (current->rseq != rseq || !current->rseq)
 			return -EINVAL;
-		if (current->rseq_len != rseq_len)
+		if (rseq_len != sizeof(*rseq))
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
@@ -322,7 +321,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		if (ret)
 			return ret;
 		current->rseq = NULL;
-		current->rseq_len = 0;
 		current->rseq_sig = 0;
 		return 0;
 	}
@@ -336,7 +334,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		 * the provided address differs from the prior
 		 * one.
 		 */
-		if (current->rseq != rseq || current->rseq_len != rseq_len)
+		if (current->rseq != rseq || rseq_len != sizeof(*rseq))
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
@@ -354,7 +352,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
 	current->rseq = rseq;
-	current->rseq_len = rseq_len;
 	current->rseq_sig = sig;
 	/*
 	 * If rseq was previously inactive, and has just been
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4778c48a7fda..102dfcf0a29a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -792,10 +792,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
+
+	p->on_rq = TASK_ON_RQ_QUEUED;
 }
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
@@ -920,7 +924,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 
 /*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
@@ -1151,7 +1155,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-		tlb_migrate_finish(p->mm);
 		return 0;
 	} else if (task_on_rq_queued(p)) {
 		/*
@@ -1237,11 +1240,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		rq_pin_lock(src_rq, &srf);
 		rq_pin_lock(dst_rq, &drf);
 
-		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
-		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 
 		rq_unpin_lock(dst_rq, &drf);
@@ -1681,16 +1682,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
-	activate_task(rq, p, en_flags);
-	p->on_rq = TASK_ON_RQ_QUEUED;
-
-	/* If a worker is waking up, notify the workqueue: */
-	if (p->flags & PF_WQ_WORKER)
-		wq_worker_waking_up(p, cpu_of(rq));
-}
-
 /*
  * Mark the task runnable and perform wakeup-preemption.
  */
@@ -1742,7 +1733,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
 
-	ttwu_activate(rq, p, en_flags);
+	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
@@ -2107,56 +2098,6 @@ out:
 }
 
 /**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
-	struct rq *rq = task_rq(p);
-
-	if (WARN_ON_ONCE(rq != this_rq()) ||
-	    WARN_ON_ONCE(p == current))
-		return;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (!raw_spin_trylock(&p->pi_lock)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet picked a replacement task.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&p->pi_lock);
-		rq_relock(rq, rf);
-	}
-
-	if (!(p->state & TASK_NORMAL))
-		goto out;
-
-	trace_sched_waking(p);
-
-	if (!task_on_rq_queued(p)) {
-		if (p->in_iowait) {
-			delayacct_blkio_end(p);
-			atomic_dec(&rq->nr_iowait);
-		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
-	}
-
-	ttwu_do_wakeup(rq, p, 0, rf);
-	ttwu_stat(p, smp_processor_id(), 0);
-out:
-	raw_spin_unlock(&p->pi_lock);
-}
-
-/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2467,7 +2408,6 @@ void wake_up_new_task(struct task_struct *p)
 	post_init_entity_util_avg(p);
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -3466,25 +3406,11 @@ static void __sched notrace __schedule(bool preempt)
 			prev->state = TASK_RUNNING;
 		} else {
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
 				atomic_inc(&rq->nr_iowait);
 				delayacct_blkio_start();
 			}
-
-			/*
-			 * If a worker went to sleep, notify and ask workqueue
-			 * whether it wants to wake up a task to maintain
-			 * concurrency.
-			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
-				to_wakeup = wq_worker_sleeping(prev);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, &rf);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -3544,6 +3470,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))
 		return;
+
+	/*
+	 * If a worker went to sleep, notify and ask workqueue whether
+	 * it wants to wake up a task to maintain concurrency.
+	 * As this function is called inside the schedule() context,
+	 * we disable preemption to avoid it calling schedule() again
+	 * in the possible wakeup of a kworker.
+	 */
+	if (tsk->flags & PF_WQ_WORKER) {
+		preempt_disable();
+		wq_worker_sleeping(tsk);
+		preempt_enable_no_resched();
+	}
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -3552,6 +3492,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
+static void sched_update_worker(struct task_struct *tsk)
+{
+	if (tsk->flags & PF_WQ_WORKER)
+		wq_worker_running(tsk);
+}
+
 asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
@@ -3562,6 +3508,7 @@ asmlinkage __visible void __sched schedule(void)
 		__schedule(false);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
@@ -5918,7 +5865,7 @@ void __init sched_init_smp(void)
 
 static int __init migration_init(void)
 {
-	sched_rq_cpu_starting(smp_processor_id());
+	sched_cpu_starting(smp_processor_id());
 	return 0;
 }
 early_initcall(migration_init);
@@ -6559,6 +6506,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
 {
+	if (shareval > scale_load_down(ULONG_MAX))
+		shareval = MAX_SHARES;
 	return sched_group_set_shares(css_tg(css), scale_load(shareval));
 }
 
@@ -6574,7 +6523,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
 static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -6654,20 +6603,22 @@ out_unlock:
 	return ret;
 }
 
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 {
 	u64 quota, period;
 
 	period = ktime_to_ns(tg->cfs_bandwidth.period);
 	if (cfs_quota_us < 0)
 		quota = RUNTIME_INF;
-	else
+	else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
 		quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+	else
+		return -EINVAL;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
 {
 	u64 quota_us;
 
@@ -6680,17 +6631,20 @@ long tg_get_cfs_quota(struct task_group *tg)
 	return quota_us;
 }
 
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
 {
 	u64 quota, period;
 
+	if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	period = (u64)cfs_period_us * NSEC_PER_USEC;
 	quota = tg->cfs_bandwidth.quota;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
 {
 	u64 cfs_period_us;
 
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 835671f0f917..b5dcd1d83c7f 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -7,7 +7,7 @@
  */
 #include "sched.h"
 
-DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
 /**
  * cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index b3a878aa593d..5403479073b0 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -773,6 +773,7 @@ out:
 	return 0;
 
 fail:
+	kobject_put(&tunables->attr_set.kobj);
 	policy->governor_data = NULL;
 	sugov_tunables_free(tunables);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8039d62ae36e..678bfb9bd87f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -702,7 +702,7 @@ do {									\
 
 static const char *sched_tunable_scaling_names[] = {
 	"none",
-	"logaritmic",
+	"logarithmic",
 	"linear"
 };
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 35f3ea375084..f35930f5e528 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2597,7 +2597,7 @@ out:
 /*
  * Drive the periodic memory faults..
  */
-void task_tick_numa(struct rq *rq, struct task_struct *curr)
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
 	struct callback_head *work = &curr->numa_work;
 	u64 period, now;
@@ -3571,7 +3571,7 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
  * Synchronize entity load avg of dequeued entity without locking
  * the previous rq.
  */
-void sync_entity_load_avg(struct sched_entity *se)
+static void sync_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 last_update_time;
@@ -3584,7 +3584,7 @@ void sync_entity_load_avg(struct sched_entity *se)
  * Task first catches up with cfs_rq, and then subtract
  * itself from the cfs_rq (task must be off the queue now).
  */
-void remove_entity_load_avg(struct sched_entity *se)
+static void remove_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	unsigned long flags;
@@ -5145,7 +5145,6 @@ static inline void hrtick_update(struct rq *rq)
 
 #ifdef CONFIG_SMP
 static inline unsigned long cpu_util(int cpu);
-static unsigned long capacity_of(int cpu);
 
 static inline bool cpu_overutilized(int cpu)
 {
@@ -7521,7 +7520,6 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	p->on_rq = TASK_ON_RQ_MIGRATING;
 	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, env->dst_cpu);
 }
@@ -7657,7 +7655,6 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 
 	BUG_ON(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
 
@@ -9551,22 +9548,26 @@ static inline int on_null_domain(struct rq *rq)
  * - When one of the busy CPUs notice that there may be an idle rebalancing
  *   needed, they will kick the idle load balancer, which then does idle
  *   load balancing for all the idle CPUs.
+ * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ *   anywhere yet.
  */
 
 static inline int find_new_ilb(void)
 {
-	int ilb = cpumask_first(nohz.idle_cpus_mask);
+	int ilb;
 
-	if (ilb < nr_cpu_ids && idle_cpu(ilb))
-		return ilb;
+	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
+			      housekeeping_cpumask(HK_FLAG_MISC)) {
+		if (idle_cpu(ilb))
+			return ilb;
+	}
 
 	return nr_cpu_ids;
 }
 
 /*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick the
- * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
- * CPU (if there is one).
+ * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
+ * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
  */
 static void kick_ilb(unsigned int flags)
 {
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index b02d148e7672..687302051a27 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -65,6 +65,7 @@ void __init housekeeping_init(void)
 static int __init housekeeping_setup(char *str, enum hk_flags flags)
 {
 	cpumask_var_t non_housekeeping_mask;
+	cpumask_var_t tmp;
 	int err;
 
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
@@ -75,16 +76,23 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 		return 0;
 	}
 
+	alloc_bootmem_cpumask_var(&tmp);
 	if (!housekeeping_flags) {
 		alloc_bootmem_cpumask_var(&housekeeping_mask);
 		cpumask_andnot(housekeeping_mask,
 			       cpu_possible_mask, non_housekeeping_mask);
-		if (cpumask_empty(housekeeping_mask))
+
+		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+		if (cpumask_empty(tmp)) {
+			pr_warn("Housekeeping: must include one present CPU, "
+				"using boot CPU:%d\n", smp_processor_id());
 			__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+		}
 	} else {
-		cpumask_var_t tmp;
-
-		alloc_bootmem_cpumask_var(&tmp);
+		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+		if (cpumask_empty(tmp))
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
 		cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
 		if (!cpumask_equal(tmp, housekeeping_mask)) {
 			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
@@ -92,8 +100,8 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 			free_bootmem_cpumask_var(non_housekeeping_mask);
 			return 0;
 		}
-		free_bootmem_cpumask_var(tmp);
 	}
+	free_bootmem_cpumask_var(tmp);
 
 	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
 		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 90fa23d36565..1e6b909dca36 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2555,6 +2555,8 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
 	if (rt_runtime_us < 0)
 		rt_runtime = RUNTIME_INF;
+	else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
 
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
@@ -2575,6 +2577,9 @@ int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
 {
 	u64 rt_runtime, rt_period;
 
+	if (rt_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	rt_period = rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efa686eeff26..b52ed1ada0be 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -780,7 +780,7 @@ struct root_domain {
 	 * NULL-terminated list of performance domains intersecting with the
 	 * CPUs of the rd. Protected by RCU.
 	 */
-	struct perf_domain	*pd;
+	struct perf_domain __rcu *pd;
 };
 
 extern struct root_domain def_root_domain;
@@ -869,8 +869,8 @@ struct rq {
 	atomic_t		nr_iowait;
 
 #ifdef CONFIG_SMP
-	struct root_domain	*rd;
-	struct sched_domain	*sd;
+	struct root_domain		*rd;
+	struct sched_domain __rcu	*sd;
 
 	unsigned long		cpu_capacity;
 	unsigned long		cpu_capacity_orig;
@@ -1324,13 +1324,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 	return sd;
 }
 
-DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
-DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
@@ -2185,7 +2185,7 @@ static inline u64 irq_time_read(int cpu)
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #ifdef CONFIG_CPU_FREQ
-DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
 /**
  * cpufreq_update_util - Take a note about CPU utilization changes.
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ab7f371a3a17..f53f89df837d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -615,13 +615,13 @@ static void destroy_sched_domains(struct sched_domain *sd)
  * the cpumask of the domain), this allows us to quickly tell if
  * two CPUs are in the same cache domain, see cpus_share_cache().
  */
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
@@ -1059,6 +1059,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
 	struct sched_domain *child = sd->child;
 	struct sched_group *sg;
+	bool already_visited;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
@@ -1066,9 +1067,14 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 	sg = *per_cpu_ptr(sdd->sg, cpu);
 	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
 
-	/* For claim_allocations: */
-	atomic_inc(&sg->ref);
-	atomic_inc(&sg->sgc->ref);
+	/* Increase refcounts for claim_allocations: */
+	already_visited = atomic_inc_return(&sg->ref) > 1;
+	/* sgc visits should follow a similar trend as sg */
+	WARN_ON(already_visited != (atomic_inc_return(&sg->sgc->ref) > 1));
+
+	/* If we have already visited that group, it's already initialized. */
+	if (already_visited)
+		return sg;
 
 	if (child) {
 		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
@@ -1087,8 +1093,8 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 
 /*
  * build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
+ * covered by the given span, will set each group's ->cpumask correctly,
+ * and will initialize their ->sgc.
  *
  * Assumes the sched_domain tree is fully constructed
  */
@@ -2075,9 +2081,8 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
 }
 
 /*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated CPUs, but could be used to
- * exclude other special cases in the future.
+ * Set up scheduler domains and groups.  For now this just excludes isolated
+ * CPUs, but could be used to exclude other special cases in the future.
  */
 int sched_init_domains(const struct cpumask *cpu_map)
 {
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index df27e499956a..3582eeb59893 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -502,7 +502,10 @@ out:
  *
  * Caller must be holding current->sighand->siglock lock.
  *
- * Returns 0 on success, -ve on error.
+ * Returns 0 on success, -ve on error, or
+ *   - in TSYNC mode: the pid of a thread which was either not in the correct
+ *     seccomp mode or did not have an ancestral seccomp filter
+ *   - in NEW_LISTENER mode: the fd of the new listener
  */
 static long seccomp_attach_filter(unsigned int flags,
 				  struct seccomp_filter *filter)
@@ -1258,6 +1261,16 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
 		return -EINVAL;
 
+	/*
+	 * In the successful case, NEW_LISTENER returns the new listener fd.
+	 * But in the failure case, TSYNC returns the thread that died. If you
+	 * combine these two flags, there's no way to tell whether something
+	 * succeeded or failed. So, let's disallow this combination.
+	 */
+	if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
+	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER))
+		return -EINVAL;
+
 	/* Prepare the new filter before holding any locks. */
 	prepared = seccomp_prepare_user_filter(filter);
 	if (IS_ERR(prepared))
@@ -1304,7 +1317,7 @@ out:
 		mutex_unlock(&current->signal->cred_guard_mutex);
 out_put_fd:
 	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
-		if (ret < 0) {
+		if (ret) {
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 10277429ed84..2c3382378d94 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -573,57 +573,6 @@ void tasklet_kill(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(tasklet_kill);
 
-/*
- * tasklet_hrtimer
- */
-
-/*
- * The trampoline is called when the hrtimer expires. It schedules a tasklet
- * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
- * hrtimer callback, but from softirq context.
- */
-static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
-{
-	struct tasklet_hrtimer *ttimer =
-		container_of(timer, struct tasklet_hrtimer, timer);
-
-	tasklet_hi_schedule(&ttimer->tasklet);
-	return HRTIMER_NORESTART;
-}
-
-/*
- * Helper function which calls the hrtimer callback from
- * tasklet/softirq context
- */
-static void __tasklet_hrtimer_trampoline(unsigned long data)
-{
-	struct tasklet_hrtimer *ttimer = (void *)data;
-	enum hrtimer_restart restart;
-
-	restart = ttimer->function(&ttimer->timer);
-	if (restart != HRTIMER_NORESTART)
-		hrtimer_restart(&ttimer->timer);
-}
-
-/**
- * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
- * @ttimer:	 tasklet_hrtimer which is initialized
- * @function:	 hrtimer callback function which gets called from softirq context
- * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
- * @mode:	 hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
- */
-void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-			  enum hrtimer_restart (*function)(struct hrtimer *),
-			  clockid_t which_clock, enum hrtimer_mode mode)
-{
-	hrtimer_init(&ttimer->timer, which_clock, mode);
-	ttimer->timer.function = __hrtimer_tasklet_trampoline;
-	tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
-		     (unsigned long)ttimer);
-	ttimer->function = function;
-}
-EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
-
 void __init softirq_init(void)
 {
 	int cpu;
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index f8edee9c792d..27bafc1e271e 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -5,41 +5,56 @@
  *
  *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
+#include <linux/sched/task_stack.h>
+#include <linux/sched/debug.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
 
-void print_stack_trace(struct stack_trace *trace, int spaces)
+/**
+ * stack_trace_print - Print the entries in the stack trace
+ * @entries:	Pointer to storage array
+ * @nr_entries:	Number of entries in the storage array
+ * @spaces:	Number of leading spaces to print
+ */
+void stack_trace_print(unsigned long *entries, unsigned int nr_entries,
+		       int spaces)
 {
-	int i;
+	unsigned int i;
 
-	if (WARN_ON(!trace->entries))
+	if (WARN_ON(!entries))
 		return;
 
-	for (i = 0; i < trace->nr_entries; i++)
-		printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
+	for (i = 0; i < nr_entries; i++)
+		printk("%*c%pS\n", 1 + spaces, ' ', (void *)entries[i]);
 }
-EXPORT_SYMBOL_GPL(print_stack_trace);
+EXPORT_SYMBOL_GPL(stack_trace_print);
 
-int snprint_stack_trace(char *buf, size_t size,
-			struct stack_trace *trace, int spaces)
+/**
+ * stack_trace_snprint - Print the entries in the stack trace into a buffer
+ * @buf:	Pointer to the print buffer
+ * @size:	Size of the print buffer
+ * @entries:	Pointer to storage array
+ * @nr_entries:	Number of entries in the storage array
+ * @spaces:	Number of leading spaces to print
+ *
+ * Return: Number of bytes printed.
+ */
+int stack_trace_snprint(char *buf, size_t size, unsigned long *entries,
+			unsigned int nr_entries, int spaces)
 {
-	int i;
-	int generated;
-	int total = 0;
+	unsigned int generated, i, total = 0;
 
-	if (WARN_ON(!trace->entries))
+	if (WARN_ON(!entries))
 		return 0;
 
-	for (i = 0; i < trace->nr_entries; i++) {
+	for (i = 0; i < nr_entries && size; i++) {
 		generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
-				     (void *)trace->entries[i]);
+				     (void *)entries[i]);
 
 		total += generated;
-
-		/* Assume that generated isn't a negative number */
 		if (generated >= size) {
 			buf += size;
 			size = 0;
@@ -51,7 +66,176 @@ int snprint_stack_trace(char *buf, size_t size,
 
 	return total;
 }
-EXPORT_SYMBOL_GPL(snprint_stack_trace);
+EXPORT_SYMBOL_GPL(stack_trace_snprint);
+
+#ifdef CONFIG_ARCH_STACKWALK
+
+struct stacktrace_cookie {
+	unsigned long	*store;
+	unsigned int	size;
+	unsigned int	skip;
+	unsigned int	len;
+};
+
+static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
+				      bool reliable)
+{
+	struct stacktrace_cookie *c = cookie;
+
+	if (c->len >= c->size)
+		return false;
+
+	if (c->skip > 0) {
+		c->skip--;
+		return true;
+	}
+	c->store[c->len++] = addr;
+	return c->len < c->size;
+}
+
+static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr,
+					      bool reliable)
+{
+	if (in_sched_functions(addr))
+		return true;
+	return stack_trace_consume_entry(cookie, addr, reliable);
+}
+
+/**
+ * stack_trace_save - Save a stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+			      unsigned int skipnr)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+		.skip	= skipnr + 1,
+	};
+
+	arch_stack_walk(consume_entry, &c, current, NULL);
+	return c.len;
+}
+EXPORT_SYMBOL_GPL(stack_trace_save);
+
+/**
+ * stack_trace_save_tsk - Save a task stack trace into a storage array
+ * @task:	The task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size, unsigned int skipnr)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+		.skip	= skipnr + 1,
+	};
+
+	if (!try_get_task_stack(tsk))
+		return 0;
+
+	arch_stack_walk(consume_entry, &c, tsk, NULL);
+	put_task_stack(tsk);
+	return c.len;
+}
+
+/**
+ * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
+ * @regs:	Pointer to pt_regs to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+				   unsigned int size, unsigned int skipnr)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+		.skip	= skipnr,
+	};
+
+	arch_stack_walk(consume_entry, &c, current, regs);
+	return c.len;
+}
+
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+/**
+ * stack_trace_save_tsk_reliable - Save task stack with verification
+ * @tsk:	Pointer to the task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return:	An error if it detects any unreliable features of the
+ *		stack. Otherwise it guarantees that the stack trace is
+ *		reliable and returns the number of entries stored.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+	};
+	int ret;
+
+	/*
+	 * If the task doesn't have a stack (e.g., a zombie), the stack is
+	 * "reliably" empty.
+	 */
+	if (!try_get_task_stack(tsk))
+		return 0;
+
+	ret = arch_stack_walk_reliable(consume_entry, &c, tsk);
+	put_task_stack(tsk);
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+/**
+ * stack_trace_save_user - Save a user space stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+	};
+
+	/* Trace user stack if not a kernel thread */
+	if (!current->mm)
+		return 0;
+
+	arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
+	return c.len;
+}
+#endif
+
+#else /* CONFIG_ARCH_STACKWALK */
 
 /*
  * Architectures that do not implement save_stack_trace_*()
@@ -77,3 +261,118 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk,
 	WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n");
 	return -ENOSYS;
 }
+
+/**
+ * stack_trace_save - Save a stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+			      unsigned int skipnr)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+		.skip		= skipnr + 1,
+	};
+
+	save_stack_trace(&trace);
+	return trace.nr_entries;
+}
+EXPORT_SYMBOL_GPL(stack_trace_save);
+
+/**
+ * stack_trace_save_tsk - Save a task stack trace into a storage array
+ * @task:	The task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_tsk(struct task_struct *task,
+				  unsigned long *store, unsigned int size,
+				  unsigned int skipnr)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+		.skip		= skipnr + 1,
+	};
+
+	save_stack_trace_tsk(task, &trace);
+	return trace.nr_entries;
+}
+
+/**
+ * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
+ * @regs:	Pointer to pt_regs to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+				   unsigned int size, unsigned int skipnr)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+		.skip		= skipnr,
+	};
+
+	save_stack_trace_regs(regs, &trace);
+	return trace.nr_entries;
+}
+
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+/**
+ * stack_trace_save_tsk_reliable - Save task stack with verification
+ * @tsk:	Pointer to the task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return:	An error if it detects any unreliable features of the
+ *		stack. Otherwise it guarantees that the stack trace is
+ *		reliable and returns the number of entries stored.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+	};
+	int ret = save_stack_trace_tsk_reliable(tsk, &trace);
+
+	return ret ? ret : trace.nr_entries;
+}
+#endif
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+/**
+ * stack_trace_save_user - Save a user space stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+	};
+
+	save_stack_trace_user(&trace);
+	return trace.nr_entries;
+}
+#endif /* CONFIG_USER_STACKTRACE_SUPPORT */
+
+#endif /* !CONFIG_ARCH_STACKWALK */
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 5e77662dd2d9..f5490222e134 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -611,6 +611,22 @@ void clockevents_resume(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+/**
+ * tick_offline_cpu - Take CPU out of the broadcast mechanism
+ * @cpu:	The outgoing CPU
+ *
+ * Called on the outgoing CPU after it took itself offline.
+ */
+void tick_offline_cpu(unsigned int cpu)
+{
+	raw_spin_lock(&clockevents_lock);
+	tick_broadcast_offline(cpu);
+	raw_spin_unlock(&clockevents_lock);
+}
+# endif
+
 /**
  * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
  */
@@ -621,8 +637,6 @@ void tick_cleanup_dead_cpu(int cpu)
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
-	tick_shutdown_broadcast_oneshot(cpu);
-	tick_shutdown_broadcast(cpu);
 	tick_shutdown(cpu);
 	/*
 	 * Unregister the clock event devices which were
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index ac9c03dd6c7d..d23b434c2ca7 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -63,7 +63,7 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
-	unsigned long seq;
+	unsigned int seq;
 	u64 ret;
 
 	do {
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 930113b9799a..968e4b07918e 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -94,7 +94,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
-	unsigned long seq;
+	unsigned int seq;
 	struct clock_read_data *rd;
 
 	do {
@@ -267,7 +267,7 @@ void __init generic_sched_clock_init(void)
  */
 static u64 notrace suspended_sched_clock_read(void)
 {
-	unsigned long seq = raw_read_seqcount(&cd.seq);
+	unsigned int seq = raw_read_seqcount(&cd.seq);
 
 	return cd.read_data[seq & 1].epoch_cyc;
 }
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index ee834d4fb814..e51778c312f1 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -36,10 +36,16 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 static void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 static void tick_broadcast_clear_oneshot(int cpu);
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+# ifdef CONFIG_HOTPLUG_CPU
+static void tick_broadcast_oneshot_offline(unsigned int cpu);
+# endif
 #else
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
 static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
+# ifdef CONFIG_HOTPLUG_CPU
+static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { }
+# endif
 #endif
 
 /*
@@ -433,27 +439,29 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-/*
- * Remove a CPU from broadcasting
- */
-void tick_shutdown_broadcast(unsigned int cpu)
+static void tick_shutdown_broadcast(void)
 {
-	struct clock_event_device *bc;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
-	bc = tick_broadcast_device.evtdev;
-	cpumask_clear_cpu(cpu, tick_broadcast_mask);
-	cpumask_clear_cpu(cpu, tick_broadcast_on);
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
 		if (bc && cpumask_empty(tick_broadcast_mask))
 			clockevents_shutdown(bc);
 	}
+}
 
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_broadcast_offline(unsigned int cpu)
+{
+	raw_spin_lock(&tick_broadcast_lock);
+	cpumask_clear_cpu(cpu, tick_broadcast_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_on);
+	tick_broadcast_oneshot_offline(cpu);
+	tick_shutdown_broadcast();
+	raw_spin_unlock(&tick_broadcast_lock);
 }
+
 #endif
 
 void tick_suspend_broadcast(void)
@@ -801,13 +809,13 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 * either the CPU handling the broadcast
 			 * interrupt or we got woken by something else.
 			 *
-			 * We are not longer in the broadcast mask, so
+			 * We are no longer in the broadcast mask, so
 			 * if the cpu local expiry time is already
 			 * reached, we would reprogram the cpu local
 			 * timer with an already expired event.
 			 *
 			 * This can lead to a ping-pong when we return
-			 * to idle and therefor rearm the broadcast
+			 * to idle and therefore rearm the broadcast
 			 * timer before the cpu local timer was able
 			 * to fire. This happens because the forced
 			 * reprogramming makes sure that the event
@@ -950,14 +958,10 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 }
 
 /*
- * Remove a dead CPU from broadcasting
+ * Remove a dying CPU from broadcasting
  */
-void tick_shutdown_broadcast_oneshot(unsigned int cpu)
+static void tick_broadcast_oneshot_offline(unsigned int cpu)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
 	/*
 	 * Clear the broadcast masks for the dead cpu, but do not stop
 	 * the broadcast device!
@@ -965,8 +969,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int cpu)
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
-
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 #endif
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index df401463a191..59225b484e4e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -46,6 +46,14 @@ ktime_t tick_period;
  *    procedure also covers cpu hotplug.
  */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
 
 /*
  * Debugging: see timer_list.c
@@ -149,7 +157,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	    !tick_broadcast_oneshot_active()) {
 		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
-		unsigned long seq;
+		unsigned int seq;
 		ktime_t next;
 
 		do {
@@ -167,6 +175,26 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	}
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+static void giveup_do_timer(void *info)
+{
+	int cpu = *(unsigned int *)info;
+
+	WARN_ON(tick_do_timer_cpu != smp_processor_id());
+
+	tick_do_timer_cpu = cpu;
+}
+
+static void tick_take_do_timer_from_boot(void)
+{
+	int cpu = smp_processor_id();
+	int from = tick_do_timer_boot_cpu;
+
+	if (from >= 0 && from != cpu)
+		smp_call_function_single(from, giveup_do_timer, &cpu, 1);
+}
+#endif
+
 /*
  * Setup the tick device
  */
@@ -186,12 +214,26 @@ static void tick_setup_device(struct tick_device *td,
 		 * this cpu:
 		 */
 		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			if (!tick_nohz_full_cpu(cpu))
-				tick_do_timer_cpu = cpu;
-			else
-				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+			tick_do_timer_cpu = cpu;
+
 			tick_next_period = ktime_get();
 			tick_period = NSEC_PER_SEC / HZ;
+#ifdef CONFIG_NO_HZ_FULL
+			/*
+			 * The boot CPU may be nohz_full, in which case set
+			 * tick_do_timer_boot_cpu so the first housekeeping
+			 * secondary that comes up will take do_timer from
+			 * us.
+			 */
+			if (tick_nohz_full_cpu(cpu))
+				tick_do_timer_boot_cpu = cpu;
+
+		} else if (tick_do_timer_boot_cpu != -1 &&
+						!tick_nohz_full_cpu(cpu)) {
+			tick_take_do_timer_from_boot();
+			tick_do_timer_boot_cpu = -1;
+			WARN_ON(tick_do_timer_cpu != cpu);
+#endif
 		}
 
 		/*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index e277284c2831..7b2496136729 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -64,7 +64,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
 extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
-extern void tick_shutdown_broadcast(unsigned int cpu);
 extern void tick_suspend_broadcast(void);
 extern void tick_resume_broadcast(void);
 extern bool tick_resume_check_broadcast(void);
@@ -78,7 +77,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
 static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
 static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
-static inline void tick_shutdown_broadcast(unsigned int cpu) { }
 static inline void tick_suspend_broadcast(void) { }
 static inline void tick_resume_broadcast(void) { }
 static inline bool tick_resume_check_broadcast(void) { return false; }
@@ -128,19 +126,23 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 /* Functions related to oneshot broadcasting */
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
 extern void tick_broadcast_switch_to_oneshot(void);
-extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 #else /* !(BROADCAST && ONESHOT): */
 static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
 #endif /* !(BROADCAST && ONESHOT) */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_broadcast_offline(unsigned int cpu);
+#else
+static inline void tick_broadcast_offline(unsigned int cpu) { }
+#endif
+
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
 extern void tick_nohz_init(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8d18e03124ff..f4ee1a3428ae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -121,10 +121,16 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 * into a long sleep. If two CPUs happen to assign themselves to
 	 * this duty, then the jiffies update is still serialized by
 	 * jiffies_lock.
+	 *
+	 * If nohz_full is enabled, this should not happen because the
+	 * tick_do_timer_cpu never relinquishes.
 	 */
-	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
-	    && !tick_nohz_full_cpu(cpu))
+	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+#ifdef CONFIG_NO_HZ_FULL
+		WARN_ON(tick_nohz_full_running);
+#endif
 		tick_do_timer_cpu = cpu;
+	}
 #endif
 
 	/* Check, if the jiffies need an update */
@@ -395,8 +401,8 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
 	/*
-	 * The boot CPU handles housekeeping duty (unbound timers,
-	 * workqueues, timekeeping, ...) on behalf of full dynticks
+	 * The tick_do_timer_cpu CPU handles housekeeping duty (unbound
+	 * timers, workqueues, timekeeping, ...) on behalf of full dynticks
 	 * CPUs. It must remain online when nohz full is enabled.
 	 */
 	if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
@@ -423,12 +429,15 @@ void __init tick_nohz_init(void)
 		return;
 	}
 
-	cpu = smp_processor_id();
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
+			!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
+		cpu = smp_processor_id();
 
-	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-		pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
-			cpu);
-		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+		if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+			pr_warn("NO_HZ: Clearing %d from nohz_full range "
+				"for timekeeping\n", cpu);
+			cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+		}
 	}
 
 	for_each_cpu(cpu, tick_nohz_full_mask)
@@ -645,7 +654,8 @@ static inline bool local_timer_softirq_pending(void)
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
 	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
-	unsigned long seq, basejiff;
+	unsigned long basejiff;
+	unsigned int seq;
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
@@ -904,8 +914,13 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		/*
 		 * Boot safety: make sure the timekeeping duty has been
 		 * assigned before entering dyntick-idle mode,
+		 * tick_do_timer_cpu is TICK_DO_TIMER_BOOT
 		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+		if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT))
+			return false;
+
+		/* Should not happen for nohz-full */
+		if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 			return false;
 	}
 
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 6de959a854b2..4fb06527cf64 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -24,12 +24,19 @@ enum tick_nohz_mode {
  * struct tick_sched - sched tick emulation and no idle tick control/stats
  * @sched_timer:	hrtimer to schedule the periodic tick in high
  *			resolution mode
+ * @check_clocks:	Notification mechanism about clocksource changes
+ * @nohz_mode:		Mode - one state of tick_nohz_mode
+ * @inidle:		Indicator that the CPU is in the tick idle mode
+ * @tick_stopped:	Indicator that the idle tick has been stopped
+ * @idle_active:	Indicator that the CPU is actively in the tick idle mode;
+ *			it is resetted during irq handling phases.
+ * @do_timer_lst:	CPU was the last one doing do_timer before going idle
+ * @got_idle_tick:	Tick timer function has run with @inidle set
  * @last_tick:		Store the last tick expiry time when the tick
  *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
  * @next_tick:		Next tick to be fired when in dynticks mode.
- * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
  * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
@@ -40,8 +47,8 @@ enum tick_nohz_mode {
  * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
  * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
- * @do_timer_lst:	CPU was the last one doing do_timer before going idle
- * @got_idle_tick:	Tick timer function has run with @inidle set
+ * @next_timer:		Expiry time of next expiring timer for debugging purpose only
+ * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
  */
 struct tick_sched {
 	struct hrtimer			sched_timer;
diff --git a/kernel/time/time.c b/kernel/time/time.c
index c3f756f8534b..86656bbac232 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -171,7 +171,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 	static int firsttime = 1;
 	int error = 0;
 
-	if (tv && !timespec64_valid(tv))
+	if (tv && !timespec64_valid_settod(tv))
 		return -EINVAL;
 
 	error = security_settime64(tv, tz);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index f986e1918d12..5716e28bfa3c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -720,7 +720,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 void ktime_get_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
@@ -829,7 +829,7 @@ EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
 ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
 {
 	ktime_t *offset = offsets[offs];
-	unsigned long seq;
+	unsigned int seq;
 	ktime_t tconv;
 
 	do {
@@ -960,7 +960,7 @@ time64_t __ktime_get_real_seconds(void)
 void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	ktime_t base_raw;
 	ktime_t base_real;
 	u64 nsec_raw;
@@ -1122,7 +1122,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 	ktime_t base_real, base_raw;
 	u64 nsec_real, nsec_raw;
 	u8 cs_was_changed_seq;
-	unsigned long seq;
+	unsigned int seq;
 	bool do_interp;
 	int ret;
 
@@ -1221,7 +1221,7 @@ int do_settimeofday64(const struct timespec64 *ts)
 	unsigned long flags;
 	int ret = 0;
 
-	if (!timespec64_valid_strict(ts))
+	if (!timespec64_valid_settod(ts))
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1278,7 +1278,7 @@ static int timekeeping_inject_offset(const struct timespec64 *ts)
 	/* Make sure the proposed value is valid */
 	tmp = timespec64_add(tk_xtime(tk), *ts);
 	if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 ||
-	    !timespec64_valid_strict(&tmp)) {
+	    !timespec64_valid_settod(&tmp)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -1409,7 +1409,7 @@ int timekeeping_notify(struct clocksource *clock)
 void ktime_get_raw_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 nsecs;
 
 	do {
@@ -1431,7 +1431,7 @@ EXPORT_SYMBOL(ktime_get_raw_ts64);
 int timekeeping_valid_for_hres(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	int ret;
 
 	do {
@@ -1450,7 +1450,7 @@ int timekeeping_valid_for_hres(void)
 u64 timekeeping_max_deferment(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 ret;
 
 	do {
@@ -1527,7 +1527,7 @@ void __init timekeeping_init(void)
 	unsigned long flags;
 
 	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
-	if (timespec64_valid_strict(&wall_time) &&
+	if (timespec64_valid_settod(&wall_time) &&
 	    timespec64_to_ns(&wall_time) > 0) {
 		persistent_clock_exists = true;
 	} else if (timespec64_to_ns(&wall_time) != 0) {
@@ -2150,7 +2150,7 @@ EXPORT_SYMBOL_GPL(getboottime64);
 void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
@@ -2164,7 +2164,7 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct timespec64 now, mono;
-	unsigned long seq;
+	unsigned int seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2fce056f8a49..a9b1bbc2d88d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -536,6 +536,8 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 	hlist_add_head(&timer->entry, base->vectors + idx);
 	__set_bit(idx, base->pending_map);
 	timer_set_idx(timer, idx);
+
+	trace_timer_start(timer, timer->expires, timer->flags);
 }
 
 static void
@@ -757,13 +759,6 @@ static inline void debug_init(struct timer_list *timer)
 	trace_timer_init(timer);
 }
 
-static inline void
-debug_activate(struct timer_list *timer, unsigned long expires)
-{
-	debug_timer_activate(timer);
-	trace_timer_start(timer, expires, timer->flags);
-}
-
 static inline void debug_deactivate(struct timer_list *timer)
 {
 	debug_timer_deactivate(timer);
@@ -1037,7 +1032,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		}
 	}
 
-	debug_activate(timer, expires);
+	debug_timer_activate(timer);
 
 	timer->expires = expires;
 	/*
@@ -1171,7 +1166,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	}
 	forward_timer_base(base);
 
-	debug_activate(timer, timer->expires);
+	debug_timer_activate(timer);
 	internal_add_timer(base, timer);
 	raw_spin_unlock_irqrestore(&base->lock, flags);
 }
@@ -1298,7 +1293,9 @@ int del_timer_sync(struct timer_list *timer)
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
-static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *))
+static void call_timer_fn(struct timer_list *timer,
+			  void (*fn)(struct timer_list *),
+			  unsigned long baseclk)
 {
 	int count = preempt_count();
 
@@ -1321,7 +1318,7 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 	 */
 	lock_map_acquire(&lockdep_map);
 
-	trace_timer_expire_entry(timer);
+	trace_timer_expire_entry(timer, baseclk);
 	fn(timer);
 	trace_timer_expire_exit(timer);
 
@@ -1342,6 +1339,13 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 
 static void expire_timers(struct timer_base *base, struct hlist_head *head)
 {
+	/*
+	 * This value is required only for tracing. base->clk was
+	 * incremented directly before expire_timers was called. But expiry
+	 * is related to the old base->clk value.
+	 */
+	unsigned long baseclk = base->clk - 1;
+
 	while (!hlist_empty(head)) {
 		struct timer_list *timer;
 		void (*fn)(struct timer_list *);
@@ -1355,11 +1359,11 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 
 		if (timer->flags & TIMER_IRQSAFE) {
 			raw_spin_unlock(&base->lock);
-			call_timer_fn(timer, fn);
+			call_timer_fn(timer, fn, baseclk);
 			raw_spin_lock(&base->lock);
 		} else {
 			raw_spin_unlock_irq(&base->lock);
-			call_timer_fn(timer, fn);
+			call_timer_fn(timer, fn, baseclk);
 			raw_spin_lock_irq(&base->lock);
 		}
 	}
diff --git a/kernel/torture.c b/kernel/torture.c
index 8faa1a9aaeb9..17b2be9bde12 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -88,6 +88,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
+	if (num_online_cpus() <= 1)
+		return false;  /* Can't offline the last CPU. */
 
 	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d64c00afceb5..94b0e37d90ef 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -14,6 +14,8 @@
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
 
+#include <asm/tlb.h>
+
 #include "trace_probe.h"
 #include "trace.h"
 
@@ -163,6 +165,10 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	 * access_ok() should prevent writing to non-user memory, but in
 	 * some situations (nommu, temporary switch, etc) access_ok() does
 	 * not provide enough validation, hence the check on KERNEL_DS.
+	 *
+	 * nmi_uaccess_okay() ensures the probe is not run in an interim
+	 * state, when the task or mm are switched. This is specifically
+	 * required to prevent the use of temporary mm.
 	 */
 
 	if (unlikely(in_interrupt() ||
@@ -170,6 +176,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 		return -EPERM;
 	if (unlikely(uaccess_kernel()))
 		return -EPERM;
+	if (unlikely(!nmi_uaccess_okay()))
+		return -EPERM;
 	if (!access_ok(unsafe_ptr, size))
 		return -EPERM;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ca1ee656d6d8..ec439999f387 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -159,6 +159,8 @@ static union trace_eval_map_item *trace_eval_maps;
 #endif /* CONFIG_TRACE_EVAL_MAP_FILE */
 
 static int tracing_set_tracer(struct trace_array *tr, const char *buf);
+static void ftrace_trace_userstack(struct ring_buffer *buffer,
+				   unsigned long flags, int pc);
 
 #define MAX_TRACER_SIZE		100
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
@@ -2752,12 +2754,21 @@ trace_function(struct trace_array *tr,
 
 #ifdef CONFIG_STACKTRACE
 
-#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+/* Allow 4 levels of nesting: normal, softirq, irq, NMI */
+#define FTRACE_KSTACK_NESTING	4
+
+#define FTRACE_KSTACK_ENTRIES	(PAGE_SIZE / FTRACE_KSTACK_NESTING)
+
 struct ftrace_stack {
-	unsigned long		calls[FTRACE_STACK_MAX_ENTRIES];
+	unsigned long		calls[FTRACE_KSTACK_ENTRIES];
+};
+
+
+struct ftrace_stacks {
+	struct ftrace_stack	stacks[FTRACE_KSTACK_NESTING];
 };
 
-static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks);
 static DEFINE_PER_CPU(int, ftrace_stack_reserve);
 
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
@@ -2766,13 +2777,10 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 {
 	struct trace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
+	unsigned int size, nr_entries;
+	struct ftrace_stack *fstack;
 	struct stack_entry *entry;
-	struct stack_trace trace;
-	int use_stack;
-	int size = FTRACE_STACK_ENTRIES;
-
-	trace.nr_entries	= 0;
-	trace.skip		= skip;
+	int stackidx;
 
 	/*
 	 * Add one, for this function and the call to save_stack_trace()
@@ -2780,7 +2788,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 #ifndef CONFIG_UNWINDER_ORC
 	if (!regs)
-		trace.skip++;
+		skip++;
 #endif
 
 	/*
@@ -2791,53 +2799,40 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 	preempt_disable_notrace();
 
-	use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
+	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
+
+	/* This should never happen. If it does, yell once and skip */
+	if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+		goto out;
+
 	/*
-	 * We don't need any atomic variables, just a barrier.
-	 * If an interrupt comes in, we don't care, because it would
-	 * have exited and put the counter back to what we want.
-	 * We just need a barrier to keep gcc from moving things
-	 * around.
+	 * The above __this_cpu_inc_return() is 'atomic' cpu local. An
+	 * interrupt will either see the value pre increment or post
+	 * increment. If the interrupt happens pre increment it will have
+	 * restored the counter when it returns.  We just need a barrier to
+	 * keep gcc from moving things around.
 	 */
 	barrier();
-	if (use_stack == 1) {
-		trace.entries		= this_cpu_ptr(ftrace_stack.calls);
-		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
 
-		if (regs)
-			save_stack_trace_regs(regs, &trace);
-		else
-			save_stack_trace(&trace);
-
-		if (trace.nr_entries > size)
-			size = trace.nr_entries;
-	} else
-		/* From now on, use_stack is a boolean */
-		use_stack = 0;
+	fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx;
+	size = ARRAY_SIZE(fstack->calls);
 
-	size *= sizeof(unsigned long);
+	if (regs) {
+		nr_entries = stack_trace_save_regs(regs, fstack->calls,
+						   size, skip);
+	} else {
+		nr_entries = stack_trace_save(fstack->calls, size, skip);
+	}
 
+	size = nr_entries * sizeof(unsigned long);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
 					    sizeof(*entry) + size, flags, pc);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
 
-	memset(&entry->caller, 0, size);
-
-	if (use_stack)
-		memcpy(&entry->caller, trace.entries,
-		       trace.nr_entries * sizeof(unsigned long));
-	else {
-		trace.max_entries	= FTRACE_STACK_ENTRIES;
-		trace.entries		= entry->caller;
-		if (regs)
-			save_stack_trace_regs(regs, &trace);
-		else
-			save_stack_trace(&trace);
-	}
-
-	entry->size = trace.nr_entries;
+	memcpy(&entry->caller, fstack->calls, size);
+	entry->size = nr_entries;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
@@ -2907,15 +2902,15 @@ void trace_dump_stack(int skip)
 }
 EXPORT_SYMBOL_GPL(trace_dump_stack);
 
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
 static DEFINE_PER_CPU(int, user_stack_count);
 
-void
+static void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
 	struct trace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
-	struct stack_trace trace;
 
 	if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
@@ -2946,12 +2941,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	entry->tgid		= current->tgid;
 	memset(&entry->caller, 0, sizeof(entry->caller));
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= FTRACE_STACK_ENTRIES;
-	trace.skip		= 0;
-	trace.entries		= entry->caller;
-
-	save_stack_trace_user(&trace);
+	stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 
@@ -2960,13 +2950,12 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
  out:
 	preempt_enable();
 }
-
-#ifdef UNUSED
-static void __trace_userstack(struct trace_array *tr, unsigned long flags)
+#else /* CONFIG_USER_STACKTRACE_SUPPORT */
+static void ftrace_trace_userstack(struct ring_buffer *buffer,
+				   unsigned long flags, int pc)
 {
-	ftrace_trace_userstack(tr, flags, preempt_count());
 }
-#endif /* UNUSED */
+#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */
 
 #endif /* CONFIG_STACKTRACE */
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d80cee49e0eb..639047b259d7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -782,17 +782,9 @@ void update_max_tr_single(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 #ifdef CONFIG_STACKTRACE
-void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
-			    int pc);
-
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
 #else
-static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
-					  unsigned long flags, int pc)
-{
-}
-
 static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
 				 int skip, int pc)
 {
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4ad967453b6f..3ea65cdff30d 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -205,6 +205,8 @@ void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 			  int expect, int is_constant)
 {
+	unsigned long flags = user_access_save();
+
 	/* A constant is always correct */
 	if (is_constant) {
 		f->constant++;
@@ -223,6 +225,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 		f->data.correct++;
 	else
 		f->data.incorrect++;
+
+	user_access_restore(flags);
 }
 EXPORT_SYMBOL(ftrace_likely_update);
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 795aa2038377..a1d20421f4b0 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5186,7 +5186,6 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec,
 	u64 var_ref_vals[TRACING_MAP_VARS_MAX];
 	char compound_key[HIST_KEY_SIZE_MAX];
 	struct tracing_map_elt *elt = NULL;
-	struct stack_trace stacktrace;
 	struct hist_field *key_field;
 	u64 field_contents;
 	void *key = NULL;
@@ -5198,14 +5197,9 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec,
 		key_field = hist_data->fields[i];
 
 		if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
-			stacktrace.max_entries = HIST_STACKTRACE_DEPTH;
-			stacktrace.entries = entries;
-			stacktrace.nr_entries = 0;
-			stacktrace.skip = HIST_STACKTRACE_SKIP;
-
-			memset(stacktrace.entries, 0, HIST_STACKTRACE_SIZE);
-			save_stack_trace(&stacktrace);
-
+			memset(entries, 0, HIST_STACKTRACE_SIZE);
+			stack_trace_save(entries, HIST_STACKTRACE_DEPTH,
+					 HIST_STACKTRACE_SKIP);
 			key = entries;
 		} else {
 			field_contents = key_field->fn(key_field, elt, rbe, rec);
@@ -5246,7 +5240,7 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
 	unsigned int i;
 
 	for (i = 0; i < max_entries; i++) {
-		if (stacktrace_entries[i] == ULONG_MAX)
+		if (!stacktrace_entries[i])
 			return;
 
 		seq_printf(m, "%*c", 1 + spaces, ' ');
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index eec648a0d673..5d16f73898db 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -18,44 +18,32 @@
 
 #include "trace.h"
 
-static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
-	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
-unsigned stack_trace_index[STACK_TRACE_ENTRIES];
+#define STACK_TRACE_ENTRIES 500
 
-/*
- * Reserve one entry for the passed in ip. This will allow
- * us to remove most or all of the stack size overhead
- * added by the stack tracer itself.
- */
-struct stack_trace stack_trace_max = {
-	.max_entries		= STACK_TRACE_ENTRIES - 1,
-	.entries		= &stack_dump_trace[0],
-};
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES];
+static unsigned stack_trace_index[STACK_TRACE_ENTRIES];
 
-unsigned long stack_trace_max_size;
-arch_spinlock_t stack_trace_max_lock =
+static unsigned int stack_trace_nr_entries;
+static unsigned long stack_trace_max_size;
+static arch_spinlock_t stack_trace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
 DEFINE_PER_CPU(int, disable_stack_tracer);
 static DEFINE_MUTEX(stack_sysctl_mutex);
 
 int stack_tracer_enabled;
-static int last_stack_tracer_enabled;
 
-void stack_trace_print(void)
+static void print_max_stack(void)
 {
 	long i;
 	int size;
 
 	pr_emerg("        Depth    Size   Location    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   stack_trace_max.nr_entries);
+			   stack_trace_nr_entries);
 
-	for (i = 0; i < stack_trace_max.nr_entries; i++) {
-		if (stack_dump_trace[i] == ULONG_MAX)
-			break;
-		if (i+1 == stack_trace_max.nr_entries ||
-				stack_dump_trace[i+1] == ULONG_MAX)
+	for (i = 0; i < stack_trace_nr_entries; i++) {
+		if (i + 1 == stack_trace_nr_entries)
 			size = stack_trace_index[i];
 		else
 			size = stack_trace_index[i] - stack_trace_index[i+1];
@@ -65,16 +53,7 @@ void stack_trace_print(void)
 	}
 }
 
-/*
- * When arch-specific code overrides this function, the following
- * data should be filled up, assuming stack_trace_max_lock is held to
- * prevent concurrent updates.
- *     stack_trace_index[]
- *     stack_trace_max
- *     stack_trace_max_size
- */
-void __weak
-check_stack(unsigned long ip, unsigned long *stack)
+static void check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags; unsigned long *p, *top, *start;
 	static int tracer_frame;
@@ -110,13 +89,12 @@ check_stack(unsigned long ip, unsigned long *stack)
 
 	stack_trace_max_size = this_size;
 
-	stack_trace_max.nr_entries = 0;
-	stack_trace_max.skip = 0;
-
-	save_stack_trace(&stack_trace_max);
+	stack_trace_nr_entries = stack_trace_save(stack_dump_trace,
+					       ARRAY_SIZE(stack_dump_trace) - 1,
+					       0);
 
 	/* Skip over the overhead of the stack tracer itself */
-	for (i = 0; i < stack_trace_max.nr_entries; i++) {
+	for (i = 0; i < stack_trace_nr_entries; i++) {
 		if (stack_dump_trace[i] == ip)
 			break;
 	}
@@ -125,7 +103,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 	 * Some archs may not have the passed in ip in the dump.
 	 * If that happens, we need to show everything.
 	 */
-	if (i == stack_trace_max.nr_entries)
+	if (i == stack_trace_nr_entries)
 		i = 0;
 
 	/*
@@ -143,15 +121,13 @@ check_stack(unsigned long ip, unsigned long *stack)
 	 * loop will only happen once. This code only takes place
 	 * on a new max, so it is far from a fast path.
 	 */
-	while (i < stack_trace_max.nr_entries) {
+	while (i < stack_trace_nr_entries) {
 		int found = 0;
 
 		stack_trace_index[x] = this_size;
 		p = start;
 
-		for (; p < top && i < stack_trace_max.nr_entries; p++) {
-			if (stack_dump_trace[i] == ULONG_MAX)
-				break;
+		for (; p < top && i < stack_trace_nr_entries; p++) {
 			/*
 			 * The READ_ONCE_NOCHECK is used to let KASAN know that
 			 * this is not a stack-out-of-bounds error.
@@ -182,12 +158,10 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	stack_trace_max.nr_entries = x;
-	for (; x < i; x++)
-		stack_dump_trace[x] = ULONG_MAX;
+	stack_trace_nr_entries = x;
 
 	if (task_stack_end_corrupted(current)) {
-		stack_trace_print();
+		print_max_stack();
 		BUG();
 	}
 
@@ -286,7 +260,7 @@ __next(struct seq_file *m, loff_t *pos)
 {
 	long n = *pos - 1;
 
-	if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+	if (n >= stack_trace_nr_entries)
 		return NULL;
 
 	m->private = (void *)n;
@@ -350,7 +324,7 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   stack_trace_max.nr_entries);
+			   stack_trace_nr_entries);
 
 		if (!stack_tracer_enabled && !stack_trace_max_size)
 			print_disabled(m);
@@ -360,12 +334,10 @@ static int t_show(struct seq_file *m, void *v)
 
 	i = *(long *)v;
 
-	if (i >= stack_trace_max.nr_entries ||
-	    stack_dump_trace[i] == ULONG_MAX)
+	if (i >= stack_trace_nr_entries)
 		return 0;
 
-	if (i+1 == stack_trace_max.nr_entries ||
-	    stack_dump_trace[i+1] == ULONG_MAX)
+	if (i + 1 == stack_trace_nr_entries)
 		size = stack_trace_index[i];
 	else
 		size = stack_trace_index[i] - stack_trace_index[i+1];
@@ -422,23 +394,21 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos)
 {
+	int was_enabled;
 	int ret;
 
 	mutex_lock(&stack_sysctl_mutex);
+	was_enabled = !!stack_tracer_enabled;
 
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
-	if (ret || !write ||
-	    (last_stack_tracer_enabled == !!stack_tracer_enabled))
+	if (ret || !write || (was_enabled == !!stack_tracer_enabled))
 		goto out;
 
-	last_stack_tracer_enabled = !!stack_tracer_enabled;
-
 	if (stack_tracer_enabled)
 		register_ftrace_function(&trace_ops);
 	else
 		unregister_ftrace_function(&trace_ops);
-
  out:
 	mutex_unlock(&stack_sysctl_mutex);
 	return ret;
@@ -454,7 +424,6 @@ static __init int enable_stacktrace(char *str)
 		strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE);
 
 	stack_tracer_enabled = 1;
-	last_stack_tracer_enabled = 1;
 	return 1;
 }
 __setup("stacktrace", enable_stacktrace);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6a5787233113..7f9e7b9306fe 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -590,7 +590,7 @@ static void lockup_detector_reconfigure(void)
  * Create the watchdog thread infrastructure and configure the detector(s).
  *
  * The threads are not unparked as watchdog_allowed_mask is empty.  When
- * the threads are sucessfully initialized, take the proper locks and
+ * the threads are successfully initialized, take the proper locks and
  * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
  */
 static __init void lockup_detector_setup(void)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ddee541ea97a..56180c9286f5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -841,43 +841,32 @@ static void wake_up_worker(struct worker_pool *pool)
 }
 
 /**
- * wq_worker_waking_up - a worker is waking up
+ * wq_worker_running - a worker is running again
  * @task: task waking up
- * @cpu: CPU @task is waking up to
  *
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu)
+void wq_worker_running(struct task_struct *task)
 {
 	struct worker *worker = kthread_data(task);
 
-	if (!(worker->flags & WORKER_NOT_RUNNING)) {
-		WARN_ON_ONCE(worker->pool->cpu != cpu);
+	if (!worker->sleeping)
+		return;
+	if (!(worker->flags & WORKER_NOT_RUNNING))
 		atomic_inc(&worker->pool->nr_running);
-	}
+	worker->sleeping = 0;
 }
 
 /**
  * wq_worker_sleeping - a worker is going to sleep
  * @task: task going to sleep
  *
- * This function is called during schedule() when a busy worker is
- * going to sleep.  Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * Return:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task)
+void wq_worker_sleeping(struct task_struct *task)
 {
-	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+	struct worker *next, *worker = kthread_data(task);
 	struct worker_pool *pool;
 
 	/*
@@ -886,13 +875,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 	 * checking NOT_RUNNING.
 	 */
 	if (worker->flags & WORKER_NOT_RUNNING)
-		return NULL;
+		return;
 
 	pool = worker->pool;
 
-	/* this can only happen on the local cpu */
-	if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id()))
-		return NULL;
+	if (WARN_ON_ONCE(worker->sleeping))
+		return;
+
+	worker->sleeping = 1;
+	spin_lock_irq(&pool->lock);
 
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
@@ -906,9 +897,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 	 * lock is safe.
 	 */
 	if (atomic_dec_and_test(&pool->nr_running) &&
-	    !list_empty(&pool->worklist))
-		to_wakeup = first_idle_worker(pool);
-	return to_wakeup ? to_wakeup->task : NULL;
+	    !list_empty(&pool->worklist)) {
+		next = first_idle_worker(pool);
+		if (next)
+			wake_up_process(next->task);
+	}
+	spin_unlock_irq(&pool->lock);
 }
 
 /**
@@ -4929,7 +4923,7 @@ static void rebind_workers(struct worker_pool *pool)
 		 *
 		 * WRITE_ONCE() is necessary because @worker->flags may be
 		 * tested without holding any lock in
-		 * wq_worker_waking_up().  Without it, NOT_RUNNING test may
+		 * wq_worker_running().  Without it, NOT_RUNNING test may
 		 * fail incorrectly leading to premature concurrency
 		 * management operations.
 		 */
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index cb68b03ca89a..498de0e909a4 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -44,6 +44,7 @@ struct worker {
 	unsigned long		last_active;	/* L: last active timestamp */
 	unsigned int		flags;		/* X: flags */
 	int			id;		/* I: worker id */
+	int			sleeping;	/* None */
 
 	/*
 	 * Opaque string set with work_set_desc().  Printed out with task
@@ -72,8 +73,8 @@ static inline struct worker *current_wq_worker(void)
  * Scheduler hooks for concurrency managed workqueue.  Only to be used from
  * sched/ and workqueue.c.
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task);
+void wq_worker_running(struct task_struct *task);
+void wq_worker_sleeping(struct task_struct *task);
 work_func_t wq_worker_last_func(struct task_struct *task);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index a9e56539bd11..e86975bfca6a 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -597,6 +597,10 @@ config ARCH_HAS_UACCESS_FLUSHCACHE
 config ARCH_HAS_UACCESS_MCSAFE
 	bool
 
+# Temporary. Goes away when all archs are cleaned up
+config ARCH_STACKWALK
+       bool
+
 config STACKDEPOT
 	bool
 	select STACKTRACE
diff --git a/lib/Makefile b/lib/Makefile
index 3b08673e8881..e16e7aadc41a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -17,6 +17,17 @@ KCOV_INSTRUMENT_list_debug.o := n
 KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 
+# Early boot use of cmdline, don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KASAN_SANITIZE_string.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_string.o = -pg
+endif
+
+CFLAGS_string.o := $(call cc-option, -fno-stack-protector)
+endif
+
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o int_sqrt.o extable.o \
@@ -268,6 +279,7 @@ obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
 obj-$(CONFIG_UBSAN) += ubsan.o
 
 UBSAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 obj-$(CONFIG_SBITMAP) += sbitmap.o
 
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index cf7b129b0b2b..e26aa4f65eb9 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -65,22 +65,16 @@ static bool fail_task(struct fault_attr *attr, struct task_struct *task)
 
 static bool fail_stacktrace(struct fault_attr *attr)
 {
-	struct stack_trace trace;
 	int depth = attr->stacktrace_depth;
 	unsigned long entries[MAX_STACK_TRACE_DEPTH];
-	int n;
+	int n, nr_entries;
 	bool found = (attr->require_start == 0 && attr->require_end == ULONG_MAX);
 
 	if (depth == 0)
 		return found;
 
-	trace.nr_entries = 0;
-	trace.entries = entries;
-	trace.max_entries = depth;
-	trace.skip = 1;
-
-	save_stack_trace(&trace);
-	for (n = 0; n < trace.nr_entries; n++) {
+	nr_entries = stack_trace_save(entries, depth, 1);
+	for (n = 0; n < nr_entries; n++) {
 		if (attr->reject_start <= entries[n] &&
 			       entries[n] < attr->reject_end)
 			return false;
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index e513459a5601..605c61f65d94 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -194,40 +194,52 @@ static inline struct stack_record *find_stack(struct stack_record *bucket,
 	return NULL;
 }
 
-void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace)
+/**
+ * stack_depot_fetch - Fetch stack entries from a depot
+ *
+ * @handle:		Stack depot handle which was returned from
+ *			stack_depot_save().
+ * @entries:		Pointer to store the entries address
+ *
+ * Return: The number of trace entries for this depot.
+ */
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+			       unsigned long **entries)
 {
 	union handle_parts parts = { .handle = handle };
 	void *slab = stack_slabs[parts.slabindex];
 	size_t offset = parts.offset << STACK_ALLOC_ALIGN;
 	struct stack_record *stack = slab + offset;
 
-	trace->nr_entries = trace->max_entries = stack->size;
-	trace->entries = stack->entries;
-	trace->skip = 0;
+	*entries = stack->entries;
+	return stack->size;
 }
-EXPORT_SYMBOL_GPL(depot_fetch_stack);
+EXPORT_SYMBOL_GPL(stack_depot_fetch);
 
 /**
- * depot_save_stack - save stack in a stack depot.
- * @trace - the stacktrace to save.
- * @alloc_flags - flags for allocating additional memory if required.
+ * stack_depot_save - Save a stack trace from an array
+ *
+ * @entries:		Pointer to storage array
+ * @nr_entries:		Size of the storage array
+ * @alloc_flags:	Allocation gfp flags
  *
- * Returns the handle of the stack struct stored in depot.
+ * Return: The handle of the stack struct stored in depot
  */
-depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
-				    gfp_t alloc_flags)
+depot_stack_handle_t stack_depot_save(unsigned long *entries,
+				      unsigned int nr_entries,
+				      gfp_t alloc_flags)
 {
-	u32 hash;
-	depot_stack_handle_t retval = 0;
 	struct stack_record *found = NULL, **bucket;
-	unsigned long flags;
+	depot_stack_handle_t retval = 0;
 	struct page *page = NULL;
 	void *prealloc = NULL;
+	unsigned long flags;
+	u32 hash;
 
-	if (unlikely(trace->nr_entries == 0))
+	if (unlikely(nr_entries == 0))
 		goto fast_exit;
 
-	hash = hash_stack(trace->entries, trace->nr_entries);
+	hash = hash_stack(entries, nr_entries);
 	bucket = &stack_table[hash & STACK_HASH_MASK];
 
 	/*
@@ -235,8 +247,8 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
 	 * The smp_load_acquire() here pairs with smp_store_release() to
 	 * |bucket| below.
 	 */
-	found = find_stack(smp_load_acquire(bucket), trace->entries,
-			   trace->nr_entries, hash);
+	found = find_stack(smp_load_acquire(bucket), entries,
+			   nr_entries, hash);
 	if (found)
 		goto exit;
 
@@ -264,10 +276,10 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
 
 	spin_lock_irqsave(&depot_lock, flags);
 
-	found = find_stack(*bucket, trace->entries, trace->nr_entries, hash);
+	found = find_stack(*bucket, entries, nr_entries, hash);
 	if (!found) {
 		struct stack_record *new =
-			depot_alloc_stack(trace->entries, trace->nr_entries,
+			depot_alloc_stack(entries, nr_entries,
 					  hash, &prealloc, alloc_flags);
 		if (new) {
 			new->next = *bucket;
@@ -297,4 +309,4 @@ exit:
 fast_exit:
 	return retval;
 }
-EXPORT_SYMBOL_GPL(depot_save_stack);
+EXPORT_SYMBOL_GPL(stack_depot_save);
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index 58eacd41526c..023ba9f3b99f 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -23,10 +23,11 @@
  * hit it), 'max' is the address space maximum (and we return
  * -EFAULT if we hit it).
  */
-static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+static inline long do_strncpy_from_user(char *dst, const char __user *src,
+					unsigned long count, unsigned long max)
 {
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
-	long res = 0;
+	unsigned long res = 0;
 
 	/*
 	 * Truncate 'max' to the user-specified limit, so that
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 1c1a1b0e38a5..7f2db3fe311f 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -28,7 +28,7 @@
 static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
 {
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
-	long align, res = 0;
+	unsigned long align, res = 0;
 	unsigned long c;
 
 	/*
@@ -42,7 +42,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
 	 * Do everything aligned. But that means that we
 	 * need to also expand the maximum..
 	 */
-	align = (sizeof(long) - 1) & (unsigned long)src;
+	align = (sizeof(unsigned long) - 1) & (unsigned long)src;
 	src -= align;
 	max += align;
 
diff --git a/lib/ubsan.c b/lib/ubsan.c
index e4162f59a81c..ecc179338094 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/uaccess.h>
 
 #include "ubsan.h"
 
@@ -86,11 +87,13 @@ static bool is_inline_int(struct type_descriptor *type)
 	return bits <= inline_bits;
 }
 
-static s_max get_signed_val(struct type_descriptor *type, unsigned long val)
+static s_max get_signed_val(struct type_descriptor *type, void *val)
 {
 	if (is_inline_int(type)) {
 		unsigned extra_bits = sizeof(s_max)*8 - type_bit_width(type);
-		return ((s_max)val) << extra_bits >> extra_bits;
+		unsigned long ulong_val = (unsigned long)val;
+
+		return ((s_max)ulong_val) << extra_bits >> extra_bits;
 	}
 
 	if (type_bit_width(type) == 64)
@@ -99,15 +102,15 @@ static s_max get_signed_val(struct type_descriptor *type, unsigned long val)
 	return *(s_max *)val;
 }
 
-static bool val_is_negative(struct type_descriptor *type, unsigned long val)
+static bool val_is_negative(struct type_descriptor *type, void *val)
 {
 	return type_is_signed(type) && get_signed_val(type, val) < 0;
 }
 
-static u_max get_unsigned_val(struct type_descriptor *type, unsigned long val)
+static u_max get_unsigned_val(struct type_descriptor *type, void *val)
 {
 	if (is_inline_int(type))
-		return val;
+		return (unsigned long)val;
 
 	if (type_bit_width(type) == 64)
 		return *(u64 *)val;
@@ -116,7 +119,7 @@ static u_max get_unsigned_val(struct type_descriptor *type, unsigned long val)
 }
 
 static void val_to_string(char *str, size_t size, struct type_descriptor *type,
-	unsigned long value)
+			void *value)
 {
 	if (type_is_int(type)) {
 		if (type_bit_width(type) == 128) {
@@ -163,8 +166,8 @@ static void ubsan_epilogue(unsigned long *flags)
 	current->in_ubsan--;
 }
 
-static void handle_overflow(struct overflow_data *data, unsigned long lhs,
-			unsigned long rhs, char op)
+static void handle_overflow(struct overflow_data *data, void *lhs,
+			void *rhs, char op)
 {
 
 	struct type_descriptor *type = data->type;
@@ -191,8 +194,7 @@ static void handle_overflow(struct overflow_data *data, unsigned long lhs,
 }
 
 void __ubsan_handle_add_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 
 	handle_overflow(data, lhs, rhs, '+');
@@ -200,23 +202,21 @@ void __ubsan_handle_add_overflow(struct overflow_data *data,
 EXPORT_SYMBOL(__ubsan_handle_add_overflow);
 
 void __ubsan_handle_sub_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 	handle_overflow(data, lhs, rhs, '-');
 }
 EXPORT_SYMBOL(__ubsan_handle_sub_overflow);
 
 void __ubsan_handle_mul_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 	handle_overflow(data, lhs, rhs, '*');
 }
 EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
 
 void __ubsan_handle_negate_overflow(struct overflow_data *data,
-				unsigned long old_val)
+				void *old_val)
 {
 	unsigned long flags;
 	char old_val_str[VALUE_LENGTH];
@@ -237,8 +237,7 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 
 
 void __ubsan_handle_divrem_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 	unsigned long flags;
 	char rhs_val_str[VALUE_LENGTH];
@@ -313,6 +312,7 @@ static void handle_object_size_mismatch(struct type_mismatch_data_common *data,
 static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,
 				unsigned long ptr)
 {
+	unsigned long flags = user_access_save();
 
 	if (!ptr)
 		handle_null_ptr_deref(data);
@@ -320,10 +320,12 @@ static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,
 		handle_misaligned_access(data, ptr);
 	else
 		handle_object_size_mismatch(data, ptr);
+
+	user_access_restore(flags);
 }
 
 void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
-				unsigned long ptr)
+				void *ptr)
 {
 	struct type_mismatch_data_common common_data = {
 		.location = &data->location,
@@ -332,12 +334,12 @@ void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
 		.type_check_kind = data->type_check_kind
 	};
 
-	ubsan_type_mismatch_common(&common_data, ptr);
+	ubsan_type_mismatch_common(&common_data, (unsigned long)ptr);
 }
 EXPORT_SYMBOL(__ubsan_handle_type_mismatch);
 
 void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
-				unsigned long ptr)
+				void *ptr)
 {
 
 	struct type_mismatch_data_common common_data = {
@@ -347,30 +349,11 @@ void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
 		.type_check_kind = data->type_check_kind
 	};
 
-	ubsan_type_mismatch_common(&common_data, ptr);
+	ubsan_type_mismatch_common(&common_data, (unsigned long)ptr);
 }
 EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1);
 
-void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data,
-					unsigned long bound)
-{
-	unsigned long flags;
-	char bound_str[VALUE_LENGTH];
-
-	if (suppress_report(&data->location))
-		return;
-
-	ubsan_prologue(&data->location, &flags);
-
-	val_to_string(bound_str, sizeof(bound_str), data->type, bound);
-	pr_err("variable length array bound value %s <= 0\n", bound_str);
-
-	ubsan_epilogue(&flags);
-}
-EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive);
-
-void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data,
-				unsigned long index)
+void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
 {
 	unsigned long flags;
 	char index_str[VALUE_LENGTH];
@@ -388,7 +371,7 @@ void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data,
 EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
 
 void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
-					unsigned long lhs, unsigned long rhs)
+					void *lhs, void *rhs)
 {
 	unsigned long flags;
 	struct type_descriptor *rhs_type = data->rhs_type;
@@ -439,7 +422,7 @@ void __ubsan_handle_builtin_unreachable(struct unreachable_data *data)
 EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
 
 void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
-				unsigned long val)
+				void *val)
 {
 	unsigned long flags;
 	char val_str[VALUE_LENGTH];
diff --git a/lib/ubsan.h b/lib/ubsan.h
index f4d8d0bd4016..b8fa83864467 100644
--- a/lib/ubsan.h
+++ b/lib/ubsan.h
@@ -57,11 +57,6 @@ struct nonnull_arg_data {
 	int arg_index;
 };
 
-struct vla_bound_data {
-	struct source_location location;
-	struct type_descriptor *type;
-};
-
 struct out_of_bounds_data {
 	struct source_location location;
 	struct type_descriptor *array_type;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 165ea46bf149..b6a34b32d8ac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1677,7 +1677,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct mm_struct *mm = tlb->mm;
 	bool ret = false;
 
-	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
@@ -1753,7 +1753,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	pmd_t orig_pmd;
 	spinlock_t *ptl;
 
-	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6cdc7b2d9100..641cedfc8c0f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3353,7 +3353,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 * This is a hugetlb vma, all the pte entries should point
 	 * to huge page.
 	 */
-	tlb_remove_check_page_size_change(tlb, sz);
+	tlb_change_page_size(tlb, sz);
 	tlb_start_vma(tlb, vma);
 
 	/*
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 5d1065efbd47..08b43de2383b 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -2,18 +2,21 @@
 KASAN_SANITIZE := n
 UBSAN_SANITIZE_common.o := n
 UBSAN_SANITIZE_generic.o := n
+UBSAN_SANITIZE_generic_report.o := n
 UBSAN_SANITIZE_tags.o := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o = -pg
-CFLAGS_REMOVE_generic.o = -pg
-CFLAGS_REMOVE_tags.o = -pg
+CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
 
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
 
 CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 obj-$(CONFIG_KASAN) := common.o init.o report.o
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 80bbe62b16cd..36afcf64e016 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -36,6 +36,7 @@
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 #include <linux/bug.h>
+#include <linux/uaccess.h>
 
 #include "kasan.h"
 #include "../slab.h"
@@ -48,37 +49,28 @@ static inline int in_irqentry_text(unsigned long ptr)
 		 ptr < (unsigned long)&__softirqentry_text_end);
 }
 
-static inline void filter_irq_stacks(struct stack_trace *trace)
+static inline unsigned int filter_irq_stacks(unsigned long *entries,
+					     unsigned int nr_entries)
 {
-	int i;
+	unsigned int i;
 
-	if (!trace->nr_entries)
-		return;
-	for (i = 0; i < trace->nr_entries; i++)
-		if (in_irqentry_text(trace->entries[i])) {
+	for (i = 0; i < nr_entries; i++) {
+		if (in_irqentry_text(entries[i])) {
 			/* Include the irqentry function into the stack. */
-			trace->nr_entries = i + 1;
-			break;
+			return i + 1;
 		}
+	}
+	return nr_entries;
 }
 
 static inline depot_stack_handle_t save_stack(gfp_t flags)
 {
 	unsigned long entries[KASAN_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = KASAN_STACK_DEPTH,
-		.skip = 0
-	};
+	unsigned int nr_entries;
 
-	save_stack_trace(&trace);
-	filter_irq_stacks(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
-
-	return depot_save_stack(&trace, flags);
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	nr_entries = filter_irq_stacks(entries, nr_entries);
+	return stack_depot_save(entries, nr_entries, flags);
 }
 
 static inline void set_track(struct kasan_track *track, gfp_t flags)
@@ -614,6 +606,15 @@ void kasan_free_shadow(const struct vm_struct *vm)
 		vfree(kasan_mem_to_shadow(vm->addr));
 }
 
+extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip);
+
+void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
+{
+	unsigned long flags = user_access_save();
+	__kasan_report(addr, size, is_write, ip);
+	user_access_restore(flags);
+}
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 static bool shadow_mapped(unsigned long addr)
 {
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index ca9418fe9232..03a443579386 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -100,10 +100,11 @@ static void print_track(struct kasan_track *track, const char *prefix)
 {
 	pr_err("%s by task %u:\n", prefix, track->pid);
 	if (track->stack) {
-		struct stack_trace trace;
+		unsigned long *entries;
+		unsigned int nr_entries;
 
-		depot_fetch_stack(track->stack, &trace);
-		print_stack_trace(&trace, 0);
+		nr_entries = stack_depot_fetch(track->stack, &entries);
+		stack_trace_print(entries, nr_entries, 0);
 	} else {
 		pr_err("(stack is not available)\n");
 	}
@@ -281,8 +282,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
 	end_report(&flags);
 }
 
-void kasan_report(unsigned long addr, size_t size,
-		bool is_write, unsigned long ip)
+void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
 {
 	struct kasan_access_info info;
 	void *tagged_addr;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 2e435b8142e5..e57bf810f798 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -410,11 +410,6 @@ static void print_unreferenced(struct seq_file *seq,
  */
 static void dump_object_info(struct kmemleak_object *object)
 {
-	struct stack_trace trace;
-
-	trace.nr_entries = object->trace_len;
-	trace.entries = object->trace;
-
 	pr_notice("Object 0x%08lx (size %zu):\n",
 		  object->pointer, object->size);
 	pr_notice("  comm \"%s\", pid %d, jiffies %lu\n",
@@ -424,7 +419,7 @@ static void dump_object_info(struct kmemleak_object *object)
 	pr_notice("  flags = 0x%x\n", object->flags);
 	pr_notice("  checksum = %u\n", object->checksum);
 	pr_notice("  backtrace:\n");
-	print_stack_trace(&trace, 4);
+	stack_trace_print(object->trace, object->trace_len, 4);
 }
 
 /*
@@ -553,15 +548,7 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
  */
 static int __save_stack_trace(unsigned long *trace)
 {
-	struct stack_trace stack_trace;
-
-	stack_trace.max_entries = MAX_TRACE;
-	stack_trace.nr_entries = 0;
-	stack_trace.entries = trace;
-	stack_trace.skip = 2;
-	save_stack_trace(&stack_trace);
-
-	return stack_trace.nr_entries;
+	return stack_trace_save(trace, MAX_TRACE, 2);
 }
 
 /*
@@ -2021,13 +2008,8 @@ early_param("kmemleak", kmemleak_boot_config);
 
 static void __init print_log_trace(struct early_log *log)
 {
-	struct stack_trace trace;
-
-	trace.nr_entries = log->trace_len;
-	trace.entries = log->trace;
-
 	pr_notice("Early log backtrace:\n");
-	print_stack_trace(&trace, 2);
+	stack_trace_print(log->trace, log->trace_len, 2);
 }
 
 /*
diff --git a/mm/madvise.c b/mm/madvise.c
index 21a7881a2db4..bb3a4554d5d5 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -328,7 +328,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
diff --git a/mm/memory.c b/mm/memory.c
index ab650c21bccd..36aac6844662 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -356,7 +356,7 @@ void free_pgd_range(struct mmu_gather *tlb,
 	 * We add page table cache pages with PAGE_SIZE,
 	 * (see pte_free_tlb()), flush the tlb if we need
 	 */
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
@@ -1046,7 +1046,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	pte_t *pte;
 	swp_entry_t entry;
 
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 again:
 	init_rss_vec(rss);
 	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
@@ -1155,7 +1155,7 @@ again:
 	 */
 	if (force_flush) {
 		force_flush = 0;
-		tlb_flush_mmu_free(tlb);
+		tlb_flush_mmu(tlb);
 		if (addr != end)
 			goto again;
 	}
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index f2f03c655807..99740e1dd273 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -11,7 +11,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-#ifdef HAVE_GENERIC_MMU_GATHER
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 
 static bool tlb_next_batch(struct mmu_gather *tlb)
 {
@@ -41,35 +41,10 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 	return true;
 }
 
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-				unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-
-	/* Is it from 0 to ~0? */
-	tlb->fullmm     = !(start | (end+1));
-	tlb->need_flush_all = 0;
-	tlb->local.next = NULL;
-	tlb->local.nr   = 0;
-	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
-	tlb->active     = &tlb->local;
-	tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
-#endif
-	tlb->page_size = 0;
-
-	__tlb_reset_range(tlb);
-}
-
-void tlb_flush_mmu_free(struct mmu_gather *tlb)
+static void tlb_batch_pages_flush(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
 	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
 		free_pages_and_swap_cache(batch->pages, batch->nr);
 		batch->nr = 0;
@@ -77,31 +52,10 @@ void tlb_flush_mmu_free(struct mmu_gather *tlb)
 	tlb->active = &tlb->local;
 }
 
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
+static void tlb_batch_list_free(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch, *next;
 
-	if (force) {
-		__tlb_reset_range(tlb);
-		__tlb_adjust_range(tlb, start, end - start);
-	}
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
 	for (batch = tlb->local.next; batch; batch = next) {
 		next = batch->next;
 		free_pages((unsigned long)batch, 0);
@@ -109,19 +63,15 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 	tlb->local.next = NULL;
 }
 
-/* __tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- *	handling the additional races in SMP caused by other CPUs caching valid
- *	mappings in their TLBs. Returns the number of free page slots left.
- *	When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
 bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
+
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
 	VM_WARN_ON(tlb->page_size != page_size);
+#endif
 
 	batch = tlb->active;
 	/*
@@ -139,7 +89,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 	return false;
 }
 
-#endif /* HAVE_GENERIC_MMU_GATHER */
+#endif /* HAVE_MMU_GATHER_NO_GATHER */
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
@@ -152,7 +102,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
  */
 static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
 	/*
 	 * Invalidate page-table caches used by hardware walkers. Then we still
 	 * need to RCU-sched wait while freeing the pages because software
@@ -193,7 +143,7 @@ static void tlb_remove_table_rcu(struct rcu_head *head)
 	free_page((unsigned long)batch);
 }
 
-void tlb_table_flush(struct mmu_gather *tlb)
+static void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
@@ -225,6 +175,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb_batch_pages_flush(tlb);
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
 /**
  * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
  * @tlb: the mmu_gather structure to initialize
@@ -240,10 +206,40 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 			unsigned long start, unsigned long end)
 {
-	arch_tlb_gather_mmu(tlb, mm, start, end);
+	tlb->mm = mm;
+
+	/* Is it from 0 to ~0? */
+	tlb->fullmm     = !(start | (end+1));
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb->need_flush_all = 0;
+	tlb->local.next = NULL;
+	tlb->local.nr   = 0;
+	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
+	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
+#endif
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	tlb->page_size = 0;
+#endif
+
+	__tlb_reset_range(tlb);
 	inc_tlb_flush_pending(tlb->mm);
 }
 
+/**
+ * tlb_finish_mmu - finish an mmu_gather structure
+ * @tlb: the mmu_gather structure to finish
+ * @start: start of the region that will be removed from the page-table
+ * @end: end of the region that will be removed from the page-table
+ *
+ * Called at the end of the shootdown operation to free up any resources that
+ * were required.
+ */
 void tlb_finish_mmu(struct mmu_gather *tlb,
 		unsigned long start, unsigned long end)
 {
@@ -254,8 +250,17 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
 	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
 	 * forcefully if we detect parallel PTE batching threads.
 	 */
-	bool force = mm_tlb_flush_nested(tlb->mm);
+	if (mm_tlb_flush_nested(tlb->mm)) {
+		__tlb_reset_range(tlb);
+		__tlb_adjust_range(tlb, start, end - start);
+	}
 
-	arch_tlb_finish_mmu(tlb, start, end, force);
+	tlb_flush_mmu(tlb);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb_batch_list_free(tlb);
+#endif
 	dec_tlb_flush_pending(tlb->mm);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c02cff1ed56e..59661106da16 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1144,7 +1144,9 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	arch_free_page(page, order);
 	kernel_poison_pages(page, 1 << order, 0);
-	kernel_map_pages(page, 1 << order, 0);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 0);
+
 	kasan_free_nondeferred_pages(page, order);
 
 	return true;
@@ -2014,7 +2016,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
-	kernel_map_pages(page, 1 << order, 1);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 1);
 	kasan_alloc_pages(page, order);
 	kernel_poison_pages(page, 1 << order, 1);
 	set_page_owner(page, order, gfp_flags);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 925b6f44a444..addcbb2ae4e4 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -58,15 +58,10 @@ static bool need_page_owner(void)
 static __always_inline depot_stack_handle_t create_dummy_stack(void)
 {
 	unsigned long entries[4];
-	struct stack_trace dummy;
+	unsigned int nr_entries;
 
-	dummy.nr_entries = 0;
-	dummy.max_entries = ARRAY_SIZE(entries);
-	dummy.entries = &entries[0];
-	dummy.skip = 0;
-
-	save_stack_trace(&dummy);
-	return depot_save_stack(&dummy, GFP_KERNEL);
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	return stack_depot_save(entries, nr_entries, GFP_KERNEL);
 }
 
 static noinline void register_dummy_stack(void)
@@ -120,49 +115,39 @@ void __reset_page_owner(struct page *page, unsigned int order)
 	}
 }
 
-static inline bool check_recursive_alloc(struct stack_trace *trace,
-					unsigned long ip)
+static inline bool check_recursive_alloc(unsigned long *entries,
+					 unsigned int nr_entries,
+					 unsigned long ip)
 {
-	int i;
-
-	if (!trace->nr_entries)
-		return false;
+	unsigned int i;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		if (trace->entries[i] == ip)
+	for (i = 0; i < nr_entries; i++) {
+		if (entries[i] == ip)
 			return true;
 	}
-
 	return false;
 }
 
 static noinline depot_stack_handle_t save_stack(gfp_t flags)
 {
 	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 2
-	};
 	depot_stack_handle_t handle;
+	unsigned int nr_entries;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
 
 	/*
-	 * We need to check recursion here because our request to stackdepot
-	 * could trigger memory allocation to save new entry. New memory
-	 * allocation would reach here and call depot_save_stack() again
-	 * if we don't catch it. There is still not enough memory in stackdepot
-	 * so it would try to allocate memory again and loop forever.
+	 * We need to check recursion here because our request to
+	 * stackdepot could trigger memory allocation to save new
+	 * entry. New memory allocation would reach here and call
+	 * stack_depot_save_entries() again if we don't catch it. There is
+	 * still not enough memory in stackdepot so it would try to
+	 * allocate memory again and loop forever.
 	 */
-	if (check_recursive_alloc(&trace, _RET_IP_))
+	if (check_recursive_alloc(entries, nr_entries, _RET_IP_))
 		return dummy_handle;
 
-	handle = depot_save_stack(&trace, flags);
+	handle = stack_depot_save(entries, nr_entries, flags);
 	if (!handle)
 		handle = failure_handle;
 
@@ -340,16 +325,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		struct page *page, struct page_owner *page_owner,
 		depot_stack_handle_t handle)
 {
-	int ret;
-	int pageblock_mt, page_mt;
+	int ret, pageblock_mt, page_mt;
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char *kbuf;
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
 
 	count = min_t(size_t, count, PAGE_SIZE);
 	kbuf = kmalloc(count, GFP_KERNEL);
@@ -378,8 +357,8 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	if (ret >= count)
 		goto err;
 
-	depot_fetch_stack(handle, &trace);
-	ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
+	nr_entries = stack_depot_fetch(handle, &entries);
+	ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0);
 	if (ret >= count)
 		goto err;
 
@@ -410,14 +389,9 @@ void __dump_page_owner(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
 	struct page_owner *page_owner;
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
 	depot_stack_handle_t handle;
+	unsigned long *entries;
+	unsigned int nr_entries;
 	gfp_t gfp_mask;
 	int mt;
 
@@ -441,10 +415,10 @@ void __dump_page_owner(struct page *page)
 		return;
 	}
 
-	depot_fetch_stack(handle, &trace);
+	nr_entries = stack_depot_fetch(handle, &entries);
 	pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
 		 page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
-	print_stack_trace(&trace, 0);
+	stack_trace_print(entries, nr_entries, 0);
 
 	if (page_owner->last_migrate_reason != -1)
 		pr_alert("page has been migrated, last migrate reason: %s\n",
diff --git a/mm/slab.c b/mm/slab.c
index 9142ee992493..284ab737faee 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1467,53 +1467,17 @@ static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
-			    unsigned long caller)
-{
-	int size = cachep->object_size;
-
-	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
-
-	if (size < 5 * sizeof(unsigned long))
-		return;
-
-	*addr++ = 0x12345678;
-	*addr++ = caller;
-	*addr++ = smp_processor_id();
-	size -= 3 * sizeof(unsigned long);
-	{
-		unsigned long *sptr = &caller;
-		unsigned long svalue;
-
-		while (!kstack_end(sptr)) {
-			svalue = *sptr++;
-			if (kernel_text_address(svalue)) {
-				*addr++ = svalue;
-				size -= sizeof(unsigned long);
-				if (size <= sizeof(unsigned long))
-					break;
-			}
-		}
-
-	}
-	*addr++ = 0x87654321;
-}
-
-static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map, unsigned long caller)
+static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
 {
 	if (!is_debug_pagealloc_cache(cachep))
 		return;
 
-	if (caller)
-		store_stackinfo(cachep, objp, caller);
-
 	kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
 }
 
 #else
 static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map, unsigned long caller) {}
+				int map) {}
 
 #endif
 
@@ -1661,7 +1625,7 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep,
 
 		if (cachep->flags & SLAB_POISON) {
 			check_poison_obj(cachep, objp);
-			slab_kernel_map(cachep, objp, 1, 0);
+			slab_kernel_map(cachep, objp, 1);
 		}
 		if (cachep->flags & SLAB_RED_ZONE) {
 			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
@@ -2433,7 +2397,7 @@ static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON) {
 			poison_obj(cachep, objp, POISON_FREE);
-			slab_kernel_map(cachep, objp, 0, 0);
+			slab_kernel_map(cachep, objp, 0);
 		}
 	}
 #endif
@@ -2812,7 +2776,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 
 	if (cachep->flags & SLAB_POISON) {
 		poison_obj(cachep, objp, POISON_FREE);
-		slab_kernel_map(cachep, objp, 0, caller);
+		slab_kernel_map(cachep, objp, 0);
 	}
 	return objp;
 }
@@ -3076,7 +3040,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
 		check_poison_obj(cachep, objp);
-		slab_kernel_map(cachep, objp, 1, 0);
+		slab_kernel_map(cachep, objp, 1);
 		poison_obj(cachep, objp, POISON_INUSE);
 	}
 	if (cachep->flags & SLAB_STORE_USER)
diff --git a/mm/slub.c b/mm/slub.c
index d30ede89f4a6..6b28cd2b5a58 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -552,31 +552,22 @@ static void set_track(struct kmem_cache *s, void *object,
 
 	if (addr) {
 #ifdef CONFIG_STACKTRACE
-		struct stack_trace trace;
-		int i;
+		unsigned int nr_entries;
 
-		trace.nr_entries = 0;
-		trace.max_entries = TRACK_ADDRS_COUNT;
-		trace.entries = p->addrs;
-		trace.skip = 3;
 		metadata_access_enable();
-		save_stack_trace(&trace);
+		nr_entries = stack_trace_save(p->addrs, TRACK_ADDRS_COUNT, 3);
 		metadata_access_disable();
 
-		/* See rant in lockdep.c */
-		if (trace.nr_entries != 0 &&
-		    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
-			trace.nr_entries--;
-
-		for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
-			p->addrs[i] = 0;
+		if (nr_entries < TRACK_ADDRS_COUNT)
+			p->addrs[nr_entries] = 0;
 #endif
 		p->addr = addr;
 		p->cpu = smp_processor_id();
 		p->pid = current->pid;
 		p->when = jiffies;
-	} else
+	} else {
 		memset(p, 0, sizeof(struct track));
+	}
 }
 
 static void init_tracking(struct kmem_cache *s, void *object)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e86ba6e74b50..e5e9e1fcac01 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/set_memory.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/list.h>
@@ -1059,24 +1060,9 @@ static void vb_free(const void *addr, unsigned long size)
 		spin_unlock(&vb->lock);
 }
 
-/**
- * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
- *
- * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
- * to amortize TLB flushing overheads. What this means is that any page you
- * have now, may, in a former life, have been mapped into kernel virtual
- * address by the vmap layer and so there might be some CPUs with TLB entries
- * still referencing that page (additional to the regular 1:1 kernel mapping).
- *
- * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
- * be sure that none of the pages we have control over will have any aliases
- * from the vmap layer.
- */
-void vm_unmap_aliases(void)
+static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
 {
-	unsigned long start = ULONG_MAX, end = 0;
 	int cpu;
-	int flush = 0;
 
 	if (unlikely(!vmap_initialized))
 		return;
@@ -1113,6 +1099,27 @@ void vm_unmap_aliases(void)
 		flush_tlb_kernel_range(start, end);
 	mutex_unlock(&vmap_purge_lock);
 }
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush = 0;
+
+	_vm_unmap_aliases(start, end, flush);
+}
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
 /**
@@ -1505,6 +1512,72 @@ struct vm_struct *remove_vm_area(const void *addr)
 	return NULL;
 }
 
+static inline void set_area_direct_map(const struct vm_struct *area,
+				       int (*set_direct_map)(struct page *page))
+{
+	int i;
+
+	for (i = 0; i < area->nr_pages; i++)
+		if (page_address(area->pages[i]))
+			set_direct_map(area->pages[i]);
+}
+
+/* Handle removing and resetting vm mappings related to the vm_struct. */
+static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
+{
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+	int i;
+
+	/*
+	 * The below block can be removed when all architectures that have
+	 * direct map permissions also have set_direct_map_() implementations.
+	 * This is concerned with resetting the direct map any an vm alias with
+	 * execute permissions, without leaving a RW+X window.
+	 */
+	if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		set_memory_nx(addr, area->nr_pages);
+		set_memory_rw(addr, area->nr_pages);
+	}
+
+	remove_vm_area(area->addr);
+
+	/* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
+	if (!flush_reset)
+		return;
+
+	/*
+	 * If not deallocating pages, just do the flush of the VM area and
+	 * return.
+	 */
+	if (!deallocate_pages) {
+		vm_unmap_aliases();
+		return;
+	}
+
+	/*
+	 * If execution gets here, flush the vm mapping and reset the direct
+	 * map. Find the start and end range of the direct mappings to make sure
+	 * the vm_unmap_aliases() flush includes the direct map.
+	 */
+	for (i = 0; i < area->nr_pages; i++) {
+		if (page_address(area->pages[i])) {
+			start = min(addr, start);
+			end = max(addr, end);
+		}
+	}
+
+	/*
+	 * Set direct map to something invalid so that it won't be cached if
+	 * there are any accesses after the TLB flush, then flush the TLB and
+	 * reset the direct map permissions to the default.
+	 */
+	set_area_direct_map(area, set_direct_map_invalid_noflush);
+	_vm_unmap_aliases(start, end, 1);
+	set_area_direct_map(area, set_direct_map_default_noflush);
+}
+
 static void __vunmap(const void *addr, int deallocate_pages)
 {
 	struct vm_struct *area;
@@ -1526,7 +1599,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
 	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
 
-	remove_vm_area(addr);
+	vm_remove_mappings(area, deallocate_pages);
+
 	if (deallocate_pages) {
 		int i;
 
@@ -1961,8 +2035,9 @@ EXPORT_SYMBOL(vzalloc_node);
  */
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
-			      NUMA_NO_NODE, __builtin_return_address(0));
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 709d2542f729..dbe8b1993be9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1920,6 +1920,7 @@ static int __init atalk_init(void)
 	ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
 	if (!ddp_dl) {
 		pr_crit("Unable to register DDP with SNAP.\n");
+		rc = -ENOMEM;
 		goto out_sock;
 	}
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 10e809b296ec..fb065a8937ea 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -226,7 +226,7 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
 	tail[plen - 1] = proto;
 }
 
-static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	int encap_type;
 	struct udphdr *uh;
@@ -234,6 +234,7 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
 	__be16 sport, dport;
 	struct xfrm_encap_tmpl *encap = x->encap;
 	struct ip_esp_hdr *esph = esp->esph;
+	unsigned int len;
 
 	spin_lock_bh(&x->lock);
 	sport = encap->encap_sport;
@@ -241,11 +242,14 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
 	encap_type = encap->encap_type;
 	spin_unlock_bh(&x->lock);
 
+	len = skb->len + esp->tailen - skb_transport_offset(skb);
+	if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
+		return -EMSGSIZE;
+
 	uh = (struct udphdr *)esph;
 	uh->source = sport;
 	uh->dest = dport;
-	uh->len = htons(skb->len + esp->tailen
-		  - skb_transport_offset(skb));
+	uh->len = htons(len);
 	uh->check = 0;
 
 	switch (encap_type) {
@@ -262,6 +266,8 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
 
 	*skb_mac_header(skb) = IPPROTO_UDP;
 	esp->esph = esph;
+
+	return 0;
 }
 
 int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
@@ -275,8 +281,12 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	int tailen = esp->tailen;
 
 	/* this is non-NULL only with UDP Encapsulation */
-	if (x->encap)
-		esp_output_udp_encap(x, skb, esp);
+	if (x->encap) {
+		int err = esp_output_udp_encap(x, skb, esp);
+
+		if (err < 0)
+			return err;
+	}
 
 	if (!skb_cloned(skb)) {
 		if (tailen <= skb_tailroom(skb)) {
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 8756e0e790d2..d3170a8001b2 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -52,13 +52,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 			goto out;
 
 		if (sp->len == XFRM_MAX_DEPTH)
-			goto out;
+			goto out_reset;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ip_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET);
 		if (!x)
-			goto out;
+			goto out_reset;
 
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
@@ -66,7 +66,7 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		xo = xfrm_offload(skb);
 		if (!xo) {
 			xfrm_state_put(x);
-			goto out;
+			goto out_reset;
 		}
 	}
 
@@ -82,6 +82,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 	xfrm_input(skb, IPPROTO_ESP, spi, -2);
 
 	return ERR_PTR(-EINPROGRESS);
+out_reset:
+	secpath_reset(skb);
 out:
 	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c80188875f39..e8bb2e85c5a4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->pkt_type = from->pkt_type;
 	to->priority = from->priority;
 	to->protocol = from->protocol;
+	to->skb_iif = from->skb_iif;
 	skb_dst_drop(to);
 	skb_dst_copy(to, from);
 	to->dev = from->dev;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 68a21bf75dd0..35d8346742e2 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -646,10 +646,8 @@ static int __init vti_init(void)
 
 	msg = "ipip tunnel";
 	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
-	if (err < 0) {
-		pr_info("%s: cant't register tunnel\n",__func__);
+	if (err < 0)
 		goto xfrm_tunnel_failed;
-	}
 
 	msg = "netlink interface";
 	err = rtnl_link_register(&vti_link_ops);
@@ -659,9 +657,9 @@ static int __init vti_init(void)
 	return err;
 
 rtnl_link_failed:
-	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
-xfrm_tunnel_failed:
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel_failed:
+	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
 xfrm_proto_comp_failed:
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 xfrm_proto_ah_failed:
@@ -676,6 +674,7 @@ pernet_dev_failed:
 static void __exit vti_fini(void)
 {
 	rtnl_link_unregister(&vti_link_ops);
+	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
 	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 835d50b279f5..a2a88ab07f7b 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -56,7 +56,7 @@ struct clusterip_config {
 #endif
 	enum clusterip_hashmode hash_mode;	/* which hashing mode */
 	u_int32_t hash_initval;			/* hash initialization */
-	struct rcu_head rcu;			/* for call_rcu_bh */
+	struct rcu_head rcu;			/* for call_rcu */
 	struct net *net;			/* netns for pernet list */
 	char ifname[IFNAMSIZ];			/* device ifname */
 };
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2f8039a26b08..a2896944aa37 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1673,7 +1673,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
 	    TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
 	    ((TCP_SKB_CB(tail)->tcp_flags |
-	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) ||
+	    !((TCP_SKB_CB(tail)->tcp_flags &
+	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
 	    ((TCP_SKB_CB(tail)->tcp_flags ^
 	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
 #ifdef CONFIG_TLS_DEVICE
@@ -1692,6 +1694,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
 			TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
 
+		/* We have to update both TCP_SKB_CB(tail)->tcp_flags and
+		 * thtail->fin, so that the fast path in tcp_rcv_established()
+		 * is not entered if we append a packet with a FIN.
+		 * SYN, RST, URG are not present.
+		 * ACK is set on both packets.
+		 * PSH : we do not really care in TCP stack,
+		 *       at least for 'GRO' packets.
+		 */
+		thtail->fin |= th->fin;
 		TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 64f9715173ac..065334b41d57 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -352,6 +352,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 	struct sk_buff *pp = NULL;
 	struct udphdr *uh2;
 	struct sk_buff *p;
+	unsigned int ulen;
 
 	/* requires non zero csum, for symmetry with GSO */
 	if (!uh->check) {
@@ -359,6 +360,12 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 		return NULL;
 	}
 
+	/* Do not deal with padded or malicious packets, sorry ! */
+	ulen = ntohs(uh->len);
+	if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
 	/* pull encapsulating udp header */
 	skb_gro_pull(skb, sizeof(struct udphdr));
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
@@ -377,13 +384,14 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot
-		 * leading to execessive truesize values
+		 * leading to excessive truesize values.
+		 * On len mismatch merge the first packet shorter than gso_size,
+		 * otherwise complete the GRO packet.
 		 */
-		if (!skb_gro_receive(p, skb) &&
+		if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) ||
+		    ulen != ntohs(uh2->len) ||
 		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
 			pp = p;
-		else if (uh->len != uh2->len)
-			pp = p;
 
 		return pp;
 	}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d73a6d6652f6..2b144b92ae46 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -111,7 +111,8 @@ static void
 _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+	int ihl = iph->ihl;
+	u8 *xprth = skb_network_header(skb) + ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
 	int oif = 0;
 
@@ -122,6 +123,11 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 	fl4->flowi4_mark = skb->mark;
 	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
 
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
+
 	if (!ip_is_fragment(iph)) {
 		switch (iph->protocol) {
 		case IPPROTO_UDP:
@@ -133,7 +139,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ports;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ports = (__be16 *)xprth;
 
 				fl4->fl4_sport = ports[!!reverse];
@@ -146,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
 				u8 *icmp;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				icmp = xprth;
 
 				fl4->fl4_icmp_type = icmp[0];
@@ -159,7 +165,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be32 *ehdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ehdr = (__be32 *)xprth;
 
 				fl4->fl4_ipsec_spi = ehdr[0];
@@ -171,7 +177,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
 				__be32 *ah_hdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ah_hdr = (__be32 *)xprth;
 
 				fl4->fl4_ipsec_spi = ah_hdr[1];
@@ -183,7 +189,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ipcomp_hdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ipcomp_hdr = (__be16 *)xprth;
 
 				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
@@ -196,7 +202,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 				__be16 *greflags;
 				__be32 *gre_hdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				greflags = (__be16 *)xprth;
 				gre_hdr = (__be32 *)xprth;
 
@@ -213,10 +219,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			break;
 		}
 	}
-	fl4->flowi4_proto = iph->protocol;
-	fl4->daddr = reverse ? iph->saddr : iph->daddr;
-	fl4->saddr = reverse ? iph->daddr : iph->saddr;
-	fl4->flowi4_tos = iph->tos;
 }
 
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d46b4eb645c2..cb99f6fb79b7 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -74,13 +74,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 			goto out;
 
 		if (sp->len == XFRM_MAX_DEPTH)
-			goto out;
+			goto out_reset;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET6);
 		if (!x)
-			goto out;
+			goto out_reset;
 
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
@@ -88,7 +88,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		xo = xfrm_offload(skb);
 		if (!xo) {
 			xfrm_state_put(x);
-			goto out;
+			goto out_reset;
 		}
 	}
 
@@ -109,6 +109,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 	xfrm_input(skb, IPPROTO_ESP, spi, -2);
 
 	return ERR_PTR(-EINPROGRESS);
+out_reset:
+	secpath_reset(skb);
 out:
 	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6613d8dbb0e5..91247a6fc67f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -921,9 +921,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		if (pcpu_rt) {
 			struct fib6_info *from;
 
-			from = rcu_dereference_protected(pcpu_rt->from,
-					     lockdep_is_held(&table->tb6_lock));
-			rcu_assign_pointer(pcpu_rt->from, NULL);
+			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
 			fib6_info_release(from);
 		}
 	}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cb54a8a3c273..be5f3d7ceb96 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
 	return fl;
 }
 
+static void fl_free_rcu(struct rcu_head *head)
+{
+	struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+	if (fl->share == IPV6_FL_S_PROCESS)
+		put_pid(fl->owner.pid);
+	kfree(fl->opt);
+	kfree(fl);
+}
+
 
 static void fl_free(struct ip6_flowlabel *fl)
 {
-	if (fl) {
-		if (fl->share == IPV6_FL_S_PROCESS)
-			put_pid(fl->owner.pid);
-		kfree(fl->opt);
-		kfree_rcu(fl, rcu);
-	}
+	if (fl)
+		call_rcu(&fl->rcu, fl_free_rcu);
 }
 
 static void fl_release(struct ip6_flowlabel *fl)
@@ -633,9 +639,9 @@ recheck:
 				if (fl1->share == IPV6_FL_S_EXCL ||
 				    fl1->share != fl->share ||
 				    ((fl1->share == IPV6_FL_S_PROCESS) &&
-				     (fl1->owner.pid == fl->owner.pid)) ||
+				     (fl1->owner.pid != fl->owner.pid)) ||
 				    ((fl1->share == IPV6_FL_S_USER) &&
-				     uid_eq(fl1->owner.uid, fl->owner.uid)))
+				     !uid_eq(fl1->owner.uid, fl->owner.uid)))
 					goto release;
 
 				err = -ENOMEM;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7178e32eb15d..0520aca3354b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -379,11 +379,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	rcu_read_lock();
-	from = rcu_dereference(rt->from);
-	rcu_assign_pointer(rt->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt->from, NULL);
 	fib6_info_release(from);
-	rcu_read_unlock();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1288,9 +1285,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = rcu_dereference_protected(rt6_ex->rt6i->from,
-					 lockdep_is_held(&rt6_exception_lock));
-	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
@@ -3397,11 +3392,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-	/* This fib6_info_hold() is safe here because we hold reference to rt
-	 * and rt already holds reference to fib6_info.
-	 */
-	fib6_info_hold(from);
-	rcu_read_unlock();
+	if (!from)
+		goto out;
 
 	nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
 	if (!nrt)
@@ -3413,10 +3405,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	/* No need to remove rt from the exception table if rt is
-	 * a cached route because rt6_insert_exception() will
-	 * takes care of it
-	 */
+	/* rt6_insert_exception() will take care of duplicated exceptions */
 	if (rt6_insert_exception(nrt, from)) {
 		dst_release_immediate(&nrt->dst);
 		goto out;
@@ -3429,7 +3418,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
 out:
-	fib6_info_release(from);
+	rcu_read_unlock();
 	neigh_release(neigh);
 }
 
@@ -3668,23 +3657,34 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
 {
-	int type;
 	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(dst->dev);
+	struct inet6_dev *idev;
+	int type;
+
+	if (netif_is_l3_master(skb->dev) &&
+	    dst->dev == net->loopback_dev)
+		idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+	else
+		idev = ip6_dst_idev(dst);
+
 	switch (ipstats_mib_noroutes) {
 	case IPSTATS_MIB_INNOROUTES:
 		type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
 		if (type == IPV6_ADDR_ANY) {
-			IP6_INC_STATS(dev_net(dst->dev),
-				      __in6_dev_get_safely(skb->dev),
-				      IPSTATS_MIB_INADDRERRORS);
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
 			break;
 		}
 		/* FALLTHROUGH */
 	case IPSTATS_MIB_OUTNOROUTES:
-		IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
-			      ipstats_mib_noroutes);
+		IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
 		break;
 	}
+
+	/* Start over by dropping the dst for l3mdev case */
+	if (netif_is_l3_master(skb->dev))
+		skb_dst_drop(skb);
+
 	icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
 	kfree_skb(skb);
 	return 0;
@@ -5017,16 +5017,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-
-	if (fibmatch)
-		err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
-				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-				    nlh->nlmsg_seq, 0);
-	else
-		err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
-				    &fl6.saddr, iif, RTM_NEWROUTE,
-				    NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-				    0);
+	if (from) {
+		if (fibmatch)
+			err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+					    iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+		else
+			err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+					    &fl6.saddr, iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+	} else {
+		err = -ENETUNREACH;
+	}
 	rcu_read_unlock();
 
 	if (err < 0) {
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index bc65db782bfb..d9e5f6808811 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -345,7 +345,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
 	unsigned int i;
 
 	xfrm_flush_gc();
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+	xfrm_state_flush(net, 0, false, true);
 
 	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
 		WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
@@ -402,6 +402,10 @@ static void __exit xfrm6_tunnel_fini(void)
 	xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
 	xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
 	unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+	/* Someone maybe has gotten the xfrm6_tunnel_spi.
+	 * So need to wait it.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
 }
 
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 5651c29cb5bd..4af1e1d60b9f 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1951,8 +1951,10 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
 
 	if (rq->sadb_x_ipsecrequest_mode == 0)
 		return -EINVAL;
+	if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto))
+		return -EINVAL;
 
-	t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */
+	t->id.proto = rq->sadb_x_ipsecrequest_proto;
 	if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0)
 		return -EINVAL;
 	t->mode = mode;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fed6becc5daf..52b5a2797c0c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -169,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (tunnel->tunnel_id == tunnel_id) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (tunnel->tunnel_id == tunnel_id &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 
 			return tunnel;
@@ -190,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (++count > nth) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (++count > nth &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 			return tunnel;
 		}
@@ -909,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
-	tunnel = l2tp_tunnel(sk);
+	tunnel = rcu_dereference_sk_user_data(sk);
 	if (tunnel == NULL)
 		goto pass_up;
 
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index cff0fb3578c9..deb3faf08337 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -841,7 +841,7 @@ void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata)
 
 	dir = sdata->vif.debugfs_dir;
 
-	if (!dir)
+	if (IS_ERR_OR_NULL(dir))
 		return;
 
 	sprintf(buf, "netdev:%s", sdata->name);
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index e03c46ac8e4d..c62101857b9b 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -112,8 +112,9 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 			     IEEE80211_HT_CAP_TX_STBC);
 
 	/* Allow user to configure RX STBC bits */
-	if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC)
-		ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC;
+	if (ht_capa_mask->cap_info & cpu_to_le16(IEEE80211_HT_CAP_RX_STBC))
+		ht_cap->cap |= le16_to_cpu(ht_capa->cap_info) &
+					IEEE80211_HT_CAP_RX_STBC;
 
 	/* Allow user to decrease AMPDU factor */
 	if (ht_capa_mask->ampdu_params_info &
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 4a6ff1482a9f..02d2e6f11e93 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1908,6 +1908,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata)
 	list_del_rcu(&sdata->list);
 	mutex_unlock(&sdata->local->iflist_mtx);
 
+	if (sdata->vif.txq)
+		ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq));
+
 	synchronize_rcu();
 
 	if (sdata->dev) {
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f0ec068e1d02..cb69d35c8e6a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -362,8 +362,8 @@ int genl_register_family(struct genl_family *family)
 	} else
 		family->attrbuf = NULL;
 
-	family->id = idr_alloc(&genl_fam_idr, family,
-			       start, end + 1, GFP_KERNEL);
+	family->id = idr_alloc_cyclic(&genl_fam_idr, family,
+				      start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
 		goto errout_free;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9419c5cf4de5..9b81813dd16a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2602,8 +2602,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	void *ph;
 	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
 	bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
+	unsigned char *addr = NULL;
 	int tp_len, size_max;
-	unsigned char *addr;
 	void *data;
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
@@ -2614,7 +2614,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2624,10 +2623,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_put;
+		if (po->sk.sk_socket->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_put;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
@@ -2799,7 +2801,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	unsigned char *addr;
+	unsigned char *addr = NULL;
 	int err, reserve = 0;
 	struct sockcm_cookie sockc;
 	struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2816,7 +2818,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2824,10 +2825,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_unlock;
+		if (sock->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_unlock;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
@@ -3344,20 +3348,29 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
+		int copy_len;
+
 		/* If the address length field is there to be filled
 		 * in, we fill it in now.
 		 */
 		if (sock->type == SOCK_PACKET) {
 			__sockaddr_check_size(sizeof(struct sockaddr_pkt));
 			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+			copy_len = msg->msg_namelen;
 		} else {
 			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
 
 			msg->msg_namelen = sll->sll_halen +
 				offsetof(struct sockaddr_ll, sll_addr);
+			copy_len = msg->msg_namelen;
+			if (msg->msg_namelen < sizeof(struct sockaddr_ll)) {
+				memset(msg->msg_name +
+				       offsetof(struct sockaddr_ll, sll_addr),
+				       0, sizeof(sll->sll_addr));
+				msg->msg_namelen = sizeof(struct sockaddr_ll);
+			}
 		}
-		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
-		       msg->msg_namelen);
+		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
 	}
 
 	if (pkt_sk(sk)->auxdata) {
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 70559854837e..8946c89d7392 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -772,7 +772,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
 	unsigned long frag_off;
 	unsigned long to_copy;
 	unsigned long copied;
-	uint64_t uncongested = 0;
+	__le64 uncongested = 0;
 	void *addr;
 
 	/* catch completely corrupt packets */
@@ -789,7 +789,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
 	copied = 0;
 
 	while (copied < RDS_CONG_MAP_BYTES) {
-		uint64_t *src, *dst;
+		__le64 *src, *dst;
 		unsigned int k;
 
 		to_copy = min(RDS_FRAG_SIZE - frag_off, PAGE_SIZE - map_off);
@@ -824,9 +824,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
 	}
 
 	/* the congestion map is in little endian order */
-	uncongested = le64_to_cpu(uncongested);
-
-	rds_cong_map_updated(map, uncongested);
+	rds_cong_map_updated(map, le64_to_cpu(uncongested));
 }
 
 static void rds_ib_process_recv(struct rds_connection *conn,
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8aa2937b069f..fe96881a334d 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -604,30 +604,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 
 	_enter("");
 
-	if (list_empty(&rxnet->calls))
-		return;
+	if (!list_empty(&rxnet->calls)) {
+		write_lock(&rxnet->call_lock);
 
-	write_lock(&rxnet->call_lock);
+		while (!list_empty(&rxnet->calls)) {
+			call = list_entry(rxnet->calls.next,
+					  struct rxrpc_call, link);
+			_debug("Zapping call %p", call);
 
-	while (!list_empty(&rxnet->calls)) {
-		call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
-		_debug("Zapping call %p", call);
+			rxrpc_see_call(call);
+			list_del_init(&call->link);
 
-		rxrpc_see_call(call);
-		list_del_init(&call->link);
+			pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
+			       call, atomic_read(&call->usage),
+			       rxrpc_call_states[call->state],
+			       call->flags, call->events);
 
-		pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
-		       call, atomic_read(&call->usage),
-		       rxrpc_call_states[call->state],
-		       call->flags, call->events);
+			write_unlock(&rxnet->call_lock);
+			cond_resched();
+			write_lock(&rxnet->call_lock);
+		}
 
 		write_unlock(&rxnet->call_lock);
-		cond_resched();
-		write_lock(&rxnet->call_lock);
 	}
 
-	write_unlock(&rxnet->call_lock);
-
 	atomic_dec(&rxnet->nr_calls);
 	wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
 }
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 1d143bc3f73d..4aa03588f87b 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1112,32 +1112,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
 }
 
 
-/* Sent the next ASCONF packet currently stored in the association.
- * This happens after the ASCONF_ACK was succeffully processed.
- */
-static void sctp_cmd_send_asconf(struct sctp_association *asoc)
-{
-	struct net *net = sock_net(asoc->base.sk);
-
-	/* Send the next asconf chunk from the addip chunk
-	 * queue.
-	 */
-	if (!list_empty(&asoc->addip_chunk_list)) {
-		struct list_head *entry = asoc->addip_chunk_list.next;
-		struct sctp_chunk *asconf = list_entry(entry,
-						struct sctp_chunk, list);
-		list_del_init(entry);
-
-		/* Hold the chunk until an ASCONF_ACK is received. */
-		sctp_chunk_hold(asconf);
-		if (sctp_primitive_ASCONF(net, asoc, asconf))
-			sctp_chunk_free(asconf);
-		else
-			asoc->addip_last_asconf = asconf;
-	}
-}
-
-
 /* These three macros allow us to pull the debugging code out of the
  * main flow of sctp_do_sm() to keep attention focused on the real
  * functionality there.
@@ -1783,9 +1757,6 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			}
 			sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp);
 			break;
-		case SCTP_CMD_SEND_NEXT_ASCONF:
-			sctp_cmd_send_asconf(asoc);
-			break;
 		case SCTP_CMD_PURGE_ASCONF_QUEUE:
 			sctp_asconf_queue_teardown(asoc);
 			break;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..713a669d2058 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static enum sctp_disposition sctp_send_next_asconf(
+					struct net *net,
+					const struct sctp_endpoint *ep,
+					struct sctp_association *asoc,
+					const union sctp_subtype type,
+					struct sctp_cmd_seq *commands)
+{
+	struct sctp_chunk *asconf;
+	struct list_head *entry;
+
+	if (list_empty(&asoc->addip_chunk_list))
+		return SCTP_DISPOSITION_CONSUME;
+
+	entry = asoc->addip_chunk_list.next;
+	asconf = list_entry(entry, struct sctp_chunk, list);
+
+	list_del_init(entry);
+	sctp_chunk_hold(asconf);
+	asoc->addip_last_asconf = asconf;
+
+	return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands);
+}
+
 /*
  * ADDIP Section 4.3 General rules for address manipulation
  * When building TLV parameters for the ASCONF Chunk that will add or
@@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
 
 		if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
-					     asconf_ack)) {
-			/* Successfully processed ASCONF_ACK.  We can
-			 * release the next asconf if we have one.
-			 */
-			sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
-					SCTP_NULL());
-			return SCTP_DISPOSITION_CONSUME;
-		}
+					     asconf_ack))
+			return sctp_send_next_asconf(net, ep,
+					(struct sctp_association *)asoc,
+							type, commands);
 
 		abort = sctp_make_abort(asoc, asconf_ack,
 					sizeof(struct sctp_errhdr));
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index cc0256939eb6..14dedb24fa7b 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -597,7 +597,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 {
 	struct strp_msg *rxm = strp_msg(skb);
-	int err = 0, offset = rxm->offset, copy, nsg;
+	int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
 	struct sk_buff *skb_iter, *unused;
 	struct scatterlist sg[1];
 	char *orig_buf, *buf;
@@ -628,25 +628,42 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 	else
 		err = 0;
 
-	copy = min_t(int, skb_pagelen(skb) - offset,
-		     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+	data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;
 
-	if (skb->decrypted)
-		skb_store_bits(skb, offset, buf, copy);
+	if (skb_pagelen(skb) > offset) {
+		copy = min_t(int, skb_pagelen(skb) - offset, data_len);
 
-	offset += copy;
-	buf += copy;
+		if (skb->decrypted)
+			skb_store_bits(skb, offset, buf, copy);
 
+		offset += copy;
+		buf += copy;
+	}
+
+	pos = skb_pagelen(skb);
 	skb_walk_frags(skb, skb_iter) {
-		copy = min_t(int, skb_iter->len,
-			     rxm->full_len - offset + rxm->offset -
-			     TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+		int frag_pos;
+
+		/* Practically all frags must belong to msg if reencrypt
+		 * is needed with current strparser and coalescing logic,
+		 * but strparser may "get optimized", so let's be safe.
+		 */
+		if (pos + skb_iter->len <= offset)
+			goto done_with_frag;
+		if (pos >= data_len + rxm->offset)
+			break;
+
+		frag_pos = offset - pos;
+		copy = min_t(int, skb_iter->len - frag_pos,
+			     data_len + rxm->offset - offset);
 
 		if (skb_iter->decrypted)
-			skb_store_bits(skb_iter, offset, buf, copy);
+			skb_store_bits(skb_iter, frag_pos, buf, copy);
 
 		offset += copy;
 		buf += copy;
+done_with_frag:
+		pos += skb_iter->len;
 	}
 
 free_buf:
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index a3ebd4b02714..c3a5fe624b4e 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -201,13 +201,14 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 
 	skb_put(nskb, skb->len);
 	memcpy(nskb->data, skb->data, headln);
-	update_chksum(nskb, headln);
 
 	nskb->destructor = skb->destructor;
 	nskb->sk = sk;
 	skb->destructor = NULL;
 	skb->sk = NULL;
 
+	update_chksum(nskb, headln);
+
 	delta = nskb->truesize - skb->truesize;
 	if (likely(delta < 0))
 		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 0ba778f371cb..a6fd5ce199da 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3778,10 +3778,9 @@ void wiphy_regulatory_register(struct wiphy *wiphy)
 		/*
 		 * The last request may have been received before this
 		 * registration call. Call the driver notifier if
-		 * initiator is USER and user type is CELL_BASE.
+		 * initiator is USER.
 		 */
-		if (lr->initiator == NL80211_REGDOM_SET_BY_USER &&
-		    lr->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE)
+		if (lr->initiator == NL80211_REGDOM_SET_BY_USER)
 			reg_call_notifier(wiphy, lr);
 	}
 
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index dbb3c1945b5c..85fec98676d3 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -70,17 +70,28 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
 	return NULL;
 }
 
-static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
+static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb,
+					    unsigned short family)
 {
 	struct xfrmi_net *xfrmn;
-	int ifindex;
 	struct xfrm_if *xi;
+	int ifindex = 0;
 
 	if (!secpath_exists(skb) || !skb->dev)
 		return NULL;
 
+	switch (family) {
+	case AF_INET6:
+		ifindex = inet6_sdif(skb);
+		break;
+	case AF_INET:
+		ifindex = inet_sdif(skb);
+		break;
+	}
+	if (!ifindex)
+		ifindex = skb->dev->ifindex;
+
 	xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
-	ifindex = skb->dev->ifindex;
 
 	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
 		if (ifindex == xi->dev->ifindex &&
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8d1a898d0ba5..a6b58df7a70f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3313,7 +3313,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	ifcb = xfrm_if_get_cb();
 
 	if (ifcb) {
-		xi = ifcb->decode_session(skb);
+		xi = ifcb->decode_session(skb, family);
 		if (xi) {
 			if_id = xi->p.if_id;
 			net = xi->net;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 1bb971f46fc6..c62f712fdaf7 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -434,7 +434,7 @@ EXPORT_SYMBOL(xfrm_state_free);
 
 static void ___xfrm_state_destroy(struct xfrm_state *x)
 {
-	tasklet_hrtimer_cancel(&x->mtimer);
+	hrtimer_cancel(&x->mtimer);
 	del_timer_sync(&x->rtimer);
 	kfree(x->aead);
 	kfree(x->aalg);
@@ -479,8 +479,8 @@ static void xfrm_state_gc_task(struct work_struct *work)
 
 static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
-	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
-	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
+	struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer);
+	enum hrtimer_restart ret = HRTIMER_NORESTART;
 	time64_t now = ktime_get_real_seconds();
 	time64_t next = TIME64_MAX;
 	int warn = 0;
@@ -544,7 +544,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 		km_state_expired(x, 0, 0);
 resched:
 	if (next != TIME64_MAX) {
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
+		hrtimer_forward_now(&x->mtimer, ktime_set(next, 0));
+		ret = HRTIMER_RESTART;
 	}
 
 	goto out;
@@ -561,7 +562,7 @@ expired:
 
 out:
 	spin_unlock(&x->lock);
-	return HRTIMER_NORESTART;
+	return ret;
 }
 
 static void xfrm_replay_timer_handler(struct timer_list *t);
@@ -580,8 +581,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		INIT_HLIST_NODE(&x->bydst);
 		INIT_HLIST_NODE(&x->bysrc);
 		INIT_HLIST_NODE(&x->byspi);
-		tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
-					CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
+		hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
+		x->mtimer.function = xfrm_timer_handler;
 		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
 		x->curlft.add_time = ktime_get_real_seconds();
 		x->lft.soft_byte_limit = XFRM_INF;
@@ -1047,7 +1048,9 @@ found:
 				hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
-			tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+			hrtimer_start(&x->mtimer,
+				      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+				      HRTIMER_MODE_REL_SOFT);
 			net->xfrm.state_num++;
 			xfrm_hash_grow_check(net, x->bydst.next != NULL);
 			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -1159,7 +1162,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 	}
 
-	tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+	hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
 	if (x->replay_maxage)
 		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
 
@@ -1266,7 +1269,9 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 		x->mark.m = m->m;
 		x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
 		xfrm_state_hold(x);
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+		hrtimer_start(&x->mtimer,
+			      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+			      HRTIMER_MODE_REL_SOFT);
 		list_add(&x->km.all, &net->xfrm.state_all);
 		hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
 		h = xfrm_src_hash(net, daddr, saddr, family);
@@ -1571,7 +1576,8 @@ out:
 		memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
 		x1->km.dying = 0;
 
-		tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+		hrtimer_start(&x1->mtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
 		if (x1->curlft.use_time)
 			xfrm_state_check_expire(x1);
 
@@ -1610,7 +1616,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL);
+		hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT);
 		return -EINVAL;
 	}
 
@@ -2384,7 +2390,7 @@ void xfrm_state_fini(struct net *net)
 
 	flush_work(&net->xfrm.state_hash_work);
 	flush_work(&xfrm_state_gc_work);
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+	xfrm_state_flush(net, 0, false, true);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index a131f9ff979e..6916931b1de1 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1424,7 +1424,7 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 	ret = verify_policy_dir(p->dir);
 	if (ret)
 		return ret;
-	if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+	if (p->index && (xfrm_policy_id2dir(p->index) != p->dir))
 		return -EINVAL;
 
 	return 0;
@@ -1513,20 +1513,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 			return -EINVAL;
 		}
 
-		switch (ut[i].id.proto) {
-		case IPPROTO_AH:
-		case IPPROTO_ESP:
-		case IPPROTO_COMP:
-#if IS_ENABLED(CONFIG_IPV6)
-		case IPPROTO_ROUTING:
-		case IPPROTO_DSTOPTS:
-#endif
-		case IPSEC_PROTO_ANY:
-			break;
-		default:
+		if (!xfrm_id_proto_valid(ut[i].id.proto))
 			return -EINVAL;
-		}
-
 	}
 
 	return 0;
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 76ca30cc4791..0c5969fa795f 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -222,6 +222,9 @@ endif
 ifdef CONFIG_RETPOLINE
   objtool_args += --retpoline
 endif
+ifdef CONFIG_X86_SMAP
+  objtool_args += --uaccess
+endif
 
 # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file
diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan
index 38b2b4818e8e..019771b845c5 100644
--- a/scripts/Makefile.ubsan
+++ b/scripts/Makefile.ubsan
@@ -3,7 +3,6 @@ ifdef CONFIG_UBSAN
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=shift)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=integer-divide-by-zero)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=unreachable)
-      CFLAGS_UBSAN += $(call cc-option, -fsanitize=vla-bound)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=signed-integer-overflow)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=bounds)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=object-size)
diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c
index 1ceedea847dd..544ca126a8a8 100644
--- a/scripts/selinux/genheaders/genheaders.c
+++ b/scripts/selinux/genheaders/genheaders.c
@@ -9,7 +9,6 @@
 #include <string.h>
 #include <errno.h>
 #include <ctype.h>
-#include <sys/socket.h>
 
 struct security_class_mapping {
 	const char *name;
diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c
index 073fe7537f6c..6d51b74bc679 100644
--- a/scripts/selinux/mdp/mdp.c
+++ b/scripts/selinux/mdp/mdp.c
@@ -32,7 +32,6 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
-#include <sys/socket.h>
 
 static void usage(char *name)
 {
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index fefee040bf79..b9298d2e8165 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -123,17 +123,22 @@ static int aafs_show_path(struct seq_file *seq, struct dentry *dentry)
 	return 0;
 }
 
-static void aafs_evict_inode(struct inode *inode)
+static void aafs_i_callback(struct rcu_head *head)
 {
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static void aafs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, aafs_i_callback);
 }
 
 static const struct super_operations aafs_super_ops = {
 	.statfs = simple_statfs,
-	.evict_inode = aafs_evict_inode,
+	.destroy_inode = aafs_destroy_inode,
 	.show_path = aafs_show_path,
 };
 
diff --git a/security/inode.c b/security/inode.c
index b7772a9b315e..421dd72b5876 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -27,17 +27,22 @@
 static struct vfsmount *mount;
 static int mount_count;
 
-static void securityfs_evict_inode(struct inode *inode)
+static void securityfs_i_callback(struct rcu_head *head)
 {
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static void securityfs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, securityfs_i_callback);
 }
 
 static const struct super_operations securityfs_super_operations = {
 	.statfs		= simple_statfs,
-	.evict_inode	= securityfs_evict_inode,
+	.destroy_inode	= securityfs_destroy_inode,
 };
 
 static int fill_super(struct super_block *sb, void *data, int silent)
diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig
index 2ea4ec9991d5..3ba1168b1756 100644
--- a/security/integrity/Kconfig
+++ b/security/integrity/Kconfig
@@ -55,13 +55,22 @@ config INTEGRITY_PLATFORM_KEYRING
         bool "Provide keyring for platform/firmware trusted keys"
         depends on INTEGRITY_ASYMMETRIC_KEYS
         depends on SYSTEM_BLACKLIST_KEYRING
-        depends on EFI
         help
          Provide a separate, distinct keyring for platform trusted keys, which
          the kernel automatically populates during initialization from values
          provided by the platform for verifying the kexec'ed kerned image
          and, possibly, the initramfs signature.
 
+config LOAD_UEFI_KEYS
+       depends on INTEGRITY_PLATFORM_KEYRING
+       depends on EFI
+       def_bool y
+
+config LOAD_IPL_KEYS
+       depends on INTEGRITY_PLATFORM_KEYRING
+       depends on S390
+       def_bool y
+
 config INTEGRITY_AUDIT
 	bool "Enables integrity auditing support "
 	depends on AUDIT
diff --git a/security/integrity/Makefile b/security/integrity/Makefile
index 86df9aba8c0f..19faace69644 100644
--- a/security/integrity/Makefile
+++ b/security/integrity/Makefile
@@ -9,10 +9,10 @@ integrity-y := iint.o
 integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o
 integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o
 integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o
-integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o \
-						  platform_certs/efi_parser.o \
-						  platform_certs/load_uefi.o
-obj-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/load_uefi.o
+integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o
+integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \
+					platform_certs/load_uefi.o
+integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o
 $(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar
 
 subdir-$(CONFIG_IMA)			+= ima
diff --git a/security/integrity/platform_certs/load_ipl_s390.c b/security/integrity/platform_certs/load_ipl_s390.c
new file mode 100644
index 000000000000..e769dcb7ea94
--- /dev/null
+++ b/security/integrity/platform_certs/load_ipl_s390.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include <asm/boot_data.h>
+#include "../integrity.h"
+
+/*
+ * Load the certs contained in the IPL report created by the machine loader
+ * into the platform trusted keyring.
+ */
+static int __init load_ipl_certs(void)
+{
+	void *ptr, *end;
+	unsigned int len;
+
+	if (!ipl_cert_list_addr)
+		return 0;
+	/* Copy the certificates to the system keyring */
+	ptr = (void *) ipl_cert_list_addr;
+	end = ptr + ipl_cert_list_size;
+	while ((void *) ptr < end) {
+		len = *(unsigned int *) ptr;
+		ptr += sizeof(unsigned int);
+		add_to_platform_keyring("IPL:db", ptr, len);
+		ptr += len;
+	}
+	return 0;
+}
+late_initcall(load_ipl_certs);
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index bd5fe0d3204a..201f7e588a29 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/capability.h>
+#include <linux/socket.h>
 
 #define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \
     "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append", "map"
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f5b510f119ed..42cd3945e0de 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5450,6 +5450,8 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 		return;
 
 	spec->gen.preferred_dacs = preferred_pairs;
+	spec->gen.auto_mute_via_amp = 1;
+	codec->power_save_node = 0;
 }
 
 /* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */
@@ -7268,6 +7270,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x14, 0x90170110},
+		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x02211020}),
@@ -7541,6 +7547,13 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},
 		{0x21, 0x04211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC294_FIXUP_ASUS_SPK,
+		{0x12, 0x90a60130},
+		{0x17, 0x90170110},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170110},
+		{0x21, 0x04211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC295_STANDARD_PINS,
 		{0x17, 0x21014020},
diff --git a/sound/soc/intel/boards/bytcht_da7213.c b/sound/soc/intel/boards/bytcht_da7213.c
index b8e884803777..4decba338156 100644
--- a/sound/soc/intel/boards/bytcht_da7213.c
+++ b/sound/soc/intel/boards/bytcht_da7213.c
@@ -226,7 +226,7 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
 	struct snd_soc_card *card;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	int dai_index = 0;
 	int ret_val = 0;
 	int i;
@@ -244,10 +244,11 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(codec_name, sizeof(codec_name),
-			"%s%s", "i2c-", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		dailink[dai_index].codec_name = codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index d2a7e6ba11ae..6937c00cf63d 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -442,7 +442,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	struct device *codec_dev;
 	int dai_index = 0;
 	int i;
@@ -463,10 +463,11 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(codec_name, sizeof(codec_name),
-			"%s%s", "i2c-", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		byt_cht_es8316_dais[dai_index].codec_name = codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 940eb27158da..f9175cf6747e 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -1154,7 +1154,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	struct byt_rt5640_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	int ret_val = 0;
 	int dai_index = 0;
 	int i;
@@ -1178,11 +1178,11 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(byt_rt5640_codec_name, sizeof(byt_rt5640_codec_name),
-			"%s%s", "i2c-", i2c_name);
-
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		byt_rt5640_dais[dai_index].codec_name = byt_rt5640_codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index b0a4d297176e..b744add01d12 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -867,8 +867,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
+	struct acpi_device *adev;
 	struct device *codec_dev;
-	const char *i2c_name = NULL;
 	const char *hp_swapped;
 	bool is_bytcr = false;
 	int ret_val = 0;
@@ -894,14 +894,16 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (!i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
+		snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name),
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
+		byt_rt5651_dais[dai_index].codec_name = byt_rt5651_codec_name;
+	} else {
 		dev_err(&pdev->dev, "Error cannot find '%s' dev\n", mach->id);
 		return -ENODEV;
 	}
-	snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name),
-		"%s%s", "i2c-", i2c_name);
-	byt_rt5651_dais[dai_index].codec_name = byt_rt5651_codec_name;
 
 	codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL,
 					    byt_rt5651_codec_name);
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index cbc2d458483f..32dbeaf1ab94 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -532,7 +532,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
 	struct cht_mc_private *drv;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	bool found = false;
 	bool is_bytcr = false;
 	int dai_index = 0;
@@ -573,10 +573,11 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 		}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(cht_rt5645_codec_name, sizeof(cht_rt5645_codec_name),
-			"%s%s", "i2c-", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		cht_dailink[dai_index].codec_name = cht_rt5645_codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
index 3d5a2b3a06f0..0f7770822388 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
@@ -401,7 +401,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	struct cht_mc_private *drv;
 	struct snd_soc_acpi_mach *mach = pdev->dev.platform_data;
 	const char *platform_name;
-	const char *i2c_name;
+	struct acpi_device *adev;
 	int i;
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
@@ -411,10 +411,11 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	strcpy(drv->codec_name, RT5672_I2C_DEFAULT);
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(drv->codec_name, sizeof(drv->codec_name),
-			 "i2c-%s", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) {
 			if (!strcmp(cht_dailink[i].codec_name,
 				RT5672_I2C_DEFAULT)) {
diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c
index 1cfca698ae4b..b0fa285c7ba2 100644
--- a/sound/soc/txx9/txx9aclc-ac97.c
+++ b/sound/soc/txx9/txx9aclc-ac97.c
@@ -102,7 +102,6 @@ static void txx9aclc_ac97_cold_reset(struct snd_ac97 *ac97)
 	u32 ready = ACINT_CODECRDY(ac97->num) | ACINT_REGACCRDY;
 
 	__raw_writel(ACCTL_ENLINK, base + ACCTLDIS);
-	mmiowb();
 	udelay(1);
 	__raw_writel(ACCTL_ENLINK, base + ACCTLEN);
 	/* wait for primary codec ready status */
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 7afe8fae4939..b61f65bed4e4 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -351,12 +351,16 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 {
 	struct usb_device *usbdev = line6->usbdev;
 	int ret;
-	unsigned char len;
+	unsigned char *len;
 	unsigned count;
 
 	if (address > 0xffff || datalen > 0xff)
 		return -EINVAL;
 
+	len = kmalloc(sizeof(*len), GFP_KERNEL);
+	if (!len)
+		return -ENOMEM;
+
 	/* query the serial number: */
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67,
 			      USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
@@ -365,7 +369,7 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 
 	if (ret < 0) {
 		dev_err(line6->ifcdev, "read request failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	/* Wait for data length. We'll get 0xff until length arrives. */
@@ -375,28 +379,29 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 		ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67,
 				      USB_TYPE_VENDOR | USB_RECIP_DEVICE |
 				      USB_DIR_IN,
-				      0x0012, 0x0000, &len, 1,
+				      0x0012, 0x0000, len, 1,
 				      LINE6_TIMEOUT * HZ);
 		if (ret < 0) {
 			dev_err(line6->ifcdev,
 				"receive length failed (error %d)\n", ret);
-			return ret;
+			goto exit;
 		}
 
-		if (len != 0xff)
+		if (*len != 0xff)
 			break;
 	}
 
-	if (len == 0xff) {
+	ret = -EIO;
+	if (*len == 0xff) {
 		dev_err(line6->ifcdev, "read failed after %d retries\n",
 			count);
-		return -EIO;
-	} else if (len != datalen) {
+		goto exit;
+	} else if (*len != datalen) {
 		/* should be equal or something went wrong */
 		dev_err(line6->ifcdev,
 			"length mismatch (expected %d, got %d)\n",
-			(int)datalen, (int)len);
-		return -EIO;
+			(int)datalen, (int)*len);
+		goto exit;
 	}
 
 	/* receive the result: */
@@ -405,12 +410,12 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 			      0x0013, 0x0000, data, datalen,
 			      LINE6_TIMEOUT * HZ);
 
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(line6->ifcdev, "read failed (error %d)\n", ret);
-		return ret;
-	}
 
-	return 0;
+exit:
+	kfree(len);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(line6_read_data);
 
@@ -422,12 +427,16 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data,
 {
 	struct usb_device *usbdev = line6->usbdev;
 	int ret;
-	unsigned char status;
+	unsigned char *status;
 	int count;
 
 	if (address > 0xffff || datalen > 0xffff)
 		return -EINVAL;
 
+	status = kmalloc(sizeof(*status), GFP_KERNEL);
+	if (!status)
+		return -ENOMEM;
+
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67,
 			      USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
 			      0x0022, address, data, datalen,
@@ -436,7 +445,7 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data,
 	if (ret < 0) {
 		dev_err(line6->ifcdev,
 			"write request failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	for (count = 0; count < LINE6_READ_WRITE_MAX_RETRIES; count++) {
@@ -447,28 +456,29 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data,
 				      USB_TYPE_VENDOR | USB_RECIP_DEVICE |
 				      USB_DIR_IN,
 				      0x0012, 0x0000,
-				      &status, 1, LINE6_TIMEOUT * HZ);
+				      status, 1, LINE6_TIMEOUT * HZ);
 
 		if (ret < 0) {
 			dev_err(line6->ifcdev,
 				"receiving status failed (error %d)\n", ret);
-			return ret;
+			goto exit;
 		}
 
-		if (status != 0xff)
+		if (*status != 0xff)
 			break;
 	}
 
-	if (status == 0xff) {
+	if (*status == 0xff) {
 		dev_err(line6->ifcdev, "write failed after %d retries\n",
 			count);
-		return -EIO;
-	} else if (status != 0) {
+		ret = -EIO;
+	} else if (*status != 0) {
 		dev_err(line6->ifcdev, "write failed (error %d)\n", ret);
-		return -EIO;
+		ret = -EIO;
 	}
-
-	return 0;
+exit:
+	kfree(status);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(line6_write_data);
 
diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c
index 36ed9c85c0eb..5f3c87264e66 100644
--- a/sound/usb/line6/podhd.c
+++ b/sound/usb/line6/podhd.c
@@ -225,28 +225,32 @@ static void podhd_startup_start_workqueue(struct timer_list *t)
 static int podhd_dev_start(struct usb_line6_podhd *pod)
 {
 	int ret;
-	u8 init_bytes[8];
+	u8 *init_bytes;
 	int i;
 	struct usb_device *usbdev = pod->line6.usbdev;
 
+	init_bytes = kmalloc(8, GFP_KERNEL);
+	if (!init_bytes)
+		return -ENOMEM;
+
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0),
 					0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
 					0x11, 0,
 					NULL, 0, LINE6_TIMEOUT * HZ);
 	if (ret < 0) {
 		dev_err(pod->line6.ifcdev, "read request failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	/* NOTE: looks like some kind of ping message */
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67,
 					USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
 					0x11, 0x0,
-					&init_bytes, 3, LINE6_TIMEOUT * HZ);
+					init_bytes, 3, LINE6_TIMEOUT * HZ);
 	if (ret < 0) {
 		dev_err(pod->line6.ifcdev,
 			"receive length failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	pod->firmware_version =
@@ -255,7 +259,7 @@ static int podhd_dev_start(struct usb_line6_podhd *pod)
 	for (i = 0; i <= 16; i++) {
 		ret = line6_read_data(&pod->line6, 0xf000 + 0x08 * i, init_bytes, 8);
 		if (ret < 0)
-			return ret;
+			goto exit;
 	}
 
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0),
@@ -263,10 +267,9 @@ static int podhd_dev_start(struct usb_line6_podhd *pod)
 					USB_TYPE_STANDARD | USB_RECIP_DEVICE | USB_DIR_OUT,
 					1, 0,
 					NULL, 0, LINE6_TIMEOUT * HZ);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+exit:
+	kfree(init_bytes);
+	return ret;
 }
 
 static void podhd_startup_workqueue(struct work_struct *work)
diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c
index f47ba94e6f4a..19bee725de00 100644
--- a/sound/usb/line6/toneport.c
+++ b/sound/usb/line6/toneport.c
@@ -365,16 +365,21 @@ static bool toneport_has_source_select(struct usb_line6_toneport *toneport)
 /*
 	Setup Toneport device.
 */
-static void toneport_setup(struct usb_line6_toneport *toneport)
+static int toneport_setup(struct usb_line6_toneport *toneport)
 {
-	u32 ticks;
+	u32 *ticks;
 	struct usb_line6 *line6 = &toneport->line6;
 	struct usb_device *usbdev = line6->usbdev;
 
+	ticks = kmalloc(sizeof(*ticks), GFP_KERNEL);
+	if (!ticks)
+		return -ENOMEM;
+
 	/* sync time on device with host: */
 	/* note: 32-bit timestamps overflow in year 2106 */
-	ticks = (u32)ktime_get_real_seconds();
-	line6_write_data(line6, 0x80c6, &ticks, 4);
+	*ticks = (u32)ktime_get_real_seconds();
+	line6_write_data(line6, 0x80c6, ticks, 4);
+	kfree(ticks);
 
 	/* enable device: */
 	toneport_send_cmd(usbdev, 0x0301, 0x0000);
@@ -389,6 +394,7 @@ static void toneport_setup(struct usb_line6_toneport *toneport)
 		toneport_update_led(toneport);
 
 	mod_timer(&toneport->timer, jiffies + TONEPORT_PCM_DELAY * HZ);
+	return 0;
 }
 
 /*
@@ -451,7 +457,9 @@ static int toneport_init(struct usb_line6 *line6,
 			return err;
 	}
 
-	toneport_setup(toneport);
+	err = toneport_setup(toneport);
+	if (err)
+		return err;
 
 	/* register audio system: */
 	return snd_card_register(line6->card);
@@ -463,7 +471,11 @@ static int toneport_init(struct usb_line6 *line6,
 */
 static int toneport_reset_resume(struct usb_interface *interface)
 {
-	toneport_setup(usb_get_intfdata(interface));
+	int err;
+
+	err = toneport_setup(usb_get_intfdata(interface));
+	if (err)
+		return err;
 	return line6_resume(interface);
 }
 #endif
diff --git a/tools/arch/arc/include/uapi/asm/unistd.h b/tools/arch/arc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5eafa1115162
--- /dev/null
+++ b/tools/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
+#define _UAPI_ASM_ARC_UNISTD_H
+
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls	__NR_syscalls
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
+/* ARC specific syscall */
+#define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#undef __SYSCALL
+
+#endif
diff --git a/tools/arch/hexagon/include/uapi/asm/unistd.h b/tools/arch/hexagon/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..432c4db1b623
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/unistd.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Syscall support for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+/*
+ *  The kernel pulls this unistd.h in three different ways:
+ *  1.  the "normal" way which gets all the __NR defines
+ *  2.  with __SYSCALL defined to produce function declarations
+ *  3.  with __SYSCALL defined to produce syscall table initialization
+ *  See also:  syscalltab.c
+ */
+
+#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/riscv/include/uapi/asm/unistd.h b/tools/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..0e2eeeb1fd27
--- /dev/null
+++ b/tools/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef __LP64__
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
+#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e0c650d91784..994a7e0d16fb 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1151,6 +1151,9 @@ static int do_create(int argc, char **argv)
 				return -1;
 			}
 			NEXT_ARG();
+		} else {
+			p_err("unknown arg %s", *argv);
+			return -1;
 		}
 	}
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 8d3864b061f3..361207387b1b 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -67,6 +67,7 @@ FEATURE_TESTS_BASIC :=                  \
         sdt				\
         setns				\
         libaio				\
+        libzstd				\
         disassembler-four-args
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
@@ -120,6 +121,7 @@ FEATURE_DISPLAY ?=              \
          get_cpuid              \
          bpf			\
          libaio			\
+         libzstd		\
          disassembler-four-args
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 7ceb4441b627..4b8244ee65ce 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -62,7 +62,8 @@ FILES=                                          \
          test-clang.bin				\
          test-llvm.bin				\
          test-llvm-version.bin			\
-         test-libaio.bin
+         test-libaio.bin			\
+         test-libzstd.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -301,6 +302,9 @@ $(OUTPUT)test-clang.bin:
 $(OUTPUT)test-libaio.bin:
 	$(BUILD) -lrt
 
+$(OUTPUT)test-libzstd.bin:
+	$(BUILD) -lzstd
+
 ###############################
 
 clean:
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 7853e6d91090..a59c53705093 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -182,6 +182,10 @@
 # include "test-disassembler-four-args.c"
 #undef main
 
+#define main main_test_zstd
+# include "test-libzstd.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -224,6 +228,7 @@ int main(int argc, char *argv[])
 	main_test_libaio();
 	main_test_reallocarray();
 	main_test_disassembler_four_args();
+	main_test_libzstd();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-libzstd.c b/tools/build/feature/test-libzstd.c
new file mode 100644
index 000000000000..55268c01b84d
--- /dev/null
+++ b/tools/build/feature/test-libzstd.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <zstd.h>
+
+int main(void)
+{
+	ZSTD_CStream	*cstream;
+
+	cstream = ZSTD_createCStream();
+	ZSTD_freeCStream(cstream);
+
+	return 0;
+}
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 4db74758c674..fecb78afea3f 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,3 +1,4 @@
 libbpf_version.h
 FEATURE-DUMP.libbpf
 test_libbpf
+libbpf.so.*
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
index d463761a58f4..988587840c80 100644
--- a/tools/lib/traceevent/event-parse-api.c
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -9,6 +9,22 @@
 #include "event-utils.h"
 
 /**
+ * tep_get_event - returns the event with the given index
+ * @tep: a handle to the tep_handle
+ * @index: index of the requested event, in the range 0 .. nr_events
+ *
+ * This returns pointer to the element of the events array with the given index
+ * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned.
+ */
+struct tep_event *tep_get_event(struct tep_handle *tep, int index)
+{
+	if (tep && tep->events && index < tep->nr_events)
+		return tep->events[index];
+
+	return NULL;
+}
+
+/**
  * tep_get_first_event - returns the first event in the events array
  * @tep: a handle to the tep_handle
  *
@@ -17,10 +33,7 @@
  */
 struct tep_event *tep_get_first_event(struct tep_handle *tep)
 {
-	if (tep && tep->events)
-		return tep->events[0];
-
-	return NULL;
+	return tep_get_event(tep, 0);
 }
 
 /**
@@ -32,7 +45,7 @@ struct tep_event *tep_get_first_event(struct tep_handle *tep)
  */
 int tep_get_events_count(struct tep_handle *tep)
 {
-	if(tep)
+	if (tep)
 		return tep->nr_events;
 	return 0;
 }
@@ -43,19 +56,47 @@ int tep_get_events_count(struct tep_handle *tep)
  * @flag: flag, or combination of flags to be set
  * can be any combination from enum tep_flag
  *
- * This sets a flag or mbination of flags  from enum tep_flag
-  */
+ * This sets a flag or combination of flags from enum tep_flag
+ */
 void tep_set_flag(struct tep_handle *tep, int flag)
 {
-	if(tep)
+	if (tep)
 		tep->flags |= flag;
 }
 
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
+/**
+ * tep_clear_flag - clear event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be cleared
+ *
+ * This clears a tep flag
+ */
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+	if (tep)
+		tep->flags &= ~flag;
+}
+
+/**
+ * tep_test_flag - check the state of event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be checked
+ *
+ * This returns the state of the requested tep flag.
+ * Returns: true if the flag is set, false otherwise.
+ */
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+	if (tep)
+		return tep->flags & flag;
+	return false;
+}
+
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data)
 {
 	unsigned short swap;
 
-	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+	if (!tep || tep->host_bigendian == tep->file_bigendian)
 		return data;
 
 	swap = ((data & 0xffULL) << 8) |
@@ -64,11 +105,11 @@ unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
 	return swap;
 }
 
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data)
 {
 	unsigned int swap;
 
-	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+	if (!tep || tep->host_bigendian == tep->file_bigendian)
 		return data;
 
 	swap = ((data & 0xffULL) << 24) |
@@ -80,11 +121,11 @@ unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
 }
 
 unsigned long long
-tep_data2host8(struct tep_handle *pevent, unsigned long long data)
+tep_data2host8(struct tep_handle *tep, unsigned long long data)
 {
 	unsigned long long swap;
 
-	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+	if (!tep || tep->host_bigendian == tep->file_bigendian)
 		return data;
 
 	swap = ((data & 0xffULL) << 56) |
@@ -101,175 +142,232 @@ tep_data2host8(struct tep_handle *pevent, unsigned long long data)
 
 /**
  * tep_get_header_page_size - get size of the header page
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
  * This returns size of the header page
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *tep)
+{
+	if (tep)
+		return tep->header_page_size_size;
+	return 0;
+}
+
+/**
+ * tep_get_header_timestamp_size - get size of the timestamp in the header page
+ * @tep: a handle to the tep_handle
+ *
+ * This returns size of the timestamp in the header page
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_header_page_size(struct tep_handle *pevent)
+int tep_get_header_timestamp_size(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->header_page_size_size;
+	if (tep)
+		return tep->header_page_ts_size;
 	return 0;
 }
 
 /**
  * tep_get_cpus - get the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
  * This returns the number of CPUs
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_cpus(struct tep_handle *pevent)
+int tep_get_cpus(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->cpus;
+	if (tep)
+		return tep->cpus;
 	return 0;
 }
 
 /**
  * tep_set_cpus - set the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
  * This sets the number of CPUs
  */
-void tep_set_cpus(struct tep_handle *pevent, int cpus)
+void tep_set_cpus(struct tep_handle *tep, int cpus)
 {
-	if(pevent)
-		pevent->cpus = cpus;
+	if (tep)
+		tep->cpus = cpus;
 }
 
 /**
- * tep_get_long_size - get the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_long_size - get the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
  *
- * This returns the size of a long integer on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a long integer on the traced machine
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_long_size(struct tep_handle *pevent)
+int tep_get_long_size(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->long_size;
+	if (tep)
+		return tep->long_size;
 	return 0;
 }
 
 /**
- * tep_set_long_size - set the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_long_size - set the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
  * @size: size, in bytes, of a long integer
  *
- * This sets the size of a long integer on the current machine
+ * This sets the size of a long integer on the traced machine
  */
-void tep_set_long_size(struct tep_handle *pevent, int long_size)
+void tep_set_long_size(struct tep_handle *tep, int long_size)
 {
-	if(pevent)
-		pevent->long_size = long_size;
+	if (tep)
+		tep->long_size = long_size;
 }
 
 /**
- * tep_get_page_size - get the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_page_size - get the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
  *
- * This returns the size of a memory page on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a memory page on the traced machine
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_page_size(struct tep_handle *pevent)
+int tep_get_page_size(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->page_size;
+	if (tep)
+		return tep->page_size;
 	return 0;
 }
 
 /**
- * tep_set_page_size - set the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_page_size - set the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
  * @_page_size: size of a memory page, in bytes
  *
- * This sets the size of a memory page on the current machine
+ * This sets the size of a memory page on the traced machine
  */
-void tep_set_page_size(struct tep_handle *pevent, int _page_size)
+void tep_set_page_size(struct tep_handle *tep, int _page_size)
 {
-	if(pevent)
-		pevent->page_size = _page_size;
+	if (tep)
+		tep->page_size = _page_size;
 }
 
 /**
- * tep_file_bigendian - get if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * tep_is_file_bigendian - return the endian of the file
+ * @tep: a handle to the tep_handle
  *
- * This returns if the file is in big endian order
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the file is in big endian order
+ * If @tep is NULL, false is returned.
  */
-int tep_file_bigendian(struct tep_handle *pevent)
+bool tep_is_file_bigendian(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->file_bigendian;
-	return 0;
+	if (tep)
+		return (tep->file_bigendian == TEP_BIG_ENDIAN);
+	return false;
 }
 
 /**
  * tep_set_file_bigendian - set if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  * @endian: non zero, if the file is in big endian order
  *
  * This sets if the file is in big endian order
  */
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian)
 {
-	if(pevent)
-		pevent->file_bigendian = endian;
+	if (tep)
+		tep->file_bigendian = endian;
 }
 
 /**
- * tep_is_host_bigendian - get if the order of the current host is big endian
- * @pevent: a handle to the tep_handle
+ * tep_is_local_bigendian - return the endian of the saved local machine
+ * @tep: a handle to the tep_handle
  *
- * This gets if the order of the current host is big endian
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the saved local machine in @tep is big endian.
+ * If @tep is NULL, false is returned.
  */
-int tep_is_host_bigendian(struct tep_handle *pevent)
+bool tep_is_local_bigendian(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->host_bigendian;
+	if (tep)
+		return (tep->host_bigendian == TEP_BIG_ENDIAN);
 	return 0;
 }
 
 /**
- * tep_set_host_bigendian - set the order of the local host
- * @pevent: a handle to the tep_handle
+ * tep_set_local_bigendian - set the stored local machine endian order
+ * @tep: a handle to the tep_handle
  * @endian: non zero, if the local host has big endian order
  *
- * This sets the order of the local host
+ * This sets the endian order for the local machine.
  */
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian)
 {
-	if(pevent)
-		pevent->host_bigendian = endian;
+	if (tep)
+		tep->host_bigendian = endian;
 }
 
 /**
  * tep_is_latency_format - get if the latency output format is configured
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
- * This gets if the latency output format is configured
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the latency output format is configured
+ * If @tep is NULL, false is returned.
  */
-int tep_is_latency_format(struct tep_handle *pevent)
+bool tep_is_latency_format(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->latency_format;
-	return 0;
+	if (tep)
+		return (tep->latency_format);
+	return false;
 }
 
 /**
  * tep_set_latency_format - set the latency output format
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  * @lat: non zero for latency output format
  *
  * This sets the latency output format
   */
-void tep_set_latency_format(struct tep_handle *pevent, int lat)
+void tep_set_latency_format(struct tep_handle *tep, int lat)
+{
+	if (tep)
+		tep->latency_format = lat;
+}
+
+/**
+ * tep_is_old_format - get if an old kernel is used
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true, if an old kernel is used to generate the tracing events or
+ * false if a new kernel is used. Old kernels did not have header page info.
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_old_format(struct tep_handle *tep)
+{
+	if (tep)
+		return tep->old_format;
+	return false;
+}
+
+/**
+ * tep_set_print_raw - set a flag to force print in raw format
+ * @tep: a handle to the tep_handle
+ * @print_raw: the new value of the print_raw flag
+ *
+ * This sets a flag to force print in raw format
+ */
+void tep_set_print_raw(struct tep_handle *tep, int print_raw)
+{
+	if (tep)
+		tep->print_raw = print_raw;
+}
+
+/**
+ * tep_set_test_filters - set a flag to test a filter string
+ * @tep: a handle to the tep_handle
+ * @test_filters: the new value of the test_filters flag
+ *
+ * This sets a flag to test a filter string. If this flag is set, when
+ * tep_filter_add_filter_str() API as called,it will print the filter string
+ * instead of adding it.
+ */
+void tep_set_test_filters(struct tep_handle *tep, int test_filters)
 {
-	if(pevent)
-		pevent->latency_format = lat;
+	if (tep)
+		tep->test_filters = test_filters;
 }
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
index 35833ee32d6c..09aa142f7fdd 100644
--- a/tools/lib/traceevent/event-parse-local.h
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -92,8 +92,8 @@ struct tep_handle {
 void tep_free_event(struct tep_event *event);
 void tep_free_format_field(struct tep_format_field *field);
 
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data);
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data);
-unsigned long long tep_data2host8(struct tep_handle *pevent, unsigned long long data);
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data);
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data);
+unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data);
 
 #endif /* _PARSE_EVENTS_INT_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 981c6ce2da2c..b36b536a9fcb 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -148,14 +148,14 @@ struct cmdline_list {
 	int			pid;
 };
 
-static int cmdline_init(struct tep_handle *pevent)
+static int cmdline_init(struct tep_handle *tep)
 {
-	struct cmdline_list *cmdlist = pevent->cmdlist;
+	struct cmdline_list *cmdlist = tep->cmdlist;
 	struct cmdline_list *item;
 	struct tep_cmdline *cmdlines;
 	int i;
 
-	cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
+	cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count);
 	if (!cmdlines)
 		return -1;
 
@@ -169,15 +169,15 @@ static int cmdline_init(struct tep_handle *pevent)
 		free(item);
 	}
 
-	qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+	qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
 
-	pevent->cmdlines = cmdlines;
-	pevent->cmdlist = NULL;
+	tep->cmdlines = cmdlines;
+	tep->cmdlist = NULL;
 
 	return 0;
 }
 
-static const char *find_cmdline(struct tep_handle *pevent, int pid)
+static const char *find_cmdline(struct tep_handle *tep, int pid)
 {
 	const struct tep_cmdline *comm;
 	struct tep_cmdline key;
@@ -185,13 +185,13 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
 	if (!pid)
 		return "<idle>";
 
-	if (!pevent->cmdlines && cmdline_init(pevent))
+	if (!tep->cmdlines && cmdline_init(tep))
 		return "<not enough memory for cmdlines!>";
 
 	key.pid = pid;
 
-	comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
-		       sizeof(*pevent->cmdlines), cmdline_cmp);
+	comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+		       sizeof(*tep->cmdlines), cmdline_cmp);
 
 	if (comm)
 		return comm->comm;
@@ -199,32 +199,32 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
 }
 
 /**
- * tep_pid_is_registered - return if a pid has a cmdline registered
- * @pevent: handle for the pevent
+ * tep_is_pid_registered - return if a pid has a cmdline registered
+ * @tep: a handle to the trace event parser context
  * @pid: The pid to check if it has a cmdline registered with.
  *
- * Returns 1 if the pid has a cmdline mapped to it
- * 0 otherwise.
+ * Returns true if the pid has a cmdline mapped to it
+ * false otherwise.
  */
-int tep_pid_is_registered(struct tep_handle *pevent, int pid)
+bool tep_is_pid_registered(struct tep_handle *tep, int pid)
 {
 	const struct tep_cmdline *comm;
 	struct tep_cmdline key;
 
 	if (!pid)
-		return 1;
+		return true;
 
-	if (!pevent->cmdlines && cmdline_init(pevent))
-		return 0;
+	if (!tep->cmdlines && cmdline_init(tep))
+		return false;
 
 	key.pid = pid;
 
-	comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
-		       sizeof(*pevent->cmdlines), cmdline_cmp);
+	comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+		       sizeof(*tep->cmdlines), cmdline_cmp);
 
 	if (comm)
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 
 /*
@@ -232,10 +232,10 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid)
  * we must add this pid. This is much slower than when cmdlines
  * are added before the array is initialized.
  */
-static int add_new_comm(struct tep_handle *pevent,
+static int add_new_comm(struct tep_handle *tep,
 			const char *comm, int pid, bool override)
 {
-	struct tep_cmdline *cmdlines = pevent->cmdlines;
+	struct tep_cmdline *cmdlines = tep->cmdlines;
 	struct tep_cmdline *cmdline;
 	struct tep_cmdline key;
 	char *new_comm;
@@ -246,8 +246,8 @@ static int add_new_comm(struct tep_handle *pevent,
 	/* avoid duplicates */
 	key.pid = pid;
 
-	cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
-		       sizeof(*pevent->cmdlines), cmdline_cmp);
+	cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+			  sizeof(*tep->cmdlines), cmdline_cmp);
 	if (cmdline) {
 		if (!override) {
 			errno = EEXIST;
@@ -264,37 +264,37 @@ static int add_new_comm(struct tep_handle *pevent,
 		return 0;
 	}
 
-	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
+	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1));
 	if (!cmdlines) {
 		errno = ENOMEM;
 		return -1;
 	}
 
-	cmdlines[pevent->cmdline_count].comm = strdup(comm);
-	if (!cmdlines[pevent->cmdline_count].comm) {
+	cmdlines[tep->cmdline_count].comm = strdup(comm);
+	if (!cmdlines[tep->cmdline_count].comm) {
 		free(cmdlines);
 		errno = ENOMEM;
 		return -1;
 	}
 
-	cmdlines[pevent->cmdline_count].pid = pid;
+	cmdlines[tep->cmdline_count].pid = pid;
 		
-	if (cmdlines[pevent->cmdline_count].comm)
-		pevent->cmdline_count++;
+	if (cmdlines[tep->cmdline_count].comm)
+		tep->cmdline_count++;
 
-	qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
-	pevent->cmdlines = cmdlines;
+	qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+	tep->cmdlines = cmdlines;
 
 	return 0;
 }
 
-static int _tep_register_comm(struct tep_handle *pevent,
+static int _tep_register_comm(struct tep_handle *tep,
 			      const char *comm, int pid, bool override)
 {
 	struct cmdline_list *item;
 
-	if (pevent->cmdlines)
-		return add_new_comm(pevent, comm, pid, override);
+	if (tep->cmdlines)
+		return add_new_comm(tep, comm, pid, override);
 
 	item = malloc(sizeof(*item));
 	if (!item)
@@ -309,17 +309,17 @@ static int _tep_register_comm(struct tep_handle *pevent,
 		return -1;
 	}
 	item->pid = pid;
-	item->next = pevent->cmdlist;
+	item->next = tep->cmdlist;
 
-	pevent->cmdlist = item;
-	pevent->cmdline_count++;
+	tep->cmdlist = item;
+	tep->cmdline_count++;
 
 	return 0;
 }
 
 /**
  * tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @comm: the command line to register
  * @pid: the pid to map the command line to
  *
@@ -327,14 +327,14 @@ static int _tep_register_comm(struct tep_handle *pevent,
  * a given pid. The comm is duplicated. If a command with the same pid
  * already exist, -1 is returned and errno is set to EEXIST
  */
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid)
 {
-	return _tep_register_comm(pevent, comm, pid, false);
+	return _tep_register_comm(tep, comm, pid, false);
 }
 
 /**
  * tep_override_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @comm: the command line to register
  * @pid: the pid to map the command line to
  *
@@ -342,19 +342,19 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
  * a given pid. The comm is duplicated. If a command with the same pid
  * already exist, the command string is udapted with the new one
  */
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid)
 {
-	if (!pevent->cmdlines && cmdline_init(pevent)) {
+	if (!tep->cmdlines && cmdline_init(tep)) {
 		errno = ENOMEM;
 		return -1;
 	}
-	return _tep_register_comm(pevent, comm, pid, true);
+	return _tep_register_comm(tep, comm, pid, true);
 }
 
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock)
 {
-	pevent->trace_clock = strdup(trace_clock);
-	if (!pevent->trace_clock) {
+	tep->trace_clock = strdup(trace_clock);
+	if (!tep->trace_clock) {
 		errno = ENOMEM;
 		return -1;
 	}
@@ -408,18 +408,18 @@ static int func_bcmp(const void *a, const void *b)
 	return 1;
 }
 
-static int func_map_init(struct tep_handle *pevent)
+static int func_map_init(struct tep_handle *tep)
 {
 	struct func_list *funclist;
 	struct func_list *item;
 	struct func_map *func_map;
 	int i;
 
-	func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1));
+	func_map = malloc(sizeof(*func_map) * (tep->func_count + 1));
 	if (!func_map)
 		return -1;
 
-	funclist = pevent->funclist;
+	funclist = tep->funclist;
 
 	i = 0;
 	while (funclist) {
@@ -432,34 +432,34 @@ static int func_map_init(struct tep_handle *pevent)
 		free(item);
 	}
 
-	qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp);
+	qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp);
 
 	/*
 	 * Add a special record at the end.
 	 */
-	func_map[pevent->func_count].func = NULL;
-	func_map[pevent->func_count].addr = 0;
-	func_map[pevent->func_count].mod = NULL;
+	func_map[tep->func_count].func = NULL;
+	func_map[tep->func_count].addr = 0;
+	func_map[tep->func_count].mod = NULL;
 
-	pevent->func_map = func_map;
-	pevent->funclist = NULL;
+	tep->func_map = func_map;
+	tep->funclist = NULL;
 
 	return 0;
 }
 
 static struct func_map *
-__find_func(struct tep_handle *pevent, unsigned long long addr)
+__find_func(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *func;
 	struct func_map key;
 
-	if (!pevent->func_map)
-		func_map_init(pevent);
+	if (!tep->func_map)
+		func_map_init(tep);
 
 	key.addr = addr;
 
-	func = bsearch(&key, pevent->func_map, pevent->func_count,
-		       sizeof(*pevent->func_map), func_bcmp);
+	func = bsearch(&key, tep->func_map, tep->func_count,
+		       sizeof(*tep->func_map), func_bcmp);
 
 	return func;
 }
@@ -472,15 +472,14 @@ struct func_resolver {
 
 /**
  * tep_set_function_resolver - set an alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @resolver: function to be used
  * @priv: resolver function private state.
  *
  * Some tools may have already a way to resolve kernel functions, allow them to
- * keep using it instead of duplicating all the entries inside
- * pevent->funclist.
+ * keep using it instead of duplicating all the entries inside tep->funclist.
  */
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
 			      tep_func_resolver_t *func, void *priv)
 {
 	struct func_resolver *resolver = malloc(sizeof(*resolver));
@@ -491,38 +490,38 @@ int tep_set_function_resolver(struct tep_handle *pevent,
 	resolver->func = func;
 	resolver->priv = priv;
 
-	free(pevent->func_resolver);
-	pevent->func_resolver = resolver;
+	free(tep->func_resolver);
+	tep->func_resolver = resolver;
 
 	return 0;
 }
 
 /**
  * tep_reset_function_resolver - reset alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  *
  * Stop using whatever alternative resolver was set, use the default
  * one instead.
  */
-void tep_reset_function_resolver(struct tep_handle *pevent)
+void tep_reset_function_resolver(struct tep_handle *tep)
 {
-	free(pevent->func_resolver);
-	pevent->func_resolver = NULL;
+	free(tep->func_resolver);
+	tep->func_resolver = NULL;
 }
 
 static struct func_map *
-find_func(struct tep_handle *pevent, unsigned long long addr)
+find_func(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *map;
 
-	if (!pevent->func_resolver)
-		return __find_func(pevent, addr);
+	if (!tep->func_resolver)
+		return __find_func(tep, addr);
 
-	map = &pevent->func_resolver->map;
+	map = &tep->func_resolver->map;
 	map->mod  = NULL;
 	map->addr = addr;
-	map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
-						&map->addr, &map->mod);
+	map->func = tep->func_resolver->func(tep->func_resolver->priv,
+					     &map->addr, &map->mod);
 	if (map->func == NULL)
 		return NULL;
 
@@ -531,18 +530,18 @@ find_func(struct tep_handle *pevent, unsigned long long addr)
 
 /**
  * tep_find_function - find a function by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @addr: the address to find the function with
  *
  * Returns a pointer to the function stored that has the given
  * address. Note, the address does not have to be exact, it
  * will select the function that would contain the address.
  */
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr)
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *map;
 
-	map = find_func(pevent, addr);
+	map = find_func(tep, addr);
 	if (!map)
 		return NULL;
 
@@ -551,7 +550,7 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr
 
 /**
  * tep_find_function_address - find a function address by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @addr: the address to find the function with
  *
  * Returns the address the function starts at. This can be used in
@@ -559,11 +558,11 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr
  * name and the function offset.
  */
 unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *map;
 
-	map = find_func(pevent, addr);
+	map = find_func(tep, addr);
 	if (!map)
 		return 0;
 
@@ -572,7 +571,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
 
 /**
  * tep_register_function - register a function with a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @function: the function name to register
  * @addr: the address the function starts at
  * @mod: the kernel module the function may be in (NULL for none)
@@ -580,7 +579,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
  * This registers a function name with an address and module.
  * The @func passed in is duplicated.
  */
-int tep_register_function(struct tep_handle *pevent, char *func,
+int tep_register_function(struct tep_handle *tep, char *func,
 			  unsigned long long addr, char *mod)
 {
 	struct func_list *item = malloc(sizeof(*item));
@@ -588,7 +587,7 @@ int tep_register_function(struct tep_handle *pevent, char *func,
 	if (!item)
 		return -1;
 
-	item->next = pevent->funclist;
+	item->next = tep->funclist;
 	item->func = strdup(func);
 	if (!item->func)
 		goto out_free;
@@ -601,8 +600,8 @@ int tep_register_function(struct tep_handle *pevent, char *func,
 		item->mod = NULL;
 	item->addr = addr;
 
-	pevent->funclist = item;
-	pevent->func_count++;
+	tep->funclist = item;
+	tep->func_count++;
 
 	return 0;
 
@@ -617,23 +616,23 @@ out_free:
 
 /**
  * tep_print_funcs - print out the stored functions
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  *
  * This prints out the stored functions.
  */
-void tep_print_funcs(struct tep_handle *pevent)
+void tep_print_funcs(struct tep_handle *tep)
 {
 	int i;
 
-	if (!pevent->func_map)
-		func_map_init(pevent);
+	if (!tep->func_map)
+		func_map_init(tep);
 
-	for (i = 0; i < (int)pevent->func_count; i++) {
+	for (i = 0; i < (int)tep->func_count; i++) {
 		printf("%016llx %s",
-		       pevent->func_map[i].addr,
-		       pevent->func_map[i].func);
-		if (pevent->func_map[i].mod)
-			printf(" [%s]\n", pevent->func_map[i].mod);
+		       tep->func_map[i].addr,
+		       tep->func_map[i].func);
+		if (tep->func_map[i].mod)
+			printf(" [%s]\n", tep->func_map[i].mod);
 		else
 			printf("\n");
 	}
@@ -663,18 +662,18 @@ static int printk_cmp(const void *a, const void *b)
 	return 0;
 }
 
-static int printk_map_init(struct tep_handle *pevent)
+static int printk_map_init(struct tep_handle *tep)
 {
 	struct printk_list *printklist;
 	struct printk_list *item;
 	struct printk_map *printk_map;
 	int i;
 
-	printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1));
+	printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1));
 	if (!printk_map)
 		return -1;
 
-	printklist = pevent->printklist;
+	printklist = tep->printklist;
 
 	i = 0;
 	while (printklist) {
@@ -686,41 +685,41 @@ static int printk_map_init(struct tep_handle *pevent)
 		free(item);
 	}
 
-	qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp);
+	qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp);
 
-	pevent->printk_map = printk_map;
-	pevent->printklist = NULL;
+	tep->printk_map = printk_map;
+	tep->printklist = NULL;
 
 	return 0;
 }
 
 static struct printk_map *
-find_printk(struct tep_handle *pevent, unsigned long long addr)
+find_printk(struct tep_handle *tep, unsigned long long addr)
 {
 	struct printk_map *printk;
 	struct printk_map key;
 
-	if (!pevent->printk_map && printk_map_init(pevent))
+	if (!tep->printk_map && printk_map_init(tep))
 		return NULL;
 
 	key.addr = addr;
 
-	printk = bsearch(&key, pevent->printk_map, pevent->printk_count,
-			 sizeof(*pevent->printk_map), printk_cmp);
+	printk = bsearch(&key, tep->printk_map, tep->printk_count,
+			 sizeof(*tep->printk_map), printk_cmp);
 
 	return printk;
 }
 
 /**
  * tep_register_print_string - register a string by its address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @fmt: the string format to register
  * @addr: the address the string was located at
  *
  * This registers a string by the address it was stored in the kernel.
  * The @fmt passed in is duplicated.
  */
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
 			      unsigned long long addr)
 {
 	struct printk_list *item = malloc(sizeof(*item));
@@ -729,7 +728,7 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
 	if (!item)
 		return -1;
 
-	item->next = pevent->printklist;
+	item->next = tep->printklist;
 	item->addr = addr;
 
 	/* Strip off quotes and '\n' from the end */
@@ -747,8 +746,8 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
 	if (strcmp(p, "\\n") == 0)
 		*p = 0;
 
-	pevent->printklist = item;
-	pevent->printk_count++;
+	tep->printklist = item;
+	tep->printk_count++;
 
 	return 0;
 
@@ -760,21 +759,21 @@ out_free:
 
 /**
  * tep_print_printk - print out the stored strings
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  *
  * This prints the string formats that were stored.
  */
-void tep_print_printk(struct tep_handle *pevent)
+void tep_print_printk(struct tep_handle *tep)
 {
 	int i;
 
-	if (!pevent->printk_map)
-		printk_map_init(pevent);
+	if (!tep->printk_map)
+		printk_map_init(tep);
 
-	for (i = 0; i < (int)pevent->printk_count; i++) {
+	for (i = 0; i < (int)tep->printk_count; i++) {
 		printf("%016llx %s\n",
-		       pevent->printk_map[i].addr,
-		       pevent->printk_map[i].printk);
+		       tep->printk_map[i].addr,
+		       tep->printk_map[i].printk);
 	}
 }
 
@@ -783,29 +782,29 @@ static struct tep_event *alloc_event(void)
 	return calloc(1, sizeof(struct tep_event));
 }
 
-static int add_event(struct tep_handle *pevent, struct tep_event *event)
+static int add_event(struct tep_handle *tep, struct tep_event *event)
 {
 	int i;
-	struct tep_event **events = realloc(pevent->events, sizeof(event) *
-					    (pevent->nr_events + 1));
+	struct tep_event **events = realloc(tep->events, sizeof(event) *
+					    (tep->nr_events + 1));
 	if (!events)
 		return -1;
 
-	pevent->events = events;
+	tep->events = events;
 
-	for (i = 0; i < pevent->nr_events; i++) {
-		if (pevent->events[i]->id > event->id)
+	for (i = 0; i < tep->nr_events; i++) {
+		if (tep->events[i]->id > event->id)
 			break;
 	}
-	if (i < pevent->nr_events)
-		memmove(&pevent->events[i + 1],
-			&pevent->events[i],
-			sizeof(event) * (pevent->nr_events - i));
+	if (i < tep->nr_events)
+		memmove(&tep->events[i + 1],
+			&tep->events[i],
+			sizeof(event) * (tep->nr_events - i));
 
-	pevent->events[i] = event;
-	pevent->nr_events++;
+	tep->events[i] = event;
+	tep->nr_events++;
 
-	event->pevent = pevent;
+	event->tep = tep;
 
 	return 0;
 }
@@ -1184,7 +1183,7 @@ static enum tep_event_type read_token(char **tok)
 }
 
 /**
- * tep_read_token - access to utilities to use the pevent parser
+ * tep_read_token - access to utilities to use the tep parser
  * @tok: The token to return
  *
  * This will parse tokens from the string given by
@@ -1657,8 +1656,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 			else if (field->flags & TEP_FIELD_IS_STRING)
 				field->elementsize = 1;
 			else if (field->flags & TEP_FIELD_IS_LONG)
-				field->elementsize = event->pevent ?
-						     event->pevent->long_size :
+				field->elementsize = event->tep ?
+						     event->tep->long_size :
 						     sizeof(long);
 		} else
 			field->elementsize = field->size;
@@ -2942,14 +2941,14 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar
 }
 
 static struct tep_function_handler *
-find_func_handler(struct tep_handle *pevent, char *func_name)
+find_func_handler(struct tep_handle *tep, char *func_name)
 {
 	struct tep_function_handler *func;
 
-	if (!pevent)
+	if (!tep)
 		return NULL;
 
-	for (func = pevent->func_handlers; func; func = func->next) {
+	for (func = tep->func_handlers; func; func = func->next) {
 		if (strcmp(func->name, func_name) == 0)
 			break;
 	}
@@ -2957,12 +2956,12 @@ find_func_handler(struct tep_handle *pevent, char *func_name)
 	return func;
 }
 
-static void remove_func_handler(struct tep_handle *pevent, char *func_name)
+static void remove_func_handler(struct tep_handle *tep, char *func_name)
 {
 	struct tep_function_handler *func;
 	struct tep_function_handler **next;
 
-	next = &pevent->func_handlers;
+	next = &tep->func_handlers;
 	while ((func = *next)) {
 		if (strcmp(func->name, func_name) == 0) {
 			*next = func->next;
@@ -3076,7 +3075,7 @@ process_function(struct tep_event *event, struct tep_print_arg *arg,
 		return process_dynamic_array_len(event, arg, tok);
 	}
 
-	func = find_func_handler(event->pevent, token);
+	func = find_func_handler(event->tep, token);
 	if (func) {
 		free_token(token);
 		return process_func_handler(event, func, arg, tok);
@@ -3357,14 +3356,14 @@ tep_find_any_field(struct tep_event *event, const char *name)
 
 /**
  * tep_read_number - read a number from data
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @ptr: the raw data
  * @size: the size of the data that holds the number
  *
  * Returns the number (converted to host) from the
  * raw data.
  */
-unsigned long long tep_read_number(struct tep_handle *pevent,
+unsigned long long tep_read_number(struct tep_handle *tep,
 				   const void *ptr, int size)
 {
 	unsigned long long val;
@@ -3373,12 +3372,12 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
 	case 1:
 		return *(unsigned char *)ptr;
 	case 2:
-		return tep_data2host2(pevent, *(unsigned short *)ptr);
+		return tep_data2host2(tep, *(unsigned short *)ptr);
 	case 4:
-		return tep_data2host4(pevent, *(unsigned int *)ptr);
+		return tep_data2host4(tep, *(unsigned int *)ptr);
 	case 8:
 		memcpy(&val, (ptr), sizeof(unsigned long long));
-		return tep_data2host8(pevent, val);
+		return tep_data2host8(tep, val);
 	default:
 		/* BUG! */
 		return 0;
@@ -3406,7 +3405,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data,
 	case 2:
 	case 4:
 	case 8:
-		*value = tep_read_number(field->event->pevent,
+		*value = tep_read_number(field->event->tep,
 					 data + field->offset, field->size);
 		return 0;
 	default:
@@ -3414,7 +3413,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data,
 	}
 }
 
-static int get_common_info(struct tep_handle *pevent,
+static int get_common_info(struct tep_handle *tep,
 			   const char *type, int *offset, int *size)
 {
 	struct tep_event *event;
@@ -3424,12 +3423,12 @@ static int get_common_info(struct tep_handle *pevent,
 	 * All events should have the same common elements.
 	 * Pick any event to find where the type is;
 	 */
-	if (!pevent->events) {
+	if (!tep->events) {
 		do_warning("no event_list!");
 		return -1;
 	}
 
-	event = pevent->events[0];
+	event = tep->events[0];
 	field = tep_find_common_field(event, type);
 	if (!field)
 		return -1;
@@ -3440,58 +3439,58 @@ static int get_common_info(struct tep_handle *pevent,
 	return 0;
 }
 
-static int __parse_common(struct tep_handle *pevent, void *data,
+static int __parse_common(struct tep_handle *tep, void *data,
 			  int *size, int *offset, const char *name)
 {
 	int ret;
 
 	if (!*size) {
-		ret = get_common_info(pevent, name, offset, size);
+		ret = get_common_info(tep, name, offset, size);
 		if (ret < 0)
 			return ret;
 	}
-	return tep_read_number(pevent, data + *offset, *size);
+	return tep_read_number(tep, data + *offset, *size);
 }
 
-static int trace_parse_common_type(struct tep_handle *pevent, void *data)
+static int trace_parse_common_type(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->type_size, &pevent->type_offset,
+	return __parse_common(tep, data,
+			      &tep->type_size, &tep->type_offset,
 			      "common_type");
 }
 
-static int parse_common_pid(struct tep_handle *pevent, void *data)
+static int parse_common_pid(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->pid_size, &pevent->pid_offset,
+	return __parse_common(tep, data,
+			      &tep->pid_size, &tep->pid_offset,
 			      "common_pid");
 }
 
-static int parse_common_pc(struct tep_handle *pevent, void *data)
+static int parse_common_pc(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->pc_size, &pevent->pc_offset,
+	return __parse_common(tep, data,
+			      &tep->pc_size, &tep->pc_offset,
 			      "common_preempt_count");
 }
 
-static int parse_common_flags(struct tep_handle *pevent, void *data)
+static int parse_common_flags(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->flags_size, &pevent->flags_offset,
+	return __parse_common(tep, data,
+			      &tep->flags_size, &tep->flags_offset,
 			      "common_flags");
 }
 
-static int parse_common_lock_depth(struct tep_handle *pevent, void *data)
+static int parse_common_lock_depth(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->ld_size, &pevent->ld_offset,
+	return __parse_common(tep, data,
+			      &tep->ld_size, &tep->ld_offset,
 			      "common_lock_depth");
 }
 
-static int parse_common_migrate_disable(struct tep_handle *pevent, void *data)
+static int parse_common_migrate_disable(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->ld_size, &pevent->ld_offset,
+	return __parse_common(tep, data,
+			      &tep->ld_size, &tep->ld_offset,
 			      "common_migrate_disable");
 }
 
@@ -3499,28 +3498,28 @@ static int events_id_cmp(const void *a, const void *b);
 
 /**
  * tep_find_event - find an event by given id
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @id: the id of the event
  *
  * Returns an event that has a given @id.
  */
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event *tep_find_event(struct tep_handle *tep, int id)
 {
 	struct tep_event **eventptr;
 	struct tep_event key;
 	struct tep_event *pkey = &key;
 
 	/* Check cache first */
-	if (pevent->last_event && pevent->last_event->id == id)
-		return pevent->last_event;
+	if (tep->last_event && tep->last_event->id == id)
+		return tep->last_event;
 
 	key.id = id;
 
-	eventptr = bsearch(&pkey, pevent->events, pevent->nr_events,
-			   sizeof(*pevent->events), events_id_cmp);
+	eventptr = bsearch(&pkey, tep->events, tep->nr_events,
+			   sizeof(*tep->events), events_id_cmp);
 
 	if (eventptr) {
-		pevent->last_event = *eventptr;
+		tep->last_event = *eventptr;
 		return *eventptr;
 	}
 
@@ -3529,7 +3528,7 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
 
 /**
  * tep_find_event_by_name - find an event by given name
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @sys: the system name to search for
  * @name: the name of the event to search for
  *
@@ -3537,19 +3536,19 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
  * @sys. If @sys is NULL the first event with @name is returned.
  */
 struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent,
+tep_find_event_by_name(struct tep_handle *tep,
 		       const char *sys, const char *name)
 {
 	struct tep_event *event = NULL;
 	int i;
 
-	if (pevent->last_event &&
-	    strcmp(pevent->last_event->name, name) == 0 &&
-	    (!sys || strcmp(pevent->last_event->system, sys) == 0))
-		return pevent->last_event;
+	if (tep->last_event &&
+	    strcmp(tep->last_event->name, name) == 0 &&
+	    (!sys || strcmp(tep->last_event->system, sys) == 0))
+		return tep->last_event;
 
-	for (i = 0; i < pevent->nr_events; i++) {
-		event = pevent->events[i];
+	for (i = 0; i < tep->nr_events; i++) {
+		event = tep->events[i];
 		if (strcmp(event->name, name) == 0) {
 			if (!sys)
 				break;
@@ -3557,17 +3556,17 @@ tep_find_event_by_name(struct tep_handle *pevent,
 				break;
 		}
 	}
-	if (i == pevent->nr_events)
+	if (i == tep->nr_events)
 		event = NULL;
 
-	pevent->last_event = event;
+	tep->last_event = event;
 	return event;
 }
 
 static unsigned long long
 eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long val = 0;
 	unsigned long long left, right;
 	struct tep_print_arg *typearg = NULL;
@@ -3589,7 +3588,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 			
 		}
 		/* must be a number */
-		val = tep_read_number(pevent, data + arg->field.field->offset,
+		val = tep_read_number(tep, data + arg->field.field->offset,
 				      arg->field.field->size);
 		break;
 	case TEP_PRINT_FLAGS:
@@ -3629,11 +3628,11 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 			}
 
 			/* Default to long size */
-			field_size = pevent->long_size;
+			field_size = tep->long_size;
 
 			switch (larg->type) {
 			case TEP_PRINT_DYNAMIC_ARRAY:
-				offset = tep_read_number(pevent,
+				offset = tep_read_number(tep,
 						   data + larg->dynarray.field->offset,
 						   larg->dynarray.field->size);
 				if (larg->dynarray.field->elementsize)
@@ -3662,7 +3661,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 			default:
 				goto default_op; /* oops, all bets off */
 			}
-			val = tep_read_number(pevent,
+			val = tep_read_number(tep,
 					      data + offset, field_size);
 			if (typearg)
 				val = eval_type(val, typearg, 1);
@@ -3763,7 +3762,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 		}
 		break;
 	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
-		offset = tep_read_number(pevent,
+		offset = tep_read_number(tep,
 					 data + arg->dynarray.field->offset,
 					 arg->dynarray.field->size);
 		/*
@@ -3775,7 +3774,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 		break;
 	case TEP_PRINT_DYNAMIC_ARRAY:
 		/* Without [], we pass the address to the dynamic data */
-		offset = tep_read_number(pevent,
+		offset = tep_read_number(tep,
 					 data + arg->dynarray.field->offset,
 					 arg->dynarray.field->size);
 		/*
@@ -3850,7 +3849,7 @@ static void print_str_to_seq(struct trace_seq *s, const char *format,
 		trace_seq_printf(s, format, str);
 }
 
-static void print_bitmask_to_seq(struct tep_handle *pevent,
+static void print_bitmask_to_seq(struct tep_handle *tep,
 				 struct trace_seq *s, const char *format,
 				 int len_arg, const void *data, int size)
 {
@@ -3882,7 +3881,7 @@ static void print_bitmask_to_seq(struct tep_handle *pevent,
 		 * In the kernel, this is an array of long words, thus
 		 * endianness is very important.
 		 */
-		if (pevent->file_bigendian)
+		if (tep->file_bigendian)
 			index = size - (len + 1);
 		else
 			index = len;
@@ -3908,7 +3907,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			  struct tep_event *event, const char *format,
 			  int len_arg, struct tep_print_arg *arg)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	struct tep_print_flag_sym *flag;
 	struct tep_format_field *field;
 	struct printk_map *printk;
@@ -3945,7 +3944,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 * is a pointer.
 		 */
 		if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
-		    field->size == pevent->long_size) {
+		    field->size == tep->long_size) {
 
 			/* Handle heterogeneous recording and processing
 			 * architectures
@@ -3960,12 +3959,12 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			 * on 32-bit devices:
 			 * In this case, 64 bits must be read.
 			 */
-			addr = (pevent->long_size == 8) ?
+			addr = (tep->long_size == 8) ?
 				*(unsigned long long *)(data + field->offset) :
 				(unsigned long long)*(unsigned int *)(data + field->offset);
 
 			/* Check if it matches a print format */
-			printk = find_printk(pevent, addr);
+			printk = find_printk(tep, addr);
 			if (printk)
 				trace_seq_puts(s, printk->printk);
 			else
@@ -4022,7 +4021,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	case TEP_PRINT_HEX_STR:
 		if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
-			offset = tep_read_number(pevent,
+			offset = tep_read_number(tep,
 				data + arg->hex.field->dynarray.field->offset,
 				arg->hex.field->dynarray.field->size);
 			hex = data + (offset & 0xffff);
@@ -4053,7 +4052,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			unsigned long offset;
 			struct tep_format_field *field =
 				arg->int_array.field->dynarray.field;
-			offset = tep_read_number(pevent,
+			offset = tep_read_number(tep,
 						 data + field->offset,
 						 field->size);
 			num = data + (offset & 0xffff);
@@ -4104,7 +4103,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			f = tep_find_any_field(event, arg->string.string);
 			arg->string.offset = f->offset;
 		}
-		str_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->string.offset));
+		str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset));
 		str_offset &= 0xffff;
 		print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
 		break;
@@ -4122,10 +4121,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			f = tep_find_any_field(event, arg->bitmask.bitmask);
 			arg->bitmask.offset = f->offset;
 		}
-		bitmask_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->bitmask.offset));
+		bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset));
 		bitmask_size = bitmask_offset >> 16;
 		bitmask_offset &= 0xffff;
-		print_bitmask_to_seq(pevent, s, format, len_arg,
+		print_bitmask_to_seq(tep, s, format, len_arg,
 				     data + bitmask_offset, bitmask_size);
 		break;
 	}
@@ -4257,7 +4256,7 @@ static void free_args(struct tep_print_arg *args)
 
 static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	struct tep_format_field *field, *ip_field;
 	struct tep_print_arg *args, *arg, **next;
 	unsigned long long ip, val;
@@ -4265,8 +4264,8 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 	void *bptr;
 	int vsize = 0;
 
-	field = pevent->bprint_buf_field;
-	ip_field = pevent->bprint_ip_field;
+	field = tep->bprint_buf_field;
+	ip_field = tep->bprint_ip_field;
 
 	if (!field) {
 		field = tep_find_field(event, "buf");
@@ -4279,11 +4278,11 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 			do_warning_event(event, "can't find ip field for binary printk");
 			return NULL;
 		}
-		pevent->bprint_buf_field = field;
-		pevent->bprint_ip_field = ip_field;
+		tep->bprint_buf_field = field;
+		tep->bprint_ip_field = ip_field;
 	}
 
-	ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size);
+	ip = tep_read_number(tep, data + ip_field->offset, ip_field->size);
 
 	/*
 	 * The first arg is the IP pointer.
@@ -4338,6 +4337,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					case 'S':
 					case 'f':
 					case 'F':
+					case 'x':
 						break;
 					default:
 						/*
@@ -4360,7 +4360,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					vsize = 4;
 					break;
 				case 1:
-					vsize = pevent->long_size;
+					vsize = tep->long_size;
 					break;
 				case 2:
 					vsize = 8;
@@ -4377,7 +4377,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 				/* the pointers are always 4 bytes aligned */
 				bptr = (void *)(((unsigned long)bptr + 3) &
 						~3);
-				val = tep_read_number(pevent, bptr, vsize);
+				val = tep_read_number(tep, bptr, vsize);
 				bptr += vsize;
 				arg = alloc_arg();
 				if (!arg) {
@@ -4434,13 +4434,13 @@ static char *
 get_bprint_format(void *data, int size __maybe_unused,
 		  struct tep_event *event)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long addr;
 	struct tep_format_field *field;
 	struct printk_map *printk;
 	char *format;
 
-	field = pevent->bprint_fmt_field;
+	field = tep->bprint_fmt_field;
 
 	if (!field) {
 		field = tep_find_field(event, "fmt");
@@ -4448,12 +4448,12 @@ get_bprint_format(void *data, int size __maybe_unused,
 			do_warning_event(event, "can't find format field for binary printk");
 			return NULL;
 		}
-		pevent->bprint_fmt_field = field;
+		tep->bprint_fmt_field = field;
 	}
 
-	addr = tep_read_number(pevent, data + field->offset, field->size);
+	addr = tep_read_number(tep, data + field->offset, field->size);
 
-	printk = find_printk(pevent, addr);
+	printk = find_printk(tep, addr);
 	if (!printk) {
 		if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
 			return NULL;
@@ -4835,13 +4835,13 @@ void tep_print_field(struct trace_seq *s, void *data,
 {
 	unsigned long long val;
 	unsigned int offset, len, i;
-	struct tep_handle *pevent = field->event->pevent;
+	struct tep_handle *tep = field->event->tep;
 
 	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len = field->size;
 		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
-			val = tep_read_number(pevent, data + offset, len);
+			val = tep_read_number(tep, data + offset, len);
 			offset = val;
 			len = offset >> 16;
 			offset &= 0xffff;
@@ -4861,7 +4861,7 @@ void tep_print_field(struct trace_seq *s, void *data,
 			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
-		val = tep_read_number(pevent, data + field->offset,
+		val = tep_read_number(tep, data + field->offset,
 				      field->size);
 		if (field->flags & TEP_FIELD_IS_POINTER) {
 			trace_seq_printf(s, "0x%llx", val);
@@ -4910,7 +4910,7 @@ void tep_print_fields(struct trace_seq *s, void *data,
 
 static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	struct tep_print_fmt *print_fmt = &event->print_fmt;
 	struct tep_print_arg *arg = print_fmt->args;
 	struct tep_print_arg *args = NULL;
@@ -5002,7 +5002,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 			case '-':
 				goto cont_process;
 			case 'p':
-				if (pevent->long_size == 4)
+				if (tep->long_size == 4)
 					ls = 1;
 				else
 					ls = 2;
@@ -5063,7 +5063,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 				arg = arg->next;
 
 				if (show_func) {
-					func = find_func(pevent, val);
+					func = find_func(tep, val);
 					if (func) {
 						trace_seq_puts(s, func->func);
 						if (show_func == 'F')
@@ -5073,7 +5073,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 						break;
 					}
 				}
-				if (pevent->long_size == 8 && ls == 1 &&
+				if (tep->long_size == 8 && ls == 1 &&
 				    sizeof(long) != 8) {
 					char *p;
 
@@ -5171,8 +5171,8 @@ out_failed:
 }
 
 /**
- * tep_data_lat_fmt - parse the data for the latency format
- * @pevent: a handle to the pevent
+ * tep_data_latency_format - parse the data for the latency format
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @record: the record to read from
  *
@@ -5180,8 +5180,8 @@ out_failed:
  * need rescheduling, in hard/soft interrupt, preempt count
  * and lock depth) and places it into the trace_seq.
  */
-void tep_data_lat_fmt(struct tep_handle *pevent,
-		      struct trace_seq *s, struct tep_record *record)
+void tep_data_latency_format(struct tep_handle *tep,
+			     struct trace_seq *s, struct tep_record *record)
 {
 	static int check_lock_depth = 1;
 	static int check_migrate_disable = 1;
@@ -5195,13 +5195,13 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
 	int softirq;
 	void *data = record->data;
 
-	lat_flags = parse_common_flags(pevent, data);
-	pc = parse_common_pc(pevent, data);
+	lat_flags = parse_common_flags(tep, data);
+	pc = parse_common_pc(tep, data);
 	/* lock_depth may not always exist */
 	if (lock_depth_exists)
-		lock_depth = parse_common_lock_depth(pevent, data);
+		lock_depth = parse_common_lock_depth(tep, data);
 	else if (check_lock_depth) {
-		lock_depth = parse_common_lock_depth(pevent, data);
+		lock_depth = parse_common_lock_depth(tep, data);
 		if (lock_depth < 0)
 			check_lock_depth = 0;
 		else
@@ -5210,9 +5210,9 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
 
 	/* migrate_disable may not always exist */
 	if (migrate_disable_exists)
-		migrate_disable = parse_common_migrate_disable(pevent, data);
+		migrate_disable = parse_common_migrate_disable(tep, data);
 	else if (check_migrate_disable) {
-		migrate_disable = parse_common_migrate_disable(pevent, data);
+		migrate_disable = parse_common_migrate_disable(tep, data);
 		if (migrate_disable < 0)
 			check_migrate_disable = 0;
 		else
@@ -5255,79 +5255,79 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
 
 /**
  * tep_data_type - parse out the given event type
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to read from
  *
  * This returns the event id from the @rec.
  */
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec)
 {
-	return trace_parse_common_type(pevent, rec->data);
+	return trace_parse_common_type(tep, rec->data);
 }
 
 /**
  * tep_data_pid - parse the PID from record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to parse
  *
  * This returns the PID from a record.
  */
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec)
 {
-	return parse_common_pid(pevent, rec->data);
+	return parse_common_pid(tep, rec->data);
 }
 
 /**
  * tep_data_preempt_count - parse the preempt count from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to parse
  *
  * This returns the preempt count from a record.
  */
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec)
 {
-	return parse_common_pc(pevent, rec->data);
+	return parse_common_pc(tep, rec->data);
 }
 
 /**
  * tep_data_flags - parse the latency flags from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to parse
  *
  * This returns the latency flags from a record.
  *
  *  Use trace_flag_type enum for the flags (see event-parse.h).
  */
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec)
 {
-	return parse_common_flags(pevent, rec->data);
+	return parse_common_flags(tep, rec->data);
 }
 
 /**
  * tep_data_comm_from_pid - return the command line from PID
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @pid: the PID of the task to search for
  *
  * This returns a pointer to the command line that has the given
  * @pid.
  */
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid)
 {
 	const char *comm;
 
-	comm = find_cmdline(pevent, pid);
+	comm = find_cmdline(tep, pid);
 	return comm;
 }
 
 static struct tep_cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
+pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)next;
 
 	if (cmdlist)
 		cmdlist = cmdlist->next;
 	else
-		cmdlist = pevent->cmdlist;
+		cmdlist = tep->cmdlist;
 
 	while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
 		cmdlist = cmdlist->next;
@@ -5337,7 +5337,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline
 
 /**
  * tep_data_pid_from_comm - return the pid from a given comm
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @comm: the cmdline to find the pid from
  * @next: the cmdline structure to find the next comm
  *
@@ -5348,7 +5348,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline
  * next pid.
  * Also, it does a linear search, so it may be slow.
  */
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
 					   struct tep_cmdline *next)
 {
 	struct tep_cmdline *cmdline;
@@ -5357,25 +5357,25 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char
 	 * If the cmdlines have not been converted yet, then use
 	 * the list.
 	 */
-	if (!pevent->cmdlines)
-		return pid_from_cmdlist(pevent, comm, next);
+	if (!tep->cmdlines)
+		return pid_from_cmdlist(tep, comm, next);
 
 	if (next) {
 		/*
 		 * The next pointer could have been still from
 		 * a previous call before cmdlines were created
 		 */
-		if (next < pevent->cmdlines ||
-		    next >= pevent->cmdlines + pevent->cmdline_count)
+		if (next < tep->cmdlines ||
+		    next >= tep->cmdlines + tep->cmdline_count)
 			next = NULL;
 		else
 			cmdline  = next++;
 	}
 
 	if (!next)
-		cmdline = pevent->cmdlines;
+		cmdline = tep->cmdlines;
 
-	while (cmdline < pevent->cmdlines + pevent->cmdline_count) {
+	while (cmdline < tep->cmdlines + tep->cmdline_count) {
 		if (strcmp(cmdline->comm, comm) == 0)
 			return cmdline;
 		cmdline++;
@@ -5385,12 +5385,13 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char
 
 /**
  * tep_cmdline_pid - return the pid associated to a given cmdline
+ * @tep: a handle to the trace event parser context
  * @cmdline: The cmdline structure to get the pid from
  *
  * Returns the pid for a give cmdline. If @cmdline is NULL, then
  * -1 is returned.
  */
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
 
@@ -5401,9 +5402,9 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
 	 * If cmdlines have not been created yet, or cmdline is
 	 * not part of the array, then treat it as a cmdlist instead.
 	 */
-	if (!pevent->cmdlines ||
-	    cmdline < pevent->cmdlines ||
-	    cmdline >= pevent->cmdlines + pevent->cmdline_count)
+	if (!tep->cmdlines ||
+	    cmdline < tep->cmdlines ||
+	    cmdline >= tep->cmdlines + tep->cmdline_count)
 		return cmdlist->pid;
 
 	return cmdline->pid;
@@ -5423,7 +5424,7 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event,
 {
 	int print_pretty = 1;
 
-	if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
+	if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
 		tep_print_fields(s, record->data, record->size, event);
 	else {
 
@@ -5444,7 +5445,8 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
 		return true;
 
 	if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
-	    || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf"))
+	    || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")
+	    || !strncmp(trace_clock, "mono", 4))
 		return true;
 
 	/* trace_clock is setting in tsc or counter mode */
@@ -5453,14 +5455,14 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
 
 /**
  * tep_find_event_by_record - return the event from a given record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @record: The record to get the event from
  *
  * Returns the associated event for a given record, or NULL if non is
  * is found.
  */
 struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record)
 {
 	int type;
 
@@ -5469,21 +5471,21 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
 		return NULL;
 	}
 
-	type = trace_parse_common_type(pevent, record->data);
+	type = trace_parse_common_type(tep, record->data);
 
-	return tep_find_event(pevent, type);
+	return tep_find_event(tep, type);
 }
 
 /**
  * tep_print_event_task - Write the event task comm, pid and CPU
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @event: the handle to the record's event
  * @record: The record to get the event from
  *
  * Writes the tasks comm, pid and CPU to @s.
  */
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record)
 {
@@ -5491,27 +5493,26 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
 	const char *comm;
 	int pid;
 
-	pid = parse_common_pid(pevent, data);
-	comm = find_cmdline(pevent, pid);
+	pid = parse_common_pid(tep, data);
+	comm = find_cmdline(tep, pid);
 
-	if (pevent->latency_format) {
-		trace_seq_printf(s, "%8.8s-%-5d %3d",
-		       comm, pid, record->cpu);
-	} else
+	if (tep->latency_format)
+		trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu);
+	else
 		trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
 }
 
 /**
  * tep_print_event_time - Write the event timestamp
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @event: the handle to the record's event
  * @record: The record to get the event from
- * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ * @use_trace_clock: Set to parse according to the @tep->trace_clock
  *
  * Writes the timestamp of the record into @s.
  */
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record,
 			  bool use_trace_clock)
@@ -5522,19 +5523,18 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
 	int p;
 	bool use_usec_format;
 
-	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
-							use_trace_clock);
+	use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock);
 	if (use_usec_format) {
 		secs = record->ts / NSEC_PER_SEC;
 		nsecs = record->ts - secs * NSEC_PER_SEC;
 	}
 
-	if (pevent->latency_format) {
-		tep_data_lat_fmt(pevent, s, record);
+	if (tep->latency_format) {
+		tep_data_latency_format(tep, s, record);
 	}
 
 	if (use_usec_format) {
-		if (pevent->flags & TEP_NSEC_OUTPUT) {
+		if (tep->flags & TEP_NSEC_OUTPUT) {
 			usecs = nsecs;
 			p = 9;
 		} else {
@@ -5554,14 +5554,14 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
 
 /**
  * tep_print_event_data - Write the event data section
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @event: the handle to the record's event
  * @record: The record to get the event from
  *
  * Writes the parsing of the record's data to @s.
  */
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record)
 {
@@ -5578,15 +5578,15 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
 	tep_event_info(s, event, record);
 }
 
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock)
 {
 	struct tep_event *event;
 
-	event = tep_find_event_by_record(pevent, record);
+	event = tep_find_event_by_record(tep, record);
 	if (!event) {
 		int i;
-		int type = trace_parse_common_type(pevent, record->data);
+		int type = trace_parse_common_type(tep, record->data);
 
 		do_warning("ug! no event found for type %d", type);
 		trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
@@ -5596,9 +5596,9 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 		return;
 	}
 
-	tep_print_event_task(pevent, s, event, record);
-	tep_print_event_time(pevent, s, event, record, use_trace_clock);
-	tep_print_event_data(pevent, s, event, record);
+	tep_print_event_task(tep, s, event, record);
+	tep_print_event_time(tep, s, event, record, use_trace_clock);
+	tep_print_event_data(tep, s, event, record);
 }
 
 static int events_id_cmp(const void *a, const void *b)
@@ -5649,32 +5649,26 @@ static int events_system_cmp(const void *a, const void *b)
 	return events_id_cmp(a, b);
 }
 
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type)
+static struct tep_event **list_events_copy(struct tep_handle *tep)
 {
 	struct tep_event **events;
-	int (*sort)(const void *a, const void *b);
-
-	events = pevent->sort_events;
-
-	if (events && pevent->last_type == sort_type)
-		return events;
 
-	if (!events) {
-		events = malloc(sizeof(*events) * (pevent->nr_events + 1));
-		if (!events)
-			return NULL;
+	if (!tep)
+		return NULL;
 
-		memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events);
-		events[pevent->nr_events] = NULL;
+	events = malloc(sizeof(*events) * (tep->nr_events + 1));
+	if (!events)
+		return NULL;
 
-		pevent->sort_events = events;
+	memcpy(events, tep->events, sizeof(*events) * tep->nr_events);
+	events[tep->nr_events] = NULL;
+	return events;
+}
 
-		/* the internal events are sorted by id */
-		if (sort_type == TEP_EVENT_SORT_ID) {
-			pevent->last_type = sort_type;
-			return events;
-		}
-	}
+static void list_events_sort(struct tep_event **events, int nr_events,
+			     enum tep_event_sort_type sort_type)
+{
+	int (*sort)(const void *a, const void *b);
 
 	switch (sort_type) {
 	case TEP_EVENT_SORT_ID:
@@ -5687,11 +5681,82 @@ struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sor
 		sort = events_system_cmp;
 		break;
 	default:
+		sort = NULL;
+	}
+
+	if (sort)
+		qsort(events, nr_events, sizeof(*events), sort);
+}
+
+/**
+ * tep_list_events - Get events, sorted by given criteria.
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * memory must not be freed, it is managed by the library.
+ * The function is not thread safe.
+ */
+struct tep_event **tep_list_events(struct tep_handle *tep,
+				   enum tep_event_sort_type sort_type)
+{
+	struct tep_event **events;
+
+	if (!tep)
+		return NULL;
+
+	events = tep->sort_events;
+	if (events && tep->last_type == sort_type)
 		return events;
+
+	if (!events) {
+		events = list_events_copy(tep);
+		if (!events)
+			return NULL;
+
+		tep->sort_events = events;
+
+		/* the internal events are sorted by id */
+		if (sort_type == TEP_EVENT_SORT_ID) {
+			tep->last_type = sort_type;
+			return events;
+		}
 	}
 
-	qsort(events, pevent->nr_events, sizeof(*events), sort);
-	pevent->last_type = sort_type;
+	list_events_sort(events, tep->nr_events, sort_type);
+	tep->last_type = sort_type;
+
+	return events;
+}
+
+
+/**
+ * tep_list_events_copy - Thread safe version of tep_list_events()
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * array is newly allocated inside the function and must be freed by the caller
+ */
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+					enum tep_event_sort_type sort_type)
+{
+	struct tep_event **events;
+
+	if (!tep)
+		return NULL;
+
+	events = list_events_copy(tep);
+	if (!events)
+		return NULL;
+
+	/* the internal events are sorted by id */
+	if (sort_type == TEP_EVENT_SORT_ID)
+		return events;
+
+	list_events_sort(events, tep->nr_events, sort_type);
 
 	return events;
 }
@@ -5950,7 +6015,7 @@ static void parse_header_field(const char *field,
 
 /**
  * tep_parse_header_page - parse the data stored in the header page
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @buf: the buffer storing the header page format string
  * @size: the size of @buf
  * @long_size: the long size to use if there is no header
@@ -5960,7 +6025,7 @@ static void parse_header_field(const char *field,
  *
  * /sys/kernel/debug/tracing/events/header_page
  */
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
 			  int long_size)
 {
 	int ignore;
@@ -5970,22 +6035,22 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
 		 * Old kernels did not have header page info.
 		 * Sorry but we just use what we find here in user space.
 		 */
-		pevent->header_page_ts_size = sizeof(long long);
-		pevent->header_page_size_size = long_size;
-		pevent->header_page_data_offset = sizeof(long long) + long_size;
-		pevent->old_format = 1;
+		tep->header_page_ts_size = sizeof(long long);
+		tep->header_page_size_size = long_size;
+		tep->header_page_data_offset = sizeof(long long) + long_size;
+		tep->old_format = 1;
 		return -1;
 	}
 	init_input_buf(buf, size);
 
-	parse_header_field("timestamp", &pevent->header_page_ts_offset,
-			   &pevent->header_page_ts_size, 1);
-	parse_header_field("commit", &pevent->header_page_size_offset,
-			   &pevent->header_page_size_size, 1);
-	parse_header_field("overwrite", &pevent->header_page_overwrite,
+	parse_header_field("timestamp", &tep->header_page_ts_offset,
+			   &tep->header_page_ts_size, 1);
+	parse_header_field("commit", &tep->header_page_size_offset,
+			   &tep->header_page_size_size, 1);
+	parse_header_field("overwrite", &tep->header_page_overwrite,
 			   &ignore, 0);
-	parse_header_field("data", &pevent->header_page_data_offset,
-			   &pevent->header_page_data_size, 1);
+	parse_header_field("data", &tep->header_page_data_offset,
+			   &tep->header_page_data_size, 1);
 
 	return 0;
 }
@@ -6013,11 +6078,11 @@ static void free_handler(struct event_handler *handle)
 	free(handle);
 }
 
-static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
+static int find_event_handle(struct tep_handle *tep, struct tep_event *event)
 {
 	struct event_handler *handle, **next;
 
-	for (next = &pevent->handlers; *next;
+	for (next = &tep->handlers; *next;
 	     next = &(*next)->next) {
 		handle = *next;
 		if (event_matches(event, handle->id,
@@ -6055,7 +6120,7 @@ static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
  * /sys/kernel/debug/tracing/events/.../.../format
  */
 enum tep_errno __tep_parse_format(struct tep_event **eventp,
-				  struct tep_handle *pevent, const char *buf,
+				  struct tep_handle *tep, const char *buf,
 				  unsigned long size, const char *sys)
 {
 	struct tep_event *event;
@@ -6097,8 +6162,8 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
 		goto event_alloc_failed;
 	}
 
-	/* Add pevent to event so that it can be referenced */
-	event->pevent = pevent;
+	/* Add tep to event so that it can be referenced */
+	event->tep = tep;
 
 	ret = event_read_format(event);
 	if (ret < 0) {
@@ -6110,7 +6175,7 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
 	 * If the event has an override, don't print warnings if the event
 	 * print format fails to parse.
 	 */
-	if (pevent && find_event_handle(pevent, event))
+	if (tep && find_event_handle(tep, event))
 		show_warning = 0;
 
 	ret = event_read_print(event);
@@ -6162,18 +6227,18 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
 }
 
 static enum tep_errno
-__parse_event(struct tep_handle *pevent,
+__parse_event(struct tep_handle *tep,
 	      struct tep_event **eventp,
 	      const char *buf, unsigned long size,
 	      const char *sys)
 {
-	int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
+	int ret = __tep_parse_format(eventp, tep, buf, size, sys);
 	struct tep_event *event = *eventp;
 
 	if (event == NULL)
 		return ret;
 
-	if (pevent && add_event(pevent, event)) {
+	if (tep && add_event(tep, event)) {
 		ret = TEP_ERRNO__MEM_ALLOC_FAILED;
 		goto event_add_failed;
 	}
@@ -6191,7 +6256,7 @@ event_add_failed:
 
 /**
  * tep_parse_format - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @eventp: returned format
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
@@ -6204,17 +6269,17 @@ event_add_failed:
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
 				struct tep_event **eventp,
 				const char *buf,
 				unsigned long size, const char *sys)
 {
-	return __parse_event(pevent, eventp, buf, size, sys);
+	return __parse_event(tep, eventp, buf, size, sys);
 }
 
 /**
  * tep_parse_event - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
  * @sys: the system the event belongs to
@@ -6226,11 +6291,11 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent,
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
 			       unsigned long size, const char *sys)
 {
 	struct tep_event *event = NULL;
-	return __parse_event(pevent, &event, buf, size, sys);
+	return __parse_event(tep, &event, buf, size, sys);
 }
 
 int get_field_val(struct trace_seq *s, struct tep_format_field *field,
@@ -6292,8 +6357,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event,
 
 	offset = field->offset;
 	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
-		offset = tep_read_number(event->pevent,
-					    data + offset, field->size);
+		offset = tep_read_number(event->tep,
+					 data + offset, field->size);
 		*len = offset >> 16;
 		offset &= 0xffff;
 	} else
@@ -6386,7 +6451,8 @@ int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event,
  * @record: The record with the field name.
  * @err: print default error if failed.
  *
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
  */
 int tep_print_num_field(struct trace_seq *s, const char *fmt,
 			struct tep_event *event, const char *name,
@@ -6418,14 +6484,15 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt,
  * @record: The record with the field name.
  * @err: print default error if failed.
  *
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
  */
 int tep_print_func_field(struct trace_seq *s, const char *fmt,
 			 struct tep_event *event, const char *name,
 			 struct tep_record *record, int err)
 {
 	struct tep_format_field *field = tep_find_field(event, name);
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long val;
 	struct func_map *func;
 	char tmp[128];
@@ -6436,7 +6503,7 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
 	if (tep_read_number_field(field, record->data, &val))
 		goto failed;
 
-	func = find_func(pevent, val);
+	func = find_func(tep, val);
 
 	if (func)
 		snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val);
@@ -6468,7 +6535,7 @@ static void free_func_handle(struct tep_function_handler *func)
 
 /**
  * tep_register_print_function - register a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @func: the function to process the helper function
  * @ret_type: the return type of the helper function
  * @name: the name of the helper function
@@ -6481,7 +6548,7 @@ static void free_func_handle(struct tep_function_handler *func)
  * The @parameters is a variable list of tep_func_arg_type enums that
  * must end with TEP_FUNC_ARG_VOID.
  */
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
 				tep_func_handler func,
 				enum tep_func_arg_type ret_type,
 				char *name, ...)
@@ -6493,7 +6560,7 @@ int tep_register_print_function(struct tep_handle *pevent,
 	va_list ap;
 	int ret;
 
-	func_handle = find_func_handler(pevent, name);
+	func_handle = find_func_handler(tep, name);
 	if (func_handle) {
 		/*
 		 * This is most like caused by the users own
@@ -6501,7 +6568,7 @@ int tep_register_print_function(struct tep_handle *pevent,
 		 * system defaults.
 		 */
 		pr_stat("override of function helper '%s'", name);
-		remove_func_handler(pevent, name);
+		remove_func_handler(tep, name);
 	}
 
 	func_handle = calloc(1, sizeof(*func_handle));
@@ -6548,8 +6615,8 @@ int tep_register_print_function(struct tep_handle *pevent,
 	}
 	va_end(ap);
 
-	func_handle->next = pevent->func_handlers;
-	pevent->func_handlers = func_handle;
+	func_handle->next = tep->func_handlers;
+	tep->func_handlers = func_handle;
 
 	return 0;
  out_free:
@@ -6560,7 +6627,7 @@ int tep_register_print_function(struct tep_handle *pevent,
 
 /**
  * tep_unregister_print_function - unregister a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @func: the function to process the helper function
  * @name: the name of the helper function
  *
@@ -6568,20 +6635,20 @@ int tep_register_print_function(struct tep_handle *pevent,
  *
  * Returns 0 if the handler was removed successully, -1 otherwise.
  */
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
 				  tep_func_handler func, char *name)
 {
 	struct tep_function_handler *func_handle;
 
-	func_handle = find_func_handler(pevent, name);
+	func_handle = find_func_handler(tep, name);
 	if (func_handle && func_handle->func == func) {
-		remove_func_handler(pevent, name);
+		remove_func_handler(tep, name);
 		return 0;
 	}
 	return -1;
 }
 
-static struct tep_event *search_event(struct tep_handle *pevent, int id,
+static struct tep_event *search_event(struct tep_handle *tep, int id,
 				      const char *sys_name,
 				      const char *event_name)
 {
@@ -6589,7 +6656,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
 
 	if (id >= 0) {
 		/* search by id */
-		event = tep_find_event(pevent, id);
+		event = tep_find_event(tep, id);
 		if (!event)
 			return NULL;
 		if (event_name && (strcmp(event_name, event->name) != 0))
@@ -6597,7 +6664,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
 		if (sys_name && (strcmp(sys_name, event->system) != 0))
 			return NULL;
 	} else {
-		event = tep_find_event_by_name(pevent, sys_name, event_name);
+		event = tep_find_event_by_name(tep, sys_name, event_name);
 		if (!event)
 			return NULL;
 	}
@@ -6606,7 +6673,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
 
 /**
  * tep_register_event_handler - register a way to parse an event
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @id: the id of the event to register
  * @sys_name: the system name the event belongs to
  * @event_name: the name of the event
@@ -6627,14 +6694,14 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
  *  negative TEP_ERRNO_... in case of an error
  *
  */
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context)
 {
 	struct tep_event *event;
 	struct event_handler *handle;
 
-	event = search_event(pevent, id, sys_name, event_name);
+	event = search_event(tep, id, sys_name, event_name);
 	if (event == NULL)
 		goto not_found;
 
@@ -6669,8 +6736,8 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 	}
 
 	handle->func = func;
-	handle->next = pevent->handlers;
-	pevent->handlers = handle;
+	handle->next = tep->handlers;
+	tep->handlers = handle;
 	handle->context = context;
 
 	return TEP_REGISTER_SUCCESS;
@@ -6697,7 +6764,7 @@ static int handle_matches(struct event_handler *handler, int id,
 
 /**
  * tep_unregister_event_handler - unregister an existing event handler
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @id: the id of the event to unregister
  * @sys_name: the system name the handler belongs to
  * @event_name: the name of the event handler
@@ -6711,7 +6778,7 @@ static int handle_matches(struct event_handler *handler, int id,
  *
  * Returns 0 if handler was removed successfully, -1 if event was not found.
  */
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
 				 const char *sys_name, const char *event_name,
 				 tep_event_handler_func func, void *context)
 {
@@ -6719,7 +6786,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
 	struct event_handler *handle;
 	struct event_handler **next;
 
-	event = search_event(pevent, id, sys_name, event_name);
+	event = search_event(tep, id, sys_name, event_name);
 	if (event == NULL)
 		goto not_found;
 
@@ -6733,7 +6800,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
 	}
 
 not_found:
-	for (next = &pevent->handlers; *next; next = &(*next)->next) {
+	for (next = &tep->handlers; *next; next = &(*next)->next) {
 		handle = *next;
 		if (handle_matches(handle, id, sys_name, event_name,
 				   func, context))
@@ -6750,23 +6817,23 @@ not_found:
 }
 
 /**
- * tep_alloc - create a pevent handle
+ * tep_alloc - create a tep handle
  */
 struct tep_handle *tep_alloc(void)
 {
-	struct tep_handle *pevent = calloc(1, sizeof(*pevent));
+	struct tep_handle *tep = calloc(1, sizeof(*tep));
 
-	if (pevent) {
-		pevent->ref_count = 1;
-		pevent->host_bigendian = tep_host_bigendian();
+	if (tep) {
+		tep->ref_count = 1;
+		tep->host_bigendian = tep_is_bigendian();
 	}
 
-	return pevent;
+	return tep;
 }
 
-void tep_ref(struct tep_handle *pevent)
+void tep_ref(struct tep_handle *tep)
 {
-	pevent->ref_count++;
+	tep->ref_count++;
 }
 
 int tep_get_ref(struct tep_handle *tep)
@@ -6816,10 +6883,10 @@ void tep_free_event(struct tep_event *event)
 }
 
 /**
- * tep_free - free a pevent handle
- * @pevent: the pevent handle to free
+ * tep_free - free a tep handle
+ * @tep: the tep handle to free
  */
-void tep_free(struct tep_handle *pevent)
+void tep_free(struct tep_handle *tep)
 {
 	struct cmdline_list *cmdlist, *cmdnext;
 	struct func_list *funclist, *funcnext;
@@ -6828,21 +6895,21 @@ void tep_free(struct tep_handle *pevent)
 	struct event_handler *handle;
 	int i;
 
-	if (!pevent)
+	if (!tep)
 		return;
 
-	cmdlist = pevent->cmdlist;
-	funclist = pevent->funclist;
-	printklist = pevent->printklist;
+	cmdlist = tep->cmdlist;
+	funclist = tep->funclist;
+	printklist = tep->printklist;
 
-	pevent->ref_count--;
-	if (pevent->ref_count)
+	tep->ref_count--;
+	if (tep->ref_count)
 		return;
 
-	if (pevent->cmdlines) {
-		for (i = 0; i < pevent->cmdline_count; i++)
-			free(pevent->cmdlines[i].comm);
-		free(pevent->cmdlines);
+	if (tep->cmdlines) {
+		for (i = 0; i < tep->cmdline_count; i++)
+			free(tep->cmdlines[i].comm);
+		free(tep->cmdlines);
 	}
 
 	while (cmdlist) {
@@ -6852,12 +6919,12 @@ void tep_free(struct tep_handle *pevent)
 		cmdlist = cmdnext;
 	}
 
-	if (pevent->func_map) {
-		for (i = 0; i < (int)pevent->func_count; i++) {
-			free(pevent->func_map[i].func);
-			free(pevent->func_map[i].mod);
+	if (tep->func_map) {
+		for (i = 0; i < (int)tep->func_count; i++) {
+			free(tep->func_map[i].func);
+			free(tep->func_map[i].mod);
 		}
-		free(pevent->func_map);
+		free(tep->func_map);
 	}
 
 	while (funclist) {
@@ -6868,16 +6935,16 @@ void tep_free(struct tep_handle *pevent)
 		funclist = funcnext;
 	}
 
-	while (pevent->func_handlers) {
-		func_handler = pevent->func_handlers;
-		pevent->func_handlers = func_handler->next;
+	while (tep->func_handlers) {
+		func_handler = tep->func_handlers;
+		tep->func_handlers = func_handler->next;
 		free_func_handle(func_handler);
 	}
 
-	if (pevent->printk_map) {
-		for (i = 0; i < (int)pevent->printk_count; i++)
-			free(pevent->printk_map[i].printk);
-		free(pevent->printk_map);
+	if (tep->printk_map) {
+		for (i = 0; i < (int)tep->printk_count; i++)
+			free(tep->printk_map[i].printk);
+		free(tep->printk_map);
 	}
 
 	while (printklist) {
@@ -6887,24 +6954,24 @@ void tep_free(struct tep_handle *pevent)
 		printklist = printknext;
 	}
 
-	for (i = 0; i < pevent->nr_events; i++)
-		tep_free_event(pevent->events[i]);
+	for (i = 0; i < tep->nr_events; i++)
+		tep_free_event(tep->events[i]);
 
-	while (pevent->handlers) {
-		handle = pevent->handlers;
-		pevent->handlers = handle->next;
+	while (tep->handlers) {
+		handle = tep->handlers;
+		tep->handlers = handle->next;
 		free_handler(handle);
 	}
 
-	free(pevent->trace_clock);
-	free(pevent->events);
-	free(pevent->sort_events);
-	free(pevent->func_resolver);
+	free(tep->trace_clock);
+	free(tep->events);
+	free(tep->sort_events);
+	free(tep->func_resolver);
 
-	free(pevent);
+	free(tep);
 }
 
-void tep_unref(struct tep_handle *pevent)
+void tep_unref(struct tep_handle *tep)
 {
-	tep_free(pevent);
+	tep_free(tep);
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index aec48f2aea8a..642f68ab5fb2 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -64,8 +64,8 @@ typedef int (*tep_event_handler_func)(struct trace_seq *s,
 				      struct tep_event *event,
 				      void *context);
 
-typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
-typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent);
+typedef int (*tep_plugin_load_func)(struct tep_handle *tep);
+typedef int (*tep_plugin_unload_func)(struct tep_handle *tep);
 
 struct tep_plugin_option {
 	struct tep_plugin_option	*next;
@@ -85,12 +85,12 @@ struct tep_plugin_option {
  * TEP_PLUGIN_LOADER:  (required)
  *   The function name to initialized the plugin.
  *
- *   int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+ *   int TEP_PLUGIN_LOADER(struct tep_handle *tep)
  *
  * TEP_PLUGIN_UNLOADER:  (optional)
  *   The function called just before unloading
  *
- *   int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+ *   int TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
  *
  * TEP_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
@@ -278,7 +278,7 @@ struct tep_print_fmt {
 };
 
 struct tep_event {
-	struct tep_handle	*pevent;
+	struct tep_handle	*tep;
 	char			*name;
 	int			id;
 	int			flags;
@@ -393,9 +393,9 @@ struct tep_plugin_list;
 
 #define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
 
-struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent);
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep);
 void tep_unload_plugins(struct tep_plugin_list *plugin_list,
-			struct tep_handle *pevent);
+			struct tep_handle *tep);
 char **tep_plugin_list_options(void);
 void tep_plugin_free_options_list(char **list);
 int tep_plugin_add_options(const char *name,
@@ -409,8 +409,10 @@ void tep_print_plugins(struct trace_seq *s,
 typedef char *(tep_func_resolver_t)(void *priv,
 				    unsigned long long *addrp, char **modp);
 void tep_set_flag(struct tep_handle *tep, int flag);
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag);
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags);
 
-static inline int tep_host_bigendian(void)
+static inline int tep_is_bigendian(void)
 {
 	unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
 	unsigned int val;
@@ -428,37 +430,37 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x10,
 };
 
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
 			      tep_func_resolver_t *func, void *priv);
-void tep_reset_function_resolver(struct tep_handle *pevent);
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
-int tep_register_function(struct tep_handle *pevent, char *name,
+void tep_reset_function_resolver(struct tep_handle *tep);
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock);
+int tep_register_function(struct tep_handle *tep, char *name,
 			  unsigned long long addr, char *mod);
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
 			      unsigned long long addr);
-int tep_pid_is_registered(struct tep_handle *pevent, int pid);
+bool tep_is_pid_registered(struct tep_handle *tep, int pid);
 
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record);
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record,
 			  bool use_trace_clock);
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record);
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock);
 
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
 			  int long_size);
 
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
 			       unsigned long size, const char *sys);
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
 				struct tep_event **eventp,
 				const char *buf,
 				unsigned long size, const char *sys);
@@ -490,50 +492,50 @@ enum tep_reg_handler {
 	TEP_REGISTER_SUCCESS_OVERWRITE,
 };
 
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context);
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
 				 const char *sys_name, const char *event_name,
 				 tep_event_handler_func func, void *context);
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
 				tep_func_handler func,
 				enum tep_func_arg_type ret_type,
 				char *name, ...);
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
 				  tep_func_handler func, char *name);
 
 struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name);
 struct tep_format_field *tep_find_field(struct tep_event *event, const char *name);
 struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name);
 
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr);
 unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
-unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr);
+unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size);
 int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value);
 
 struct tep_event *tep_get_first_event(struct tep_handle *tep);
 int tep_get_events_count(struct tep_handle *tep);
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event *tep_find_event(struct tep_handle *tep, int id);
 
 struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
+tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name);
 struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
-
-void tep_data_lat_fmt(struct tep_handle *pevent,
-		      struct trace_seq *s, struct tep_record *record);
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record);
+
+void tep_data_latency_format(struct tep_handle *tep,
+			     struct trace_seq *s, struct tep_record *record);
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec);
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid);
 struct tep_cmdline;
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
 					   struct tep_cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
 		     struct tep_format_field *field);
@@ -541,10 +543,12 @@ void tep_print_fields(struct trace_seq *s, void *data,
 		      int size __maybe_unused, struct tep_event *event);
 void tep_event_info(struct trace_seq *s, struct tep_event *event,
 		    struct tep_record *record);
-int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
+int tep_strerror(struct tep_handle *tep, enum tep_errno errnum,
 		 char *buf, size_t buflen);
 
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type);
+struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type);
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+					enum tep_event_sort_type);
 struct tep_format_field **tep_event_common_fields(struct tep_event *event);
 struct tep_format_field **tep_event_fields(struct tep_event *event);
 
@@ -552,24 +556,28 @@ enum tep_endian {
         TEP_LITTLE_ENDIAN = 0,
         TEP_BIG_ENDIAN
 };
-int tep_get_cpus(struct tep_handle *pevent);
-void tep_set_cpus(struct tep_handle *pevent, int cpus);
-int tep_get_long_size(struct tep_handle *pevent);
-void tep_set_long_size(struct tep_handle *pevent, int long_size);
-int tep_get_page_size(struct tep_handle *pevent);
-void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_file_bigendian(struct tep_handle *pevent);
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_host_bigendian(struct tep_handle *pevent);
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_latency_format(struct tep_handle *pevent);
-void tep_set_latency_format(struct tep_handle *pevent, int lat);
-int tep_get_header_page_size(struct tep_handle *pevent);
+int tep_get_cpus(struct tep_handle *tep);
+void tep_set_cpus(struct tep_handle *tep, int cpus);
+int tep_get_long_size(struct tep_handle *tep);
+void tep_set_long_size(struct tep_handle *tep, int long_size);
+int tep_get_page_size(struct tep_handle *tep);
+void tep_set_page_size(struct tep_handle *tep, int _page_size);
+bool tep_is_file_bigendian(struct tep_handle *tep);
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_local_bigendian(struct tep_handle *tep);
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_latency_format(struct tep_handle *tep);
+void tep_set_latency_format(struct tep_handle *tep, int lat);
+int tep_get_header_page_size(struct tep_handle *tep);
+int tep_get_header_timestamp_size(struct tep_handle *tep);
+bool tep_is_old_format(struct tep_handle *tep);
+void tep_set_print_raw(struct tep_handle *tep, int print_raw);
+void tep_set_test_filters(struct tep_handle *tep, int test_filters);
 
 struct tep_handle *tep_alloc(void);
-void tep_free(struct tep_handle *pevent);
-void tep_ref(struct tep_handle *pevent);
-void tep_unref(struct tep_handle *pevent);
+void tep_free(struct tep_handle *tep);
+void tep_ref(struct tep_handle *tep);
+void tep_unref(struct tep_handle *tep);
 int tep_get_ref(struct tep_handle *tep);
 
 /* access to the internal parser */
@@ -581,8 +589,8 @@ const char *tep_get_input_buf(void);
 unsigned long long tep_get_input_buf_ptr(void);
 
 /* for debugging */
-void tep_print_funcs(struct tep_handle *pevent);
-void tep_print_printk(struct tep_handle *pevent);
+void tep_print_funcs(struct tep_handle *tep);
+void tep_print_printk(struct tep_handle *tep);
 
 /* ----------------------- filtering ----------------------- */
 
@@ -709,13 +717,13 @@ struct tep_filter_type {
 #define TEP_FILTER_ERROR_BUFSZ  1024
 
 struct tep_event_filter {
-	struct tep_handle	*pevent;
+	struct tep_handle	*tep;
 	int			filters;
 	struct tep_filter_type	*event_filters;
 	char			error_buffer[TEP_FILTER_ERROR_BUFSZ];
 };
 
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep);
 
 /* for backward compatibility */
 #define FILTER_NONE		TEP_ERRNO__NO_FILTER
@@ -723,12 +731,6 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
 #define FILTER_MISS		TEP_ERRNO__FILTER_MISS
 #define FILTER_MATCH		TEP_ERRNO__FILTER_MATCH
 
-enum tep_filter_trivial_type {
-	TEP_FILTER_TRIVIAL_FALSE,
-	TEP_FILTER_TRIVIAL_TRUE,
-	TEP_FILTER_TRIVIAL_BOTH,
-};
-
 enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str);
 
@@ -743,9 +745,6 @@ int tep_event_filtered(struct tep_event_filter *filter,
 
 void tep_filter_reset(struct tep_event_filter *filter);
 
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
-			     enum tep_filter_trivial_type type);
-
 void tep_filter_free(struct tep_event_filter *filter);
 
 char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
@@ -753,15 +752,8 @@ char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
 int tep_filter_remove_event(struct tep_event_filter *filter,
 			    int event_id);
 
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
-				 int event_id,
-				 enum tep_filter_trivial_type type);
-
 int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
 
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
-			enum tep_filter_trivial_type type);
-
 int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
 
 #endif /* _PARSE_EVENTS_H */
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index e74f16c88398..8ca28de9337a 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -269,7 +269,7 @@ void tep_print_plugins(struct trace_seq *s,
 }
 
 static void
-load_plugin(struct tep_handle *pevent, const char *path,
+load_plugin(struct tep_handle *tep, const char *path,
 	    const char *file, void *data)
 {
 	struct tep_plugin_list **plugin_list = data;
@@ -316,7 +316,7 @@ load_plugin(struct tep_handle *pevent, const char *path,
 	*plugin_list = list;
 
 	pr_stat("registering plugin: %s", plugin);
-	func(pevent);
+	func(tep);
 	return;
 
  out_free:
@@ -324,9 +324,9 @@ load_plugin(struct tep_handle *pevent, const char *path,
 }
 
 static void
-load_plugins_dir(struct tep_handle *pevent, const char *suffix,
+load_plugins_dir(struct tep_handle *tep, const char *suffix,
 		 const char *path,
-		 void (*load_plugin)(struct tep_handle *pevent,
+		 void (*load_plugin)(struct tep_handle *tep,
 				     const char *path,
 				     const char *name,
 				     void *data),
@@ -359,15 +359,15 @@ load_plugins_dir(struct tep_handle *pevent, const char *suffix,
 		if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
 			continue;
 
-		load_plugin(pevent, path, name, data);
+		load_plugin(tep, path, name, data);
 	}
 
 	closedir(dir);
 }
 
 static void
-load_plugins(struct tep_handle *pevent, const char *suffix,
-	     void (*load_plugin)(struct tep_handle *pevent,
+load_plugins(struct tep_handle *tep, const char *suffix,
+	     void (*load_plugin)(struct tep_handle *tep,
 				 const char *path,
 				 const char *name,
 				 void *data),
@@ -378,7 +378,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	char *envdir;
 	int ret;
 
-	if (pevent->flags & TEP_DISABLE_PLUGINS)
+	if (tep->flags & TEP_DISABLE_PLUGINS)
 		return;
 
 	/*
@@ -386,8 +386,8 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	 * check that first.
 	 */
 #ifdef PLUGIN_DIR
-	if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS))
-		load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+	if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS))
+		load_plugins_dir(tep, suffix, PLUGIN_DIR,
 				 load_plugin, data);
 #endif
 
@@ -397,7 +397,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	 */
 	envdir = getenv("TRACEEVENT_PLUGIN_DIR");
 	if (envdir)
-		load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+		load_plugins_dir(tep, suffix, envdir, load_plugin, data);
 
 	/*
 	 * Now let the home directory override the environment
@@ -413,22 +413,22 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 		return;
 	}
 
-	load_plugins_dir(pevent, suffix, path, load_plugin, data);
+	load_plugins_dir(tep, suffix, path, load_plugin, data);
 
 	free(path);
 }
 
 struct tep_plugin_list*
-tep_load_plugins(struct tep_handle *pevent)
+tep_load_plugins(struct tep_handle *tep)
 {
 	struct tep_plugin_list *list = NULL;
 
-	load_plugins(pevent, ".so", load_plugin, &list);
+	load_plugins(tep, ".so", load_plugin, &list);
 	return list;
 }
 
 void
-tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep)
 {
 	tep_plugin_unload_func func;
 	struct tep_plugin_list *list;
@@ -438,7 +438,7 @@ tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *peven
 		plugin_list = list->next;
 		func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME);
 		if (func)
-			func(pevent);
+			func(tep);
 		dlclose(list->handle);
 		free(list->name);
 		free(list);
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index af2a1f3b7424..b887e7437d67 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -727,3 +727,52 @@ int kbuffer_start_of_data(struct kbuffer *kbuf)
 {
 	return kbuf->start;
 }
+
+/**
+ * kbuffer_raw_get - get raw buffer info
+ * @kbuf:	The kbuffer
+ * @subbuf:	Start of mapped subbuffer
+ * @info:	Info descriptor to fill in
+ *
+ * For debugging. This can return internals of the ring buffer.
+ * Expects to have info->next set to what it will read.
+ * The type, length and timestamp delta will be filled in, and
+ * @info->next will be updated to the next element.
+ * The @subbuf is used to know if the info is passed the end of
+ * data and NULL will be returned if it is.
+ */
+struct kbuffer_raw_info *
+kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info)
+{
+	unsigned long long flags;
+	unsigned long long delta;
+	unsigned int type_len;
+	unsigned int size;
+	int start;
+	int length;
+	void *ptr = info->next;
+
+	if (!kbuf || !subbuf)
+		return NULL;
+
+	if (kbuf->flags & KBUFFER_FL_LONG_8)
+		start = 16;
+	else
+		start = 12;
+
+	flags = read_long(kbuf, subbuf + 8);
+	size = (unsigned int)flags & COMMIT_MASK;
+
+	if (ptr < subbuf || ptr >= subbuf + start + size)
+		return NULL;
+
+	type_len = translate_data(kbuf, ptr, &ptr, &delta, &length);
+
+	info->next = ptr + length;
+
+	info->type = type_len;
+	info->delta = delta;
+	info->length = length;
+
+	return info;
+}
diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h
index 03dce757553f..ed4d697fc137 100644
--- a/tools/lib/traceevent/kbuffer.h
+++ b/tools/lib/traceevent/kbuffer.h
@@ -65,4 +65,17 @@ int kbuffer_subbuffer_size(struct kbuffer *kbuf);
 void kbuffer_set_old_format(struct kbuffer *kbuf);
 int kbuffer_start_of_data(struct kbuffer *kbuf);
 
+/* Debugging */
+
+struct kbuffer_raw_info {
+	int			type;
+	int			length;
+	unsigned long long	delta;
+	void			*next;
+};
+
+/* Read raw data */
+struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf,
+					 struct kbuffer_raw_info *info);
+
 #endif /* _K_BUFFER_H */
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index cb5ce66dab6e..552592d153fb 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -154,7 +154,7 @@ add_filter_type(struct tep_event_filter *filter, int id)
 
 	filter_type = &filter->event_filters[i];
 	filter_type->event_id = id;
-	filter_type->event = tep_find_event(filter->pevent, id);
+	filter_type->event = tep_find_event(filter->tep, id);
 	filter_type->filter = NULL;
 
 	filter->filters++;
@@ -164,9 +164,9 @@ add_filter_type(struct tep_event_filter *filter, int id)
 
 /**
  * tep_filter_alloc - create a new event filter
- * @pevent: The pevent that this filter is associated with
+ * @tep: The tep that this filter is associated with
  */
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep)
 {
 	struct tep_event_filter *filter;
 
@@ -175,8 +175,8 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
 		return NULL;
 
 	memset(filter, 0, sizeof(*filter));
-	filter->pevent = pevent;
-	tep_ref(pevent);
+	filter->tep = tep;
+	tep_ref(tep);
 
 	return filter;
 }
@@ -256,7 +256,7 @@ static int event_match(struct tep_event *event,
 }
 
 static enum tep_errno
-find_event(struct tep_handle *pevent, struct event_list **events,
+find_event(struct tep_handle *tep, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
 	struct tep_event *event;
@@ -299,8 +299,8 @@ find_event(struct tep_handle *pevent, struct event_list **events,
 		}
 	}
 
-	for (i = 0; i < pevent->nr_events; i++) {
-		event = pevent->events[i];
+	for (i = 0; i < tep->nr_events; i++) {
+		event = tep->events[i];
 		if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
 			match = 1;
 			if (add_event(events, event) < 0) {
@@ -1257,7 +1257,7 @@ static void filter_init_error_buf(struct tep_event_filter *filter)
 enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str)
 {
-	struct tep_handle *pevent = filter->pevent;
+	struct tep_handle *tep = filter->tep;
 	struct event_list *event;
 	struct event_list *events = NULL;
 	const char *filter_start;
@@ -1313,7 +1313,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 		}
 
 		/* Find this event */
-		ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
+		ret = find_event(tep, &events, strim(sys_name), strim(event_name));
 		if (ret < 0) {
 			free_events(events);
 			free(this_event);
@@ -1334,7 +1334,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 		if (ret < 0)
 			rtn = ret;
 
-		if (ret >= 0 && pevent->test_filters) {
+		if (ret >= 0 && tep->test_filters) {
 			char *test;
 			test = tep_filter_make_string(filter, event->event->id);
 			if (test) {
@@ -1346,9 +1346,6 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 
 	free_events(events);
 
-	if (rtn >= 0 && pevent->test_filters)
-		exit(0);
-
 	return rtn;
 }
 
@@ -1380,7 +1377,7 @@ int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
 		return 0;
 	}
 
-	return tep_strerror(filter->pevent, err, buf, buflen);
+	return tep_strerror(filter->tep, err, buf, buflen);
 }
 
 /**
@@ -1443,7 +1440,7 @@ void tep_filter_reset(struct tep_event_filter *filter)
 
 void tep_filter_free(struct tep_event_filter *filter)
 {
-	tep_unref(filter->pevent);
+	tep_unref(filter->tep);
 
 	tep_filter_reset(filter);
 
@@ -1462,10 +1459,10 @@ static int copy_filter_type(struct tep_event_filter *filter,
 	const char *name;
 	char *str;
 
-	/* Can't assume that the pevent's are the same */
+	/* Can't assume that the tep's are the same */
 	sys = filter_type->event->system;
 	name = filter_type->event->name;
-	event = tep_find_event_by_name(filter->pevent, sys, name);
+	event = tep_find_event_by_name(filter->tep, sys, name);
 	if (!event)
 		return -1;
 
@@ -1522,167 +1519,6 @@ int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *sour
 	return ret;
 }
 
-
-/**
- * tep_update_trivial - update the trivial filters with the given filter
- * @dest - the filter to update
- * @source - the filter as the source of the update
- * @type - the type of trivial filter to update.
- *
- * Scan dest for trivial events matching @type to replace with the source.
- *
- * Returns 0 on success and -1 if there was a problem updating, but
- *   events may have still been updated on error.
- */
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
-		       enum tep_filter_trivial_type type)
-{
-	struct tep_handle *src_pevent;
-	struct tep_handle *dest_pevent;
-	struct tep_event *event;
-	struct tep_filter_type *filter_type;
-	struct tep_filter_arg *arg;
-	char *str;
-	int i;
-
-	src_pevent = source->pevent;
-	dest_pevent = dest->pevent;
-
-	/* Do nothing if either of the filters has nothing to filter */
-	if (!dest->filters || !source->filters)
-		return 0;
-
-	for (i = 0; i < dest->filters; i++) {
-		filter_type = &dest->event_filters[i];
-		arg = filter_type->filter;
-		if (arg->type != TEP_FILTER_ARG_BOOLEAN)
-			continue;
-		if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) ||
-		    (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE))
-			continue;
-
-		event = filter_type->event;
-
-		if (src_pevent != dest_pevent) {
-			/* do a look up */
-			event = tep_find_event_by_name(src_pevent,
-						       event->system,
-						       event->name);
-			if (!event)
-				return -1;
-		}
-
-		str = tep_filter_make_string(source, event->id);
-		if (!str)
-			continue;
-
-		/* Don't bother if the filter is trivial too */
-		if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0)
-			filter_event(dest, event, str, NULL);
-		free(str);
-	}
-	return 0;
-}
-
-/**
- * tep_filter_clear_trivial - clear TRUE and FALSE filters
- * @filter: the filter to remove trivial filters from
- * @type: remove only true, false, or both
- *
- * Removes filters that only contain a TRUE or FALES boolean arg.
- *
- * Returns 0 on success and -1 if there was a problem.
- */
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
-			     enum tep_filter_trivial_type type)
-{
-	struct tep_filter_type *filter_type;
-	int count = 0;
-	int *ids = NULL;
-	int i;
-
-	if (!filter->filters)
-		return 0;
-
-	/*
-	 * Two steps, first get all ids with trivial filters.
-	 *  then remove those ids.
-	 */
-	for (i = 0; i < filter->filters; i++) {
-		int *new_ids;
-
-		filter_type = &filter->event_filters[i];
-		if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
-			continue;
-		switch (type) {
-		case TEP_FILTER_TRIVIAL_FALSE:
-			if (filter_type->filter->boolean.value)
-				continue;
-			break;
-		case TEP_FILTER_TRIVIAL_TRUE:
-			if (!filter_type->filter->boolean.value)
-				continue;
-		default:
-			break;
-		}
-
-		new_ids = realloc(ids, sizeof(*ids) * (count + 1));
-		if (!new_ids) {
-			free(ids);
-			return -1;
-		}
-
-		ids = new_ids;
-		ids[count++] = filter_type->event_id;
-	}
-
-	if (!count)
-		return 0;
-
-	for (i = 0; i < count; i++)
-		tep_filter_remove_event(filter, ids[i]);
-
-	free(ids);
-	return 0;
-}
-
-/**
- * tep_filter_event_has_trivial - return true event contains trivial filter
- * @filter: the filter with the information
- * @event_id: the id of the event to test
- * @type: trivial type to test for (TRUE, FALSE, EITHER)
- *
- * Returns 1 if the event contains a matching trivial type
- *  otherwise 0.
- */
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
-				 int event_id,
-				 enum tep_filter_trivial_type type)
-{
-	struct tep_filter_type *filter_type;
-
-	if (!filter->filters)
-		return 0;
-
-	filter_type = find_filter_type(filter, event_id);
-
-	if (!filter_type)
-		return 0;
-
-	if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
-		return 0;
-
-	switch (type) {
-	case TEP_FILTER_TRIVIAL_FALSE:
-		return !filter_type->filter->boolean.value;
-
-	case TEP_FILTER_TRIVIAL_TRUE:
-		return filter_type->filter->boolean.value;
-	default:
-		return 1;
-	}
-}
-
 static int test_filter(struct tep_event *event, struct tep_filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err);
 
@@ -1692,8 +1528,8 @@ get_comm(struct tep_event *event, struct tep_record *record)
 	const char *comm;
 	int pid;
 
-	pid = tep_data_pid(event->pevent, record);
-	comm = tep_data_comm_from_pid(event->pevent, pid);
+	pid = tep_data_pid(event->tep, record);
+	comm = tep_data_comm_from_pid(event->tep, pid);
 	return comm;
 }
 
@@ -1861,7 +1697,7 @@ static int test_num(struct tep_event *event, struct tep_filter_arg *arg,
 static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
 {
 	struct tep_event *event;
-	struct tep_handle *pevent;
+	struct tep_handle *tep;
 	unsigned long long addr;
 	const char *val = NULL;
 	unsigned int size;
@@ -1891,12 +1727,12 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *
 
 	} else {
 		event = arg->str.field->event;
-		pevent = event->pevent;
+		tep = event->tep;
 		addr = get_value(event, arg->str.field, record);
 
 		if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
 			/* convert to a kernel symbol */
-			val = tep_find_function(pevent, addr);
+			val = tep_find_function(tep, addr);
 
 		if (val == NULL) {
 			/* just use the hex of the string name */
@@ -2036,7 +1872,7 @@ int tep_event_filtered(struct tep_event_filter *filter, int event_id)
 enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 				struct tep_record *record)
 {
-	struct tep_handle *pevent = filter->pevent;
+	struct tep_handle *tep = filter->tep;
 	struct tep_filter_type *filter_type;
 	int event_id;
 	int ret;
@@ -2047,7 +1883,7 @@ enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 	if (!filter->filters)
 		return TEP_ERRNO__NO_FILTER;
 
-	event_id = tep_data_type(pevent, record);
+	event_id = tep_data_type(tep, record);
 
 	filter_type = find_filter_type(filter, event_id);
 	if (!filter_type)
@@ -2409,14 +2245,6 @@ int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter
 			break;
 		if (filter_type1->filter->type != filter_type2->filter->type)
 			break;
-		switch (filter_type1->filter->type) {
-		case TEP_FILTER_TRIVIAL_FALSE:
-		case TEP_FILTER_TRIVIAL_TRUE:
-			/* trivial types just need the type compared */
-			continue;
-		default:
-			break;
-		}
 		/* The best way to compare complex filters is with strings */
 		str1 = arg_to_str(filter1, filter_type1->filter);
 		str2 = arg_to_str(filter2, filter_type2->filter);
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index 77e4ec6402dd..e99867111387 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -14,7 +14,7 @@
 void __vwarning(const char *fmt, va_list ap)
 {
 	if (errno)
-		perror("trace-cmd");
+		perror("libtraceevent");
 	errno = 0;
 
 	fprintf(stderr, "  ");
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index a51b366f47da..3d43b56a6c98 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -25,9 +25,9 @@ process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 	return val ? (long long) le16toh(*val) : 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process___le16_to_cpup,
 				    TEP_FUNC_ARG_INT,
 				    "__le16_to_cpup",
@@ -36,8 +36,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process___le16_to_cpup,
+	tep_unregister_print_function(tep, process___le16_to_cpup,
 				      "__le16_to_cpup");
 }
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index a73eca34a8f9..7770fcb78e0f 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -126,7 +126,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu)
 static int function_handler(struct trace_seq *s, struct tep_record *record,
 			    struct tep_event *event, void *context)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long function;
 	unsigned long long pfunction;
 	const char *func;
@@ -136,12 +136,12 @@ static int function_handler(struct trace_seq *s, struct tep_record *record,
 	if (tep_get_field_val(s, event, "ip", record, &function, 1))
 		return trace_seq_putc(s, '!');
 
-	func = tep_find_function(pevent, function);
+	func = tep_find_function(tep, function);
 
 	if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
 		return trace_seq_putc(s, '!');
 
-	parent = tep_find_function(pevent, pfunction);
+	parent = tep_find_function(tep, pfunction);
 
 	if (parent && ftrace_indent->set)
 		index = add_and_get_index(parent, func, record->cpu);
@@ -164,9 +164,9 @@ static int function_handler(struct trace_seq *s, struct tep_record *record,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "ftrace", "function",
+	tep_register_event_handler(tep, -1, "ftrace", "function",
 				   function_handler, NULL);
 
 	tep_plugin_add_options("ftrace", plugin_options);
@@ -174,11 +174,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
 	int i, x;
 
-	tep_unregister_event_handler(pevent, -1, "ftrace", "function",
+	tep_unregister_event_handler(tep, -1, "ftrace", "function",
 				     function_handler, NULL);
 
 	for (i = 0; i <= cpus; i++) {
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index 5db5e401275f..bb434e0ed03a 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -67,23 +67,23 @@ static int timer_start_handler(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1,
+	tep_register_event_handler(tep, -1,
 				   "timer", "hrtimer_expire_entry",
 				   timer_expire_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+	tep_register_event_handler(tep, -1, "timer", "hrtimer_start",
 				   timer_start_handler, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1,
+	tep_unregister_event_handler(tep, -1,
 				     "timer", "hrtimer_expire_entry",
 				     timer_expire_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+	tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start",
 				     timer_start_handler, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index a5e34135dd6a..04fc125f38cb 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -48,16 +48,16 @@ process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args)
 	return jiffies;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_jbd2_dev_to_name,
 				    TEP_FUNC_ARG_STRING,
 				    "jbd2_dev_to_name",
 				    TEP_FUNC_ARG_INT,
 				    TEP_FUNC_ARG_VOID);
 
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_jiffies_to_msecs,
 				    TEP_FUNC_ARG_LONG,
 				    "jiffies_to_msecs",
@@ -66,11 +66,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process_jbd2_dev_to_name,
+	tep_unregister_print_function(tep, process_jbd2_dev_to_name,
 				      "jbd2_dev_to_name");
 
-	tep_unregister_print_function(pevent, process_jiffies_to_msecs,
+	tep_unregister_print_function(tep, process_jiffies_to_msecs,
 				      "jiffies_to_msecs");
 }
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 0e3c601f9ed1..edaec5d962c3 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -39,57 +39,57 @@ static int call_site_handler(struct trace_seq *s, struct tep_record *record,
 	if (tep_read_number_field(field, data, &val))
 		return 1;
 
-	func = tep_find_function(event->pevent, val);
+	func = tep_find_function(event->tep, val);
 	if (!func)
 		return 1;
 
-	addr = tep_find_function_address(event->pevent, val);
+	addr = tep_find_function_address(event->tep, val);
 
 	trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
 	return 1;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "kmem", "kfree",
+	tep_register_event_handler(tep, -1, "kmem", "kfree",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmalloc",
+	tep_register_event_handler(tep, -1, "kmem", "kmalloc",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+	tep_register_event_handler(tep, -1, "kmem", "kmalloc_node",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+	tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem",
+	tep_register_event_handler(tep, -1, "kmem",
 				   "kmem_cache_alloc_node",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+	tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free",
 				   call_site_handler, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "kmem", "kfree",
+	tep_unregister_event_handler(tep, -1, "kmem", "kfree",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmalloc",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem",
+	tep_unregister_event_handler(tep, -1, "kmem",
 				     "kmem_cache_alloc_node",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free",
 				     call_site_handler, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 64b9c25a1fd3..c8e623065a7e 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -389,8 +389,8 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 	 * We can only use the structure if file is of the same
 	 * endianness.
 	 */
-	if (tep_file_bigendian(event->pevent) ==
-	    tep_is_host_bigendian(event->pevent)) {
+	if (tep_is_file_bigendian(event->tep) ==
+	    tep_is_local_bigendian(event->tep)) {
 
 		trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
 				 role.level,
@@ -445,40 +445,40 @@ process_is_writable_pte(struct trace_seq *s, unsigned long long *args)
 	return pte & PT_WRITABLE_MASK;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
 	init_disassembler();
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_exit",
 				   kvm_exit_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
 				   kvm_emulate_insn_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
 				   kvm_nested_vmexit_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
 				   kvm_nested_vmexit_inject_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+	tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
 				   kvm_mmu_get_page_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+	tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
 				   kvm_mmu_print_role, NULL);
 
-	tep_register_event_handler(pevent, -1,
+	tep_register_event_handler(tep, -1,
 				   "kvmmmu", "kvm_mmu_unsync_page",
 				   kvm_mmu_print_role, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+	tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
 				   kvm_mmu_print_role, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu",
+	tep_register_event_handler(tep, -1, "kvmmmu",
 			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
 			NULL);
 
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_is_writable_pte,
 				    TEP_FUNC_ARG_INT,
 				    "is_writable_pte",
@@ -487,37 +487,37 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit",
 				     kvm_exit_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
 				     kvm_emulate_insn_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
 				     kvm_nested_vmexit_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
 				     kvm_nested_vmexit_inject_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+	tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
 				     kvm_mmu_get_page_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+	tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
 				     kvm_mmu_print_role, NULL);
 
-	tep_unregister_event_handler(pevent, -1,
+	tep_unregister_event_handler(tep, -1,
 				     "kvmmmu", "kvm_mmu_unsync_page",
 				     kvm_mmu_print_role, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+	tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
 				     kvm_mmu_print_role, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu",
+	tep_unregister_event_handler(tep, -1, "kvmmmu",
 			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
 			NULL);
 
-	tep_unregister_print_function(pevent, process_is_writable_pte,
+	tep_unregister_print_function(tep, process_is_writable_pte,
 				      "is_writable_pte");
 }
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index e38b9477aad2..884303c26b5c 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -87,17 +87,17 @@ static int drv_bss_info_changed(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "mac80211",
+	tep_register_event_handler(tep, -1, "mac80211",
 				   "drv_bss_info_changed",
 				   drv_bss_info_changed, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "mac80211",
+	tep_unregister_event_handler(tep, -1, "mac80211",
 				     "drv_bss_info_changed",
 				     drv_bss_info_changed, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index 834c9e378ff8..957389a0ff7a 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -62,7 +62,7 @@ static void write_and_save_comm(struct tep_format_field *field,
 	comm = &s->buffer[len];
 
 	/* Help out the comm to ids. This will handle dups */
-	tep_register_comm(field->event->pevent, comm, pid);
+	tep_register_comm(field->event->tep, comm, pid);
 }
 
 static int sched_wakeup_handler(struct trace_seq *s,
@@ -135,27 +135,27 @@ static int sched_switch_handler(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "sched", "sched_switch",
+	tep_register_event_handler(tep, -1, "sched", "sched_switch",
 				   sched_switch_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+	tep_register_event_handler(tep, -1, "sched", "sched_wakeup",
 				   sched_wakeup_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+	tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new",
 				   sched_wakeup_handler, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+	tep_unregister_event_handler(tep, -1, "sched", "sched_switch",
 				     sched_switch_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+	tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup",
 				     sched_wakeup_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+	tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new",
 				     sched_wakeup_handler, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 4eba25cc1431..5d0387a4b65a 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -414,9 +414,9 @@ unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_scsi_trace_parse_cdb,
 				    TEP_FUNC_ARG_STRING,
 				    "scsi_trace_parse_cdb",
@@ -427,8 +427,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+	tep_unregister_print_function(tep, process_scsi_trace_parse_cdb,
 				      "scsi_trace_parse_cdb");
 }
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index bc0496e4c296..993b208d0323 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -120,9 +120,9 @@ unsigned long long process_xen_hypercall_name(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_xen_hypercall_name,
 				    TEP_FUNC_ARG_STRING,
 				    "xen_hypercall_name",
@@ -131,8 +131,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process_xen_hypercall_name,
+	tep_unregister_print_function(tep, process_xen_hypercall_name,
 				      "xen_hypercall_name");
 }
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 35bff92cc773..68caa9a976d0 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -27,7 +27,7 @@ Explanation of the Linux-Kernel Memory Consistency Model
   19. AND THEN THERE WAS ALPHA
   20. THE HAPPENS-BEFORE RELATION: hb
   21. THE PROPAGATES-BEFORE RELATION: pb
-  22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
+  22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
   23. LOCKING
   24. ODDS AND ENDS
 
@@ -1430,8 +1430,8 @@ they execute means that it cannot have cycles.  This requirement is
 the content of the LKMM's "propagation" axiom.
 
 
-RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
-----------------------------------------------------
+RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
+-------------------------------------------------------------
 
 RCU (Read-Copy-Update) is a powerful synchronization mechanism.  It
 rests on two concepts: grace periods and read-side critical sections.
@@ -1446,17 +1446,19 @@ As far as memory models are concerned, RCU's main feature is its
 Grace-Period Guarantee, which states that a critical section can never
 span a full grace period.  In more detail, the Guarantee says:
 
-	If a critical section starts before a grace period then it
-	must end before the grace period does.  In addition, every
-	store that propagates to the critical section's CPU before the
-	end of the critical section must propagate to every CPU before
-	the end of the grace period.
+	For any critical section C and any grace period G, at least
+	one of the following statements must hold:
 
-	If a critical section ends after a grace period ends then it
-	must start after the grace period does.  In addition, every
-	store that propagates to the grace period's CPU before the
-	start of the grace period must propagate to every CPU before
-	the start of the critical section.
+(1)	C ends before G does, and in addition, every store that
+	propagates to C's CPU before the end of C must propagate to
+	every CPU before G ends.
+
+(2)	G starts before C does, and in addition, every store that
+	propagates to G's CPU before the start of G must propagate
+	to every CPU before C starts.
+
+In particular, it is not possible for a critical section to both start
+before and end after a grace period.
 
 Here is a simple example of RCU in action:
 
@@ -1483,10 +1485,11 @@ The Grace Period Guarantee tells us that when this code runs, it will
 never end with r1 = 1 and r2 = 0.  The reasoning is as follows.  r1 = 1
 means that P0's store to x propagated to P1 before P1 called
 synchronize_rcu(), so P0's critical section must have started before
-P1's grace period.  On the other hand, r2 = 0 means that P0's store to
-y, which occurs before the end of the critical section, did not
-propagate to P1 before the end of the grace period, violating the
-Guarantee.
+P1's grace period, contrary to part (2) of the Guarantee.  On the
+other hand, r2 = 0 means that P0's store to y, which occurs before the
+end of the critical section, did not propagate to P1 before the end of
+the grace period, contrary to part (1).  Together the results violate
+the Guarantee.
 
 In the kernel's implementations of RCU, the requirements for stores
 to propagate to every CPU are fulfilled by placing strong fences at
@@ -1504,11 +1507,11 @@ before" or "ends after" a grace period?  Some aspects of the meaning
 are pretty obvious, as in the example above, but the details aren't
 entirely clear.  The LKMM formalizes this notion by means of the
 rcu-link relation.  rcu-link encompasses a very general notion of
-"before": Among other things, X ->rcu-link Z includes cases where X
-happens-before or is equal to some event Y which is equal to or comes
-before Z in the coherence order.  When Y = Z this says that X ->rfe Z
-implies X ->rcu-link Z.  In addition, when Y = X it says that X ->fr Z
-and X ->co Z each imply X ->rcu-link Z.
+"before": If E and F are RCU fence events (i.e., rcu_read_lock(),
+rcu_read_unlock(), or synchronize_rcu()) then among other things,
+E ->rcu-link F includes cases where E is po-before some memory-access
+event X, F is po-after some memory-access event Y, and we have any of
+X ->rfe Y, X ->co Y, or X ->fr Y.
 
 The formal definition of the rcu-link relation is more than a little
 obscure, and we won't give it here.  It is closely related to the pb
@@ -1516,171 +1519,173 @@ relation, and the details don't matter unless you want to comb through
 a somewhat lengthy formal proof.  Pretty much all you need to know
 about rcu-link is the information in the preceding paragraph.
 
-The LKMM also defines the gp and rscs relations.  They bring grace
-periods and read-side critical sections into the picture, in the
+The LKMM also defines the rcu-gp and rcu-rscsi relations.  They bring
+grace periods and read-side critical sections into the picture, in the
 following way:
 
-	E ->gp F means there is a synchronize_rcu() fence event S such
-	that E ->po S and either S ->po F or S = F.  In simple terms,
-	there is a grace period po-between E and F.
+	E ->rcu-gp F means that E and F are in fact the same event,
+	and that event is a synchronize_rcu() fence (i.e., a grace
+	period).
 
-	E ->rscs F means there is a critical section delimited by an
-	rcu_read_lock() fence L and an rcu_read_unlock() fence U, such
-	that E ->po U and either L ->po F or L = F.  You can think of
-	this as saying that E and F are in the same critical section
-	(in fact, it also allows E to be po-before the start of the
-	critical section and F to be po-after the end).
+	E ->rcu-rscsi F means that E and F are the rcu_read_unlock()
+	and rcu_read_lock() fence events delimiting some read-side
+	critical section.  (The 'i' at the end of the name emphasizes
+	that this relation is "inverted": It links the end of the
+	critical section to the start.)
 
 If we think of the rcu-link relation as standing for an extended
-"before", then X ->gp Y ->rcu-link Z says that X executes before a
-grace period which ends before Z executes.  (In fact it covers more
-than this, because it also includes cases where X executes before a
-grace period and some store propagates to Z's CPU before Z executes
-but doesn't propagate to some other CPU until after the grace period
-ends.)  Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or
-before the start of) a critical section which starts before Z
-executes.
-
-The LKMM goes on to define the rcu-fence relation as a sequence of gp
-and rscs links separated by rcu-link links, in which the number of gp
-links is >= the number of rscs links.  For example:
+"before", then X ->rcu-gp Y ->rcu-link Z roughly says that X is a
+grace period which ends before Z begins.  (In fact it covers more than
+this, because it also includes cases where some store propagates to
+Z's CPU before Z begins but doesn't propagate to some other CPU until
+after X ends.)  Similarly, X ->rcu-rscsi Y ->rcu-link Z says that X is
+the end of a critical section which starts before Z begins.
+
+The LKMM goes on to define the rcu-fence relation as a sequence of
+rcu-gp and rcu-rscsi links separated by rcu-link links, in which the
+number of rcu-gp links is >= the number of rcu-rscsi links.  For
+example:
 
-	X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+	X ->rcu-gp Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
 
 would imply that X ->rcu-fence V, because this sequence contains two
-gp links and only one rscs link.  (It also implies that X ->rcu-fence T
-and Z ->rcu-fence V.)  On the other hand:
+rcu-gp links and one rcu-rscsi link.  (It also implies that
+X ->rcu-fence T and Z ->rcu-fence V.)  On the other hand:
 
-	X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+	X ->rcu-rscsi Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
 
 does not imply X ->rcu-fence V, because the sequence contains only
-one gp link but two rscs links.
+one rcu-gp link but two rcu-rscsi links.
 
 The rcu-fence relation is important because the Grace Period Guarantee
 means that rcu-fence acts kind of like a strong fence.  In particular,
-if W is a write and we have W ->rcu-fence Z, the Guarantee says that W
-will propagate to every CPU before Z executes.
+E ->rcu-fence F implies not only that E begins before F ends, but also
+that any write po-before E will propagate to every CPU before any
+instruction po-after F can execute.  (However, it does not imply that
+E must execute before F; in fact, each synchronize_rcu() fence event
+is linked to itself by rcu-fence as a degenerate case.)
 
 To prove this in full generality requires some intellectual effort.
 We'll consider just a very simple case:
 
-	W ->gp X ->rcu-link Y ->rscs Z.
+	G ->rcu-gp W ->rcu-link Z ->rcu-rscsi F.
 
-This formula means that there is a grace period G and a critical
-section C such that:
+This formula means that G and W are the same event (a grace period),
+and there are events X, Y and a read-side critical section C such that:
 
-	1. W is po-before G;
+	1. G = W is po-before or equal to X;
 
-	2. X is equal to or po-after G;
+	2. X comes "before" Y in some sense (including rfe, co and fr);
 
-	3. X comes "before" Y in some sense;
+	2. Y is po-before Z;
 
-	4. Y is po-before the end of C;
+	4. Z is the rcu_read_unlock() event marking the end of C;
 
-	5. Z is equal to or po-after the start of C.
+	5. F is the rcu_read_lock() event marking the start of C.
 
-From 2 - 4 we deduce that the grace period G ends before the critical
-section C.  Then the second part of the Grace Period Guarantee says
-not only that G starts before C does, but also that W (which executes
-on G's CPU before G starts) must propagate to every CPU before C
-starts.  In particular, W propagates to every CPU before Z executes
-(or finishes executing, in the case where Z is equal to the
-rcu_read_lock() fence event which starts C.)  This sort of reasoning
-can be expanded to handle all the situations covered by rcu-fence.
+From 1 - 4 we deduce that the grace period G ends before the critical
+section C.  Then part (2) of the Grace Period Guarantee says not only
+that G starts before C does, but also that any write which executes on
+G's CPU before G starts must propagate to every CPU before C starts.
+In particular, the write propagates to every CPU before F finishes
+executing and hence before any instruction po-after F can execute.
+This sort of reasoning can be extended to handle all the situations
+covered by rcu-fence.
 
 Finally, the LKMM defines the RCU-before (rb) relation in terms of
 rcu-fence.  This is done in essentially the same way as the pb
 relation was defined in terms of strong-fence.  We will omit the
-details; the end result is that E ->rb F implies E must execute before
-F, just as E ->pb F does (and for much the same reasons).
+details; the end result is that E ->rb F implies E must execute
+before F, just as E ->pb F does (and for much the same reasons).
 
 Putting this all together, the LKMM expresses the Grace Period
 Guarantee by requiring that the rb relation does not contain a cycle.
-Equivalently, this "rcu" axiom requires that there are no events E and
-F with E ->rcu-link F ->rcu-fence E.  Or to put it a third way, the
-axiom requires that there are no cycles consisting of gp and rscs
-alternating with rcu-link, where the number of gp links is >= the
-number of rscs links.
+Equivalently, this "rcu" axiom requires that there are no events E
+and F with E ->rcu-link F ->rcu-fence E.  Or to put it a third way,
+the axiom requires that there are no cycles consisting of rcu-gp and
+rcu-rscsi alternating with rcu-link, where the number of rcu-gp links
+is >= the number of rcu-rscsi links.
 
 Justifying the axiom isn't easy, but it is in fact a valid
 formalization of the Grace Period Guarantee.  We won't attempt to go
 through the detailed argument, but the following analysis gives a
-taste of what is involved.  Suppose we have a violation of the first
-part of the Guarantee: A critical section starts before a grace
-period, and some store propagates to the critical section's CPU before
-the end of the critical section but doesn't propagate to some other
-CPU until after the end of the grace period.
+taste of what is involved.  Suppose both parts of the Guarantee are
+violated: A critical section starts before a grace period, and some
+store propagates to the critical section's CPU before the end of the
+critical section but doesn't propagate to some other CPU until after
+the end of the grace period.
 
 Putting symbols to these ideas, let L and U be the rcu_read_lock() and
 rcu_read_unlock() fence events delimiting the critical section in
 question, and let S be the synchronize_rcu() fence event for the grace
 period.  Saying that the critical section starts before S means there
-are events E and F where E is po-after L (which marks the start of the
-critical section), E is "before" F in the sense of the rcu-link
-relation, and F is po-before the grace period S:
+are events Q and R where Q is po-after L (which marks the start of the
+critical section), Q is "before" R in the sense used by the rcu-link
+relation, and R is po-before the grace period S.  Thus we have:
 
-	L ->po E ->rcu-link F ->po S.
+	L ->rcu-link S.
 
-Let W be the store mentioned above, let Z come before the end of the
+Let W be the store mentioned above, let Y come before the end of the
 critical section and witness that W propagates to the critical
-section's CPU by reading from W, and let Y on some arbitrary CPU be a
-witness that W has not propagated to that CPU, where Y happens after
+section's CPU by reading from W, and let Z on some arbitrary CPU be a
+witness that W has not propagated to that CPU, where Z happens after
 some event X which is po-after S.  Symbolically, this amounts to:
 
-	S ->po X ->hb* Y ->fr W ->rf Z ->po U.
+	S ->po X ->hb* Z ->fr W ->rf Y ->po U.
 
-The fr link from Y to W indicates that W has not propagated to Y's CPU
-at the time that Y executes.  From this, it can be shown (see the
-discussion of the rcu-link relation earlier) that X and Z are related
-by rcu-link, yielding:
+The fr link from Z to W indicates that W has not propagated to Z's CPU
+at the time that Z executes.  From this, it can be shown (see the
+discussion of the rcu-link relation earlier) that S and U are related
+by rcu-link:
 
-	S ->po X ->rcu-link Z ->po U.
+	S ->rcu-link U.
 
-The formulas say that S is po-between F and X, hence F ->gp X.  They
-also say that Z comes before the end of the critical section and E
-comes after its start, hence Z ->rscs E.  From all this we obtain:
+Since S is a grace period we have S ->rcu-gp S, and since L and U are
+the start and end of the critical section C we have U ->rcu-rscsi L.
+From this we obtain:
 
-	F ->gp X ->rcu-link Z ->rscs E ->rcu-link F,
+	S ->rcu-gp S ->rcu-link U ->rcu-rscsi L ->rcu-link S,
 
 a forbidden cycle.  Thus the "rcu" axiom rules out this violation of
 the Grace Period Guarantee.
 
 For something a little more down-to-earth, let's see how the axiom
 works out in practice.  Consider the RCU code example from above, this
-time with statement labels added to the memory access instructions:
+time with statement labels added:
 
 	int x, y;
 
 	P0()
 	{
-		rcu_read_lock();
-		W: WRITE_ONCE(x, 1);
-		X: WRITE_ONCE(y, 1);
-		rcu_read_unlock();
+		L: rcu_read_lock();
+		X: WRITE_ONCE(x, 1);
+		Y: WRITE_ONCE(y, 1);
+		U: rcu_read_unlock();
 	}
 
 	P1()
 	{
 		int r1, r2;
 
-		Y: r1 = READ_ONCE(x);
-		synchronize_rcu();
-		Z: r2 = READ_ONCE(y);
+		Z: r1 = READ_ONCE(x);
+		S: synchronize_rcu();
+		W: r2 = READ_ONCE(y);
 	}
 
 
-If r2 = 0 at the end then P0's store at X overwrites the value that
-P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X.
-In addition, there is a synchronize_rcu() between Y and Z, so therefore
-we have Y ->gp Z.
+If r2 = 0 at the end then P0's store at Y overwrites the value that
+P1's load at W reads from, so we have W ->fre Y.  Since S ->po W and
+also Y ->po U, we get S ->rcu-link U.  In addition, S ->rcu-gp S
+because S is a grace period.
 
-If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
-so we have W ->rcu-link Y.  In addition, W and X are in the same critical
-section, so therefore we have X ->rscs W.
+If r1 = 1 at the end then P1's load at Z reads from P0's store at X,
+so we have X ->rfe Z.  Together with L ->po X and Z ->po S, this
+yields L ->rcu-link S.  And since L and U are the start and end of a
+critical section, we have U ->rcu-rscsi L.
 
-Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle,
-violating the "rcu" axiom.  Hence the outcome is not allowed by the
-LKMM, as we would expect.
+Then U ->rcu-rscsi L ->rcu-link S ->rcu-gp S ->rcu-link U is a
+forbidden cycle, violating the "rcu" axiom.  Hence the outcome is not
+allowed by the LKMM, as we would expect.
 
 For contrast, let's see what can happen in a more complicated example:
 
@@ -1690,51 +1695,52 @@ For contrast, let's see what can happen in a more complicated example:
 	{
 		int r0;
 
-		rcu_read_lock();
-		W: r0 = READ_ONCE(x);
-		X: WRITE_ONCE(y, 1);
-		rcu_read_unlock();
+		L0: rcu_read_lock();
+		    r0 = READ_ONCE(x);
+		    WRITE_ONCE(y, 1);
+		U0: rcu_read_unlock();
 	}
 
 	P1()
 	{
 		int r1;
 
-		Y: r1 = READ_ONCE(y);
-		synchronize_rcu();
-		Z: WRITE_ONCE(z, 1);
+		    r1 = READ_ONCE(y);
+		S1: synchronize_rcu();
+		    WRITE_ONCE(z, 1);
 	}
 
 	P2()
 	{
 		int r2;
 
-		rcu_read_lock();
-		U: r2 = READ_ONCE(z);
-		V: WRITE_ONCE(x, 1);
-		rcu_read_unlock();
+		L2: rcu_read_lock();
+		    r2 = READ_ONCE(z);
+		    WRITE_ONCE(x, 1);
+		U2: rcu_read_unlock();
 	}
 
 If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
-that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W.
-However this cycle is not forbidden, because the sequence of relations
-contains fewer instances of gp (one) than of rscs (two).  Consequently
-the outcome is allowed by the LKMM.  The following instruction timing
-diagram shows how it might actually occur:
+that U0 ->rcu-rscsi L0 ->rcu-link S1 ->rcu-gp S1 ->rcu-link U2 ->rcu-rscsi
+L2 ->rcu-link U0.  However this cycle is not forbidden, because the
+sequence of relations contains fewer instances of rcu-gp (one) than of
+rcu-rscsi (two).  Consequently the outcome is allowed by the LKMM.
+The following instruction timing diagram shows how it might actually
+occur:
 
 P0			P1			P2
 --------------------	--------------------	--------------------
 rcu_read_lock()
-X: WRITE_ONCE(y, 1)
-			Y: r1 = READ_ONCE(y)
+WRITE_ONCE(y, 1)
+			r1 = READ_ONCE(y)
 			synchronize_rcu() starts
 			.			rcu_read_lock()
-			.			V: WRITE_ONCE(x, 1)
-W: r0 = READ_ONCE(x)	.
+			.			WRITE_ONCE(x, 1)
+r0 = READ_ONCE(x)	.
 rcu_read_unlock()	.
 			synchronize_rcu() ends
-			Z: WRITE_ONCE(z, 1)
-						U: r2 = READ_ONCE(z)
+			WRITE_ONCE(z, 1)
+						r2 = READ_ONCE(z)
 						rcu_read_unlock()
 
 This requires P0 and P2 to execute their loads and stores out of
@@ -1744,6 +1750,15 @@ section in P0 both starts before P1's grace period does and ends
 before it does, and the critical section in P2 both starts after P1's
 grace period does and ends after it does.
 
+Addendum: The LKMM now supports SRCU (Sleepable Read-Copy-Update) in
+addition to normal RCU.  The ideas involved are much the same as
+above, with new relations srcu-gp and srcu-rscsi added to represent
+SRCU grace periods and read-side critical sections.  There is a
+restriction on the srcu-gp and srcu-rscsi links that can appear in an
+rcu-fence sequence (the srcu-rscsi links must be paired with srcu-gp
+links having the same SRCU domain with proper nesting); the details
+are relatively unimportant.
+
 
 LOCKING
 -------
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 0f2c366518c6..2b87f3971548 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -20,13 +20,17 @@ that litmus test to be exercised within the Linux kernel.
 REQUIREMENTS
 ============
 
-Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded
-separately:
+Version 7.52 or higher of the "herd7" and "klitmus7" tools must be
+downloaded separately:
 
   https://github.com/herd/herdtools7
 
 See "herdtools7/INSTALL.md" for installation instructions.
 
+Note that although these tools usually provide backwards compatibility,
+this is not absolutely guaranteed.  Therefore, if a later version does
+not work, please try using the exact version called out above.
+
 
 ==================
 BASIC USAGE: HERD7
@@ -221,8 +225,29 @@ The Linux-kernel memory model has the following limitations:
 		additional call_rcu() process to the site of the
 		emulated rcu-barrier().
 
-	e.	Sleepable RCU (SRCU) is not modeled.  It can be
-		emulated, but perhaps not simply.
+	e.	Although sleepable RCU (SRCU) is now modeled, there
+		are some subtle differences between its semantics and
+		those in the Linux kernel.  For example, the kernel
+		might interpret the following sequence as two partially
+		overlapping SRCU read-side critical sections:
+
+			 1  r1 = srcu_read_lock(&my_srcu);
+			 2  do_something_1();
+			 3  r2 = srcu_read_lock(&my_srcu);
+			 4  do_something_2();
+			 5  srcu_read_unlock(&my_srcu, r1);
+			 6  do_something_3();
+			 7  srcu_read_unlock(&my_srcu, r2);
+
+		In contrast, LKMM will interpret this as a nested pair of
+		SRCU read-side critical sections, with the outer critical
+		section spanning lines 1-7 and the inner critical section
+		spanning lines 3-5.
+
+		This difference would be more of a concern had anyone
+		identified a reasonable use case for partially overlapping
+		SRCU read-side critical sections.  For more information,
+		please see: https://paulmck.livejournal.com/40593.html
 
 	f.	Reader-writer locking is not modeled.  It can be
 		emulated in litmus tests using atomic read-modify-write
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 796513362c05..def9131d3d8e 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -33,8 +33,14 @@ enum Barriers = 'wmb (*smp_wmb*) ||
 		'after-unlock-lock (*smp_mb__after_unlock_lock*)
 instructions F[Barriers]
 
+(* SRCU *)
+enum SRCU = 'srcu-lock || 'srcu-unlock || 'sync-srcu
+instructions SRCU[SRCU]
+(* All srcu events *)
+let Srcu = Srcu-lock | Srcu-unlock | Sync-srcu
+
 (* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
-let matched = let rec
+let rcu-rscs = let rec
 	    unmatched-locks = Rcu-lock \ domain(matched)
 	and unmatched-unlocks = Rcu-unlock \ range(matched)
 	and unmatched = unmatched-locks | unmatched-unlocks
@@ -46,8 +52,27 @@ let matched = let rec
 	in matched
 
 (* Validate nesting *)
-flag ~empty Rcu-lock \ domain(matched) as unbalanced-rcu-locking
-flag ~empty Rcu-unlock \ range(matched) as unbalanced-rcu-locking
+flag ~empty Rcu-lock \ domain(rcu-rscs) as unbalanced-rcu-locking
+flag ~empty Rcu-unlock \ range(rcu-rscs) as unbalanced-rcu-locking
+
+(* Compute matching pairs of nested Srcu-lock and Srcu-unlock *)
+let srcu-rscs = let rec
+	    unmatched-locks = Srcu-lock \ domain(matched)
+	and unmatched-unlocks = Srcu-unlock \ range(matched)
+	and unmatched = unmatched-locks | unmatched-unlocks
+	and unmatched-po = ([unmatched] ; po ; [unmatched]) & loc
+	and unmatched-locks-to-unlocks =
+		([unmatched-locks] ; po ; [unmatched-unlocks]) & loc
+	and matched = matched | (unmatched-locks-to-unlocks \
+		(unmatched-po ; unmatched-po))
+	in matched
+
+(* Validate nesting *)
+flag ~empty Srcu-lock \ domain(srcu-rscs) as unbalanced-srcu-locking
+flag ~empty Srcu-unlock \ range(srcu-rscs) as unbalanced-srcu-locking
+
+(* Check for use of synchronize_srcu() inside an RCU critical section *)
+flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep
 
-(* Outermost level of nesting only *)
-let crit = matched \ (po^-1 ; matched ; po^-1)
+(* Validate SRCU dynamic match *)
+flag ~empty different-values(srcu-rscs) as srcu-bad-nesting
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index 8f23c74a96fd..8dcb37835b61 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -33,7 +33,7 @@ let mb = ([M] ; fencerel(Mb) ; [M]) |
 	([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M]) |
 	([M] ; po ; [UL] ; (co | po) ; [LKW] ;
 		fencerel(After-unlock-lock) ; [M])
-let gp = po ; [Sync-rcu] ; po?
+let gp = po ; [Sync-rcu | Sync-srcu] ; po?
 
 let strong-fence = mb | gp
 
@@ -91,32 +91,47 @@ acyclic pb as propagation
 (*******)
 
 (*
- * Effect of read-side critical section proceeds from the rcu_read_lock()
- * onward on the one hand and from the rcu_read_unlock() backwards on the
- * other hand.
+ * Effects of read-side critical sections proceed from the rcu_read_unlock()
+ * or srcu_read_unlock() backwards on the one hand, and from the
+ * rcu_read_lock() or srcu_read_lock() forwards on the other hand.
+ *
+ * In the definition of rcu-fence below, the po term at the left-hand side
+ * of each disjunct and the po? term at the right-hand end have been factored
+ * out.  They have been moved into the definitions of rcu-link and rb.
+ * This was necessary in order to apply the "& loc" tests correctly.
  *)
-let rscs = po ; crit^-1 ; po?
+let rcu-gp = [Sync-rcu]		(* Compare with gp *)
+let srcu-gp = [Sync-srcu]
+let rcu-rscsi = rcu-rscs^-1
+let srcu-rscsi = srcu-rscs^-1
 
 (*
  * The synchronize_rcu() strong fence is special in that it can order not
  * one but two non-rf relations, but only in conjunction with an RCU
  * read-side critical section.
  *)
-let rcu-link = hb* ; pb* ; prop
+let rcu-link = po? ; hb* ; pb* ; prop ; po
 
 (*
  * Any sequence containing at least as many grace periods as RCU read-side
  * critical sections (joined by rcu-link) acts as a generalized strong fence.
+ * Likewise for SRCU grace periods and read-side critical sections, provided
+ * the synchronize_srcu() and srcu_read_[un]lock() calls refer to the same
+ * struct srcu_struct location.
  *)
-let rec rcu-fence = gp |
-	(gp ; rcu-link ; rscs) |
-	(rscs ; rcu-link ; gp) |
-	(gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) |
-	(rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) |
+let rec rcu-fence = rcu-gp | srcu-gp |
+	(rcu-gp ; rcu-link ; rcu-rscsi) |
+	((srcu-gp ; rcu-link ; srcu-rscsi) & loc) |
+	(rcu-rscsi ; rcu-link ; rcu-gp) |
+	((srcu-rscsi ; rcu-link ; srcu-gp) & loc) |
+	(rcu-gp ; rcu-link ; rcu-fence ; rcu-link ; rcu-rscsi) |
+	((srcu-gp ; rcu-link ; rcu-fence ; rcu-link ; srcu-rscsi) & loc) |
+	(rcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; rcu-gp) |
+	((srcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; srcu-gp) & loc) |
 	(rcu-fence ; rcu-link ; rcu-fence)
 
 (* rb orders instructions just as pb does *)
-let rb = prop ; rcu-fence ; hb* ; pb*
+let rb = prop ; po ; rcu-fence ; po? ; hb* ; pb*
 
 irreflexive rb as rcu
 
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
index b27911cc087d..551eeaa389d4 100644
--- a/tools/memory-model/linux-kernel.def
+++ b/tools/memory-model/linux-kernel.def
@@ -47,6 +47,12 @@ rcu_read_unlock() { __fence{rcu-unlock}; }
 synchronize_rcu() { __fence{sync-rcu}; }
 synchronize_rcu_expedited() { __fence{sync-rcu}; }
 
+// SRCU
+srcu_read_lock(X)  __srcu{srcu-lock}(X)
+srcu_read_unlock(X,Y) { __srcu{srcu-unlock}(X,Y); }
+synchronize_srcu(X)  { __srcu{sync-srcu}(X); }
+synchronize_srcu_expedited(X)  { __srcu{sync-srcu}(X); }
+
 // Atomic
 atomic_read(X) READ_ONCE(*X)
 atomic_set(X,V) { WRITE_ONCE(*X,V); }
diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
index 305ded17e741..a059d1a6d8a2 100644
--- a/tools/memory-model/lock.cat
+++ b/tools/memory-model/lock.cat
@@ -6,9 +6,6 @@
 
 (*
  * Generate coherence orders and handle lock operations
- *
- * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48.
- * spin_is_locked() is functional from herd7 version 7.49.
  *)
 
 include "cross.cat"
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index b0d7dc3d71b5..7a111a77b7aa 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -33,7 +33,11 @@
 #define INSN_STACK		8
 #define INSN_BUG		9
 #define INSN_NOP		10
-#define INSN_OTHER		11
+#define INSN_STAC		11
+#define INSN_CLAC		12
+#define INSN_STD		13
+#define INSN_CLD		14
+#define INSN_OTHER		15
 #define INSN_LAST		INSN_OTHER
 
 enum op_dest_type {
@@ -41,6 +45,7 @@ enum op_dest_type {
 	OP_DEST_REG_INDIRECT,
 	OP_DEST_MEM,
 	OP_DEST_PUSH,
+	OP_DEST_PUSHF,
 	OP_DEST_LEAVE,
 };
 
@@ -55,6 +60,7 @@ enum op_src_type {
 	OP_SRC_REG_INDIRECT,
 	OP_SRC_CONST,
 	OP_SRC_POP,
+	OP_SRC_POPF,
 	OP_SRC_ADD,
 	OP_SRC_AND,
 };
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 540a209b78ab..472e991f6512 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -357,19 +357,26 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		/* pushf */
 		*type = INSN_STACK;
 		op->src.type = OP_SRC_CONST;
-		op->dest.type = OP_DEST_PUSH;
+		op->dest.type = OP_DEST_PUSHF;
 		break;
 
 	case 0x9d:
 		/* popf */
 		*type = INSN_STACK;
-		op->src.type = OP_SRC_POP;
+		op->src.type = OP_SRC_POPF;
 		op->dest.type = OP_DEST_MEM;
 		break;
 
 	case 0x0f:
 
-		if (op2 >= 0x80 && op2 <= 0x8f) {
+		if (op2 == 0x01) {
+
+			if (modrm == 0xca)
+				*type = INSN_CLAC;
+			else if (modrm == 0xcb)
+				*type = INSN_STAC;
+
+		} else if (op2 >= 0x80 && op2 <= 0x8f) {
 
 			*type = INSN_JUMP_CONDITIONAL;
 
@@ -444,6 +451,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		*type = INSN_CALL;
 		break;
 
+	case 0xfc:
+		*type = INSN_CLD;
+		break;
+
+	case 0xfd:
+		*type = INSN_STD;
+		break;
+
 	case 0xff:
 		if (modrm_reg == 2 || modrm_reg == 3)
 
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 694abc628e9b..f3b378126011 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -29,7 +29,7 @@
 #include "builtin.h"
 #include "check.h"
 
-bool no_fp, no_unreachable, retpoline, module;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
 
 static const char * const check_usage[] = {
 	"objtool check [<options>] file.o",
@@ -41,6 +41,8 @@ const struct option check_options[] = {
 	OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
 	OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
 	OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
+	OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
+	OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
 	OPT_END(),
 };
 
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index 28ff40e19a14..69762f9c5602 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -20,7 +20,7 @@
 #include <subcmd/parse-options.h>
 
 extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
 
 extern int cmd_check(int argc, const char **argv);
 extern int cmd_orc(int argc, const char **argv);
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 479196aeb409..ac743a1d53ab 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -31,6 +31,7 @@
 struct alternative {
 	struct list_head list;
 	struct instruction *insn;
+	bool skip_orig;
 };
 
 const char *objname;
@@ -105,29 +106,6 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
 	     insn = next_insn_same_sec(file, insn))
 
 /*
- * Check if the function has been manually whitelisted with the
- * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted
- * due to its use of a context switching instruction.
- */
-static bool ignore_func(struct objtool_file *file, struct symbol *func)
-{
-	struct rela *rela;
-
-	/* check for STACK_FRAME_NON_STANDARD */
-	if (file->whitelist && file->whitelist->rela)
-		list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) {
-			if (rela->sym->type == STT_SECTION &&
-			    rela->sym->sec == func->sec &&
-			    rela->addend == func->offset)
-				return true;
-			if (rela->sym->type == STT_FUNC && rela->sym == func)
-				return true;
-		}
-
-	return false;
-}
-
-/*
  * This checks to see if the given function is a "noreturn" function.
  *
  * For global functions which are outside the scope of this object file, we
@@ -437,18 +415,107 @@ static void add_ignores(struct objtool_file *file)
 	struct instruction *insn;
 	struct section *sec;
 	struct symbol *func;
+	struct rela *rela;
 
-	for_each_sec(file, sec) {
-		list_for_each_entry(func, &sec->symbol_list, list) {
-			if (func->type != STT_FUNC)
-				continue;
+	sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard");
+	if (!sec)
+		return;
 
-			if (!ignore_func(file, func))
+	list_for_each_entry(rela, &sec->rela_list, list) {
+		switch (rela->sym->type) {
+		case STT_FUNC:
+			func = rela->sym;
+			break;
+
+		case STT_SECTION:
+			func = find_symbol_by_offset(rela->sym->sec, rela->addend);
+			if (!func || func->type != STT_FUNC)
 				continue;
+			break;
 
-			func_for_each_insn_all(file, func, insn)
-				insn->ignore = true;
+		default:
+			WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type);
+			continue;
 		}
+
+		func_for_each_insn_all(file, func, insn)
+			insn->ignore = true;
+	}
+}
+
+/*
+ * This is a whitelist of functions that is allowed to be called with AC set.
+ * The list is meant to be minimal and only contains compiler instrumentation
+ * ABI and a few functions used to implement *_{to,from}_user() functions.
+ *
+ * These functions must not directly change AC, but may PUSHF/POPF.
+ */
+static const char *uaccess_safe_builtin[] = {
+	/* KASAN */
+	"kasan_report",
+	"check_memory_region",
+	/* KASAN out-of-line */
+	"__asan_loadN_noabort",
+	"__asan_load1_noabort",
+	"__asan_load2_noabort",
+	"__asan_load4_noabort",
+	"__asan_load8_noabort",
+	"__asan_load16_noabort",
+	"__asan_storeN_noabort",
+	"__asan_store1_noabort",
+	"__asan_store2_noabort",
+	"__asan_store4_noabort",
+	"__asan_store8_noabort",
+	"__asan_store16_noabort",
+	/* KASAN in-line */
+	"__asan_report_load_n_noabort",
+	"__asan_report_load1_noabort",
+	"__asan_report_load2_noabort",
+	"__asan_report_load4_noabort",
+	"__asan_report_load8_noabort",
+	"__asan_report_load16_noabort",
+	"__asan_report_store_n_noabort",
+	"__asan_report_store1_noabort",
+	"__asan_report_store2_noabort",
+	"__asan_report_store4_noabort",
+	"__asan_report_store8_noabort",
+	"__asan_report_store16_noabort",
+	/* KCOV */
+	"write_comp_data",
+	"__sanitizer_cov_trace_pc",
+	"__sanitizer_cov_trace_const_cmp1",
+	"__sanitizer_cov_trace_const_cmp2",
+	"__sanitizer_cov_trace_const_cmp4",
+	"__sanitizer_cov_trace_const_cmp8",
+	"__sanitizer_cov_trace_cmp1",
+	"__sanitizer_cov_trace_cmp2",
+	"__sanitizer_cov_trace_cmp4",
+	"__sanitizer_cov_trace_cmp8",
+	/* UBSAN */
+	"ubsan_type_mismatch_common",
+	"__ubsan_handle_type_mismatch",
+	"__ubsan_handle_type_mismatch_v1",
+	/* misc */
+	"csum_partial_copy_generic",
+	"__memcpy_mcsafe",
+	"ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
+	NULL
+};
+
+static void add_uaccess_safe(struct objtool_file *file)
+{
+	struct symbol *func;
+	const char **name;
+
+	if (!uaccess)
+		return;
+
+	for (name = uaccess_safe_builtin; *name; name++) {
+		func = find_symbol_by_name(file->elf, *name);
+		if (!func)
+			continue;
+
+		func->alias->uaccess_safe = true;
 	}
 }
 
@@ -458,13 +525,13 @@ static void add_ignores(struct objtool_file *file)
  * But it at least allows objtool to understand the control flow *around* the
  * retpoline.
  */
-static int add_nospec_ignores(struct objtool_file *file)
+static int add_ignore_alternatives(struct objtool_file *file)
 {
 	struct section *sec;
 	struct rela *rela;
 	struct instruction *insn;
 
-	sec = find_section_by_name(file->elf, ".rela.discard.nospec");
+	sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts");
 	if (!sec)
 		return 0;
 
@@ -476,7 +543,7 @@ static int add_nospec_ignores(struct objtool_file *file)
 
 		insn = find_insn(file, rela->sym->sec, rela->addend);
 		if (!insn) {
-			WARN("bad .discard.nospec entry");
+			WARN("bad .discard.ignore_alts entry");
 			return -1;
 		}
 
@@ -525,7 +592,8 @@ static int add_jump_destinations(struct objtool_file *file)
 			continue;
 		} else {
 			/* sibling call */
-			insn->jump_dest = 0;
+			insn->call_dest = rela->sym;
+			insn->jump_dest = NULL;
 			continue;
 		}
 
@@ -547,25 +615,38 @@ static int add_jump_destinations(struct objtool_file *file)
 		}
 
 		/*
-		 * For GCC 8+, create parent/child links for any cold
-		 * subfunctions.  This is _mostly_ redundant with a similar
-		 * initialization in read_symbols().
-		 *
-		 * If a function has aliases, we want the *first* such function
-		 * in the symbol table to be the subfunction's parent.  In that
-		 * case we overwrite the initialization done in read_symbols().
-		 *
-		 * However this code can't completely replace the
-		 * read_symbols() code because this doesn't detect the case
-		 * where the parent function's only reference to a subfunction
-		 * is through a switch table.
+		 * Cross-function jump.
 		 */
 		if (insn->func && insn->jump_dest->func &&
-		    insn->func != insn->jump_dest->func &&
-		    !strstr(insn->func->name, ".cold.") &&
-		    strstr(insn->jump_dest->func->name, ".cold.")) {
-			insn->func->cfunc = insn->jump_dest->func;
-			insn->jump_dest->func->pfunc = insn->func;
+		    insn->func != insn->jump_dest->func) {
+
+			/*
+			 * For GCC 8+, create parent/child links for any cold
+			 * subfunctions.  This is _mostly_ redundant with a
+			 * similar initialization in read_symbols().
+			 *
+			 * If a function has aliases, we want the *first* such
+			 * function in the symbol table to be the subfunction's
+			 * parent.  In that case we overwrite the
+			 * initialization done in read_symbols().
+			 *
+			 * However this code can't completely replace the
+			 * read_symbols() code because this doesn't detect the
+			 * case where the parent function's only reference to a
+			 * subfunction is through a switch table.
+			 */
+			if (!strstr(insn->func->name, ".cold.") &&
+			    strstr(insn->jump_dest->func->name, ".cold.")) {
+				insn->func->cfunc = insn->jump_dest->func;
+				insn->jump_dest->func->pfunc = insn->func;
+
+			} else if (insn->jump_dest->func->pfunc != insn->func->pfunc &&
+				   insn->jump_dest->offset == insn->jump_dest->func->offset) {
+
+				/* sibling class */
+				insn->call_dest = insn->jump_dest->func;
+				insn->jump_dest = NULL;
+			}
 		}
 	}
 
@@ -634,9 +715,6 @@ static int add_call_destinations(struct objtool_file *file)
  *    conditionally jumps to the _end_ of the entry.  We have to modify these
  *    jumps' destinations to point back to .text rather than the end of the
  *    entry in .altinstr_replacement.
- *
- * 4. It has been requested that we don't validate the !POPCNT feature path
- *    which is a "very very small percentage of machines".
  */
 static int handle_group_alt(struct objtool_file *file,
 			    struct special_alt *special_alt,
@@ -652,9 +730,6 @@ static int handle_group_alt(struct objtool_file *file,
 		if (insn->offset >= special_alt->orig_off + special_alt->orig_len)
 			break;
 
-		if (special_alt->skip_orig)
-			insn->type = INSN_NOP;
-
 		insn->alt_group = true;
 		last_orig_insn = insn;
 	}
@@ -696,6 +771,7 @@ static int handle_group_alt(struct objtool_file *file,
 		last_new_insn = insn;
 
 		insn->ignore = orig_insn->ignore_alts;
+		insn->func = orig_insn->func;
 
 		if (insn->type != INSN_JUMP_CONDITIONAL &&
 		    insn->type != INSN_JUMP_UNCONDITIONAL)
@@ -818,6 +894,8 @@ static int add_special_section_alts(struct objtool_file *file)
 		}
 
 		alt->insn = new_insn;
+		alt->skip_orig = special_alt->skip_orig;
+		orig_insn->ignore_alts |= special_alt->skip_alt;
 		list_add_tail(&alt->list, &orig_insn->alts);
 
 		list_del(&special_alt->list);
@@ -1239,8 +1317,9 @@ static int decode_sections(struct objtool_file *file)
 		return ret;
 
 	add_ignores(file);
+	add_uaccess_safe(file);
 
-	ret = add_nospec_ignores(file);
+	ret = add_ignore_alternatives(file);
 	if (ret)
 		return ret;
 
@@ -1320,11 +1399,11 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s
 		return 0;
 
 	/* push */
-	if (op->dest.type == OP_DEST_PUSH)
+	if (op->dest.type == OP_DEST_PUSH || op->dest.type == OP_DEST_PUSHF)
 		cfa->offset += 8;
 
 	/* pop */
-	if (op->src.type == OP_SRC_POP)
+	if (op->src.type == OP_SRC_POP || op->src.type == OP_SRC_POPF)
 		cfa->offset -= 8;
 
 	/* add immediate to sp */
@@ -1581,6 +1660,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 			break;
 
 		case OP_SRC_POP:
+		case OP_SRC_POPF:
 			if (!state->drap && op->dest.type == OP_DEST_REG &&
 			    op->dest.reg == cfa->base) {
 
@@ -1645,6 +1725,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		break;
 
 	case OP_DEST_PUSH:
+	case OP_DEST_PUSHF:
 		state->stack_size += 8;
 		if (cfa->base == CFI_SP)
 			cfa->offset += 8;
@@ -1735,7 +1816,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		break;
 
 	case OP_DEST_MEM:
-		if (op->src.type != OP_SRC_POP) {
+		if (op->src.type != OP_SRC_POP && op->src.type != OP_SRC_POPF) {
 			WARN_FUNC("unknown stack-related memory operation",
 				  insn->sec, insn->offset);
 			return -1;
@@ -1799,6 +1880,50 @@ static bool insn_state_match(struct instruction *insn, struct insn_state *state)
 	return false;
 }
 
+static inline bool func_uaccess_safe(struct symbol *func)
+{
+	if (func)
+		return func->alias->uaccess_safe;
+
+	return false;
+}
+
+static inline const char *insn_dest_name(struct instruction *insn)
+{
+	if (insn->call_dest)
+		return insn->call_dest->name;
+
+	return "{dynamic}";
+}
+
+static int validate_call(struct instruction *insn, struct insn_state *state)
+{
+	if (state->uaccess && !func_uaccess_safe(insn->call_dest)) {
+		WARN_FUNC("call to %s() with UACCESS enabled",
+				insn->sec, insn->offset, insn_dest_name(insn));
+		return 1;
+	}
+
+	if (state->df) {
+		WARN_FUNC("call to %s() with DF set",
+				insn->sec, insn->offset, insn_dest_name(insn));
+		return 1;
+	}
+
+	return 0;
+}
+
+static int validate_sibling_call(struct instruction *insn, struct insn_state *state)
+{
+	if (has_modified_stack_frame(state)) {
+		WARN_FUNC("sibling call from callable instruction with modified stack frame",
+				insn->sec, insn->offset);
+		return 1;
+	}
+
+	return validate_call(insn, state);
+}
+
 /*
  * Follow the branch starting at the given instruction, and recursively follow
  * any other branches (jumps).  Meanwhile, track the frame pointer state at
@@ -1844,7 +1969,9 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			if (!insn->hint && !insn_state_match(insn, &state))
 				return 1;
 
-			return 0;
+			/* If we were here with AC=0, but now have AC=1, go again */
+			if (insn->state.uaccess || !state.uaccess)
+				return 0;
 		}
 
 		if (insn->hint) {
@@ -1893,16 +2020,42 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 		insn->visited = true;
 
 		if (!insn->ignore_alts) {
+			bool skip_orig = false;
+
 			list_for_each_entry(alt, &insn->alts, list) {
+				if (alt->skip_orig)
+					skip_orig = true;
+
 				ret = validate_branch(file, alt->insn, state);
-				if (ret)
-					return 1;
+				if (ret) {
+					if (backtrace)
+						BT_FUNC("(alt)", insn);
+					return ret;
+				}
 			}
+
+			if (skip_orig)
+				return 0;
 		}
 
 		switch (insn->type) {
 
 		case INSN_RETURN:
+			if (state.uaccess && !func_uaccess_safe(func)) {
+				WARN_FUNC("return with UACCESS enabled", sec, insn->offset);
+				return 1;
+			}
+
+			if (!state.uaccess && func_uaccess_safe(func)) {
+				WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", sec, insn->offset);
+				return 1;
+			}
+
+			if (state.df) {
+				WARN_FUNC("return with DF set", sec, insn->offset);
+				return 1;
+			}
+
 			if (func && has_modified_stack_frame(&state)) {
 				WARN_FUNC("return with modified stack frame",
 					  sec, insn->offset);
@@ -1918,17 +2071,22 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			return 0;
 
 		case INSN_CALL:
-			if (is_fentry_call(insn))
-				break;
+		case INSN_CALL_DYNAMIC:
+			ret = validate_call(insn, &state);
+			if (ret)
+				return ret;
 
-			ret = dead_end_function(file, insn->call_dest);
-			if (ret == 1)
-				return 0;
-			if (ret == -1)
-				return 1;
+			if (insn->type == INSN_CALL) {
+				if (is_fentry_call(insn))
+					break;
+
+				ret = dead_end_function(file, insn->call_dest);
+				if (ret == 1)
+					return 0;
+				if (ret == -1)
+					return 1;
+			}
 
-			/* fallthrough */
-		case INSN_CALL_DYNAMIC:
 			if (!no_fp && func && !has_valid_stack_frame(&state)) {
 				WARN_FUNC("call without frame pointer save/setup",
 					  sec, insn->offset);
@@ -1938,18 +2096,21 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
 		case INSN_JUMP_CONDITIONAL:
 		case INSN_JUMP_UNCONDITIONAL:
-			if (insn->jump_dest &&
-			    (!func || !insn->jump_dest->func ||
-			     insn->jump_dest->func->pfunc == func)) {
-				ret = validate_branch(file, insn->jump_dest,
-						      state);
+			if (func && !insn->jump_dest) {
+				ret = validate_sibling_call(insn, &state);
 				if (ret)
-					return 1;
+					return ret;
 
-			} else if (func && has_modified_stack_frame(&state)) {
-				WARN_FUNC("sibling call from callable instruction with modified stack frame",
-					  sec, insn->offset);
-				return 1;
+			} else if (insn->jump_dest &&
+				   (!func || !insn->jump_dest->func ||
+				    insn->jump_dest->func->pfunc == func)) {
+				ret = validate_branch(file, insn->jump_dest,
+						      state);
+				if (ret) {
+					if (backtrace)
+						BT_FUNC("(branch)", insn);
+					return ret;
+				}
 			}
 
 			if (insn->type == INSN_JUMP_UNCONDITIONAL)
@@ -1958,11 +2119,10 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			break;
 
 		case INSN_JUMP_DYNAMIC:
-			if (func && list_empty(&insn->alts) &&
-			    has_modified_stack_frame(&state)) {
-				WARN_FUNC("sibling call from callable instruction with modified stack frame",
-					  sec, insn->offset);
-				return 1;
+			if (func && list_empty(&insn->alts)) {
+				ret = validate_sibling_call(insn, &state);
+				if (ret)
+					return ret;
 			}
 
 			return 0;
@@ -1979,6 +2139,63 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			if (update_insn_state(insn, &state))
 				return 1;
 
+			if (insn->stack_op.dest.type == OP_DEST_PUSHF) {
+				if (!state.uaccess_stack) {
+					state.uaccess_stack = 1;
+				} else if (state.uaccess_stack >> 31) {
+					WARN_FUNC("PUSHF stack exhausted", sec, insn->offset);
+					return 1;
+				}
+				state.uaccess_stack <<= 1;
+				state.uaccess_stack  |= state.uaccess;
+			}
+
+			if (insn->stack_op.src.type == OP_SRC_POPF) {
+				if (state.uaccess_stack) {
+					state.uaccess = state.uaccess_stack & 1;
+					state.uaccess_stack >>= 1;
+					if (state.uaccess_stack == 1)
+						state.uaccess_stack = 0;
+				}
+			}
+
+			break;
+
+		case INSN_STAC:
+			if (state.uaccess) {
+				WARN_FUNC("recursive UACCESS enable", sec, insn->offset);
+				return 1;
+			}
+
+			state.uaccess = true;
+			break;
+
+		case INSN_CLAC:
+			if (!state.uaccess && insn->func) {
+				WARN_FUNC("redundant UACCESS disable", sec, insn->offset);
+				return 1;
+			}
+
+			if (func_uaccess_safe(func) && !state.uaccess_stack) {
+				WARN_FUNC("UACCESS-safe disables UACCESS", sec, insn->offset);
+				return 1;
+			}
+
+			state.uaccess = false;
+			break;
+
+		case INSN_STD:
+			if (state.df)
+				WARN_FUNC("recursive STD", sec, insn->offset);
+
+			state.df = true;
+			break;
+
+		case INSN_CLD:
+			if (!state.df && insn->func)
+				WARN_FUNC("redundant CLD", sec, insn->offset);
+
+			state.df = false;
 			break;
 
 		default:
@@ -2015,6 +2232,8 @@ static int validate_unwind_hints(struct objtool_file *file)
 	for_each_insn(file, insn) {
 		if (insn->hint && !insn->visited) {
 			ret = validate_branch(file, insn, state);
+			if (ret && backtrace)
+				BT_FUNC("<=== (hint)", insn);
 			warnings += ret;
 		}
 	}
@@ -2142,7 +2361,11 @@ static int validate_functions(struct objtool_file *file)
 			if (!insn || insn->ignore)
 				continue;
 
+			state.uaccess = func->alias->uaccess_safe;
+
 			ret = validate_branch(file, insn, state);
+			if (ret && backtrace)
+				BT_FUNC("<=== (func)", insn);
 			warnings += ret;
 		}
 	}
@@ -2199,7 +2422,6 @@ int check(const char *_objname, bool orc)
 
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
-	file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
 	file.c_file = find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index e6e8a655b556..71e54f97dbcd 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,8 @@ struct insn_state {
 	int stack_size;
 	unsigned char type;
 	bool bp_scratch;
-	bool drap, end;
+	bool drap, end, uaccess, df;
+	unsigned int uaccess_stack;
 	int drap_reg, drap_offset;
 	struct cfi_reg vals[CFI_NUM_REGS];
 };
@@ -60,7 +61,6 @@ struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 16);
-	struct section *whitelist;
 	bool ignore_unreachables, c_file, hints, rodata;
 };
 
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index b8f3cca8e58b..dd198d53387d 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -219,7 +219,7 @@ static int read_sections(struct elf *elf)
 static int read_symbols(struct elf *elf)
 {
 	struct section *symtab, *sec;
-	struct symbol *sym, *pfunc;
+	struct symbol *sym, *pfunc, *alias;
 	struct list_head *entry, *tmp;
 	int symbols_nr, i;
 	char *coldstr;
@@ -239,6 +239,7 @@ static int read_symbols(struct elf *elf)
 			return -1;
 		}
 		memset(sym, 0, sizeof(*sym));
+		alias = sym;
 
 		sym->idx = i;
 
@@ -288,11 +289,17 @@ static int read_symbols(struct elf *elf)
 				break;
 			}
 
-			if (sym->offset == s->offset && sym->len >= s->len) {
-				entry = tmp;
-				break;
+			if (sym->offset == s->offset) {
+				if (sym->len == s->len && alias == sym)
+					alias = s;
+
+				if (sym->len >= s->len) {
+					entry = tmp;
+					break;
+				}
 			}
 		}
+		sym->alias = alias;
 		list_add(&sym->list, entry);
 		hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
 	}
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index bc97ed86b9cd..2cc2ed49322d 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -61,7 +61,8 @@ struct symbol {
 	unsigned char bind, type;
 	unsigned long offset;
 	unsigned int len;
-	struct symbol *pfunc, *cfunc;
+	struct symbol *pfunc, *cfunc, *alias;
+	bool uaccess_safe;
 };
 
 struct rela {
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 50af4e1274b3..4e50563d87c6 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -23,6 +23,7 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include "builtin.h"
 #include "special.h"
 #include "warn.h"
 
@@ -42,6 +43,7 @@
 #define ALT_NEW_LEN_OFFSET	11
 
 #define X86_FEATURE_POPCNT (4*32+23)
+#define X86_FEATURE_SMAP   (9*32+20)
 
 struct special_entry {
 	const char *sec;
@@ -110,6 +112,22 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 		 */
 		if (feature == X86_FEATURE_POPCNT)
 			alt->skip_orig = true;
+
+		/*
+		 * If UACCESS validation is enabled; force that alternative;
+		 * otherwise force it the other way.
+		 *
+		 * What we want to avoid is having both the original and the
+		 * alternative code flow at the same time, in that case we can
+		 * find paths that see the STAC but take the NOP instead of
+		 * CLAC and the other way around.
+		 */
+		if (feature == X86_FEATURE_SMAP) {
+			if (uaccess)
+				alt->skip_orig = true;
+			else
+				alt->skip_alt = true;
+		}
 	}
 
 	orig_rela = find_rela_by_dest(sec, offset + entry->orig);
diff --git a/tools/objtool/special.h b/tools/objtool/special.h
index fad1d092f679..d5c062e718ef 100644
--- a/tools/objtool/special.h
+++ b/tools/objtool/special.h
@@ -26,6 +26,7 @@ struct special_alt {
 
 	bool group;
 	bool skip_orig;
+	bool skip_alt;
 	bool jump_or_nop;
 
 	struct section *orig_sec;
diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h
index afd9f7a05f6d..f4fbb972b611 100644
--- a/tools/objtool/warn.h
+++ b/tools/objtool/warn.h
@@ -64,6 +64,14 @@ static inline char *offstr(struct section *sec, unsigned long offset)
 	free(_str);					\
 })
 
+#define BT_FUNC(format, insn, ...)			\
+({							\
+	struct instruction *_insn = (insn);		\
+	char *_str = offstr(_insn->sec, _insn->offset); \
+	WARN("  %s: " format, _str, ##__VA_ARGS__);	\
+	free(_str);					\
+})
+
 #define WARN_ELF(format, ...)				\
 	WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1))
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8fe4dffcadd0..58986f4cc190 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -459,6 +459,25 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo
   node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
   cpu  - thread affinity mask is set to cpu of the processed mmap buffer
 
+--mmap-flush=number::
+
+Specify minimal number of bytes that is extracted from mmap data pages and
+processed for output. One can specify the number using B/K/M/G suffixes.
+
+The maximal allowed value is a quarter of the size of mmaped data pages.
+
+The default option value is 1 byte which means that every time that the output
+writing thread finds some new data in the mmaped buffer the data is extracted,
+possibly compressed (-z) and written to the output, perf.data or pipe.
+
+Larger data chunks are compressed more effectively in comparison to smaller
+chunks so extraction of larger chunks from the mmap data pages is preferable
+from the perspective of output size reduction.
+
+Also at some cases executing less output write syscalls with bigger data size
+can take less time than executing more output write syscalls with smaller data
+size thus lowering runtime profiling overhead.
+
 --all-kernel::
 Configure all used events to run in kernel space.
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fe3f97e342fa..0c52a01dc759 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -152,6 +152,13 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
+ifdef LIBZSTD_DIR
+  LIBZSTD_CFLAGS  := -I$(LIBZSTD_DIR)/lib
+  LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib
+endif
+FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
+
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(SRCARCH)/Makefile
@@ -227,7 +234,7 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
-FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
@@ -787,6 +794,19 @@ ifndef NO_LZMA
   endif
 endif
 
+ifndef NO_LIBZSTD
+  ifeq ($(feature-libzstd), 1)
+    CFLAGS += -DHAVE_ZSTD_SUPPORT
+    CFLAGS += $(LIBZSTD_CFLAGS)
+    LDFLAGS += $(LIBZSTD_LDFLAGS)
+    EXTLIBS += -lzstd
+    $(call detected,CONFIG_ZSTD)
+  else
+    msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR);
+    NO_LIBZSTD := 1
+  endif
+endif
+
 ifndef NO_BACKTRACE
   ifeq ($(feature-backtrace), 1)
     CFLAGS += -DHAVE_BACKTRACE_SUPPORT
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e8c9f77e9010..c706548d5b10 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -108,6 +108,9 @@ include ../scripts/utilities.mak
 # streaming for record mode. Currently Posix AIO trace streaming is
 # supported only when linking with glibc.
 #
+# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
+# trace compression in record mode.
+#
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 98ad783efc69..a7784554a80d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -39,6 +39,10 @@
 #include <numa.h>
 #include <numaif.h>
 
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
 /*
  * Regular printout to the terminal, supressed if -q is specified:
  */
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fa520f4b8095..b80eee455111 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1975,7 +1975,7 @@ int cmd_kmem(int argc, const char **argv)
 			goto out_delete;
 		}
 
-		kmem_page_size = tep_get_page_size(evsel->tp_format->pevent);
+		kmem_page_size = tep_get_page_size(evsel->tp_format->tep);
 		symbol_conf.use_callchain = true;
 	}
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index a8394b4f1167..e0312a1c4792 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv)
 			print_symbol_events(NULL, PERF_TYPE_HARDWARE,
 					event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 		else if (strcmp(argv[i], "sw") == 0 ||
-			 strcmp(argv[i], "software") == 0)
+			 strcmp(argv[i], "software") == 0) {
 			print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
 					event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
-		else if (strcmp(argv[i], "cache") == 0 ||
+			print_tool_events(NULL, raw_dump);
+		} else if (strcmp(argv[i], "cache") == 0 ||
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
@@ -113,6 +114,7 @@ int cmd_list(int argc, const char **argv)
 					    event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 			print_symbol_events(s, PERF_TYPE_SOFTWARE,
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+			print_tool_events(s, raw_dump);
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
 						long_desc_flag,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e2d953d4bc5..c5e10552776a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -337,6 +337,41 @@ static int record__aio_enabled(struct record *rec)
 	return rec->opts.nr_cblocks > 0;
 }
 
+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+				    const char *str,
+				    int unset)
+{
+	int flush_max;
+	struct record_opts *opts = (struct record_opts *)opt->value;
+	static struct parse_tag tags[] = {
+			{ .tag  = 'B', .mult = 1       },
+			{ .tag  = 'K', .mult = 1 << 10 },
+			{ .tag  = 'M', .mult = 1 << 20 },
+			{ .tag  = 'G', .mult = 1 << 30 },
+			{ .tag  = 0 },
+	};
+
+	if (unset)
+		return 0;
+
+	if (str) {
+		opts->mmap_flush = parse_tag_value(str, tags);
+		if (opts->mmap_flush == (int)-1)
+			opts->mmap_flush = strtol(str, NULL, 0);
+	}
+
+	if (!opts->mmap_flush)
+		opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+	flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+	flush_max /= 4;
+	if (opts->mmap_flush > flush_max)
+		opts->mmap_flush = flush_max;
+
+	return 0;
+}
+
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -546,7 +581,8 @@ static int record__mmap_evlist(struct record *rec,
 	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode,
-				 opts->nr_cblocks, opts->affinity) < 0) {
+				 opts->nr_cblocks, opts->affinity,
+				 opts->mmap_flush) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
@@ -736,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
 }
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
-				    bool overwrite)
+				    bool overwrite, bool synch)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
@@ -759,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		off = record__aio_get_pos(trace_fd);
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
+		u64 flush = 0;
 		struct perf_mmap *map = &maps[i];
 
 		if (map->base) {
 			record__adjust_affinity(rec, map);
+			if (synch) {
+				flush = map->flush;
+				map->flush = 1;
+			}
 			if (!record__aio_enabled(rec)) {
 				if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+					if (synch)
+						map->flush = flush;
 					rc = -1;
 					goto out;
 				}
@@ -777,10 +820,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 				idx = record__aio_sync(map, false);
 				if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
 					record__aio_set_pos(trace_fd, off);
+					if (synch)
+						map->flush = flush;
 					rc = -1;
 					goto out;
 				}
 			}
+			if (synch)
+				map->flush = flush;
 		}
 
 		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
@@ -806,15 +853,15 @@ out:
 	return rc;
 }
 
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_all(struct record *rec, bool synch)
 {
 	int err;
 
-	err = record__mmap_read_evlist(rec, rec->evlist, false);
+	err = record__mmap_read_evlist(rec, rec->evlist, false, synch);
 	if (err)
 		return err;
 
-	return record__mmap_read_evlist(rec, rec->evlist, true);
+	return record__mmap_read_evlist(rec, rec->evlist, true, synch);
 }
 
 static void record__init_features(struct record *rec)
@@ -1340,7 +1387,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		if (trigger_is_hit(&switch_output_trigger) || done || draining)
 			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
 
-		if (record__mmap_read_all(rec) < 0) {
+		if (record__mmap_read_all(rec, false) < 0) {
 			trigger_error(&auxtrace_snapshot_trigger);
 			trigger_error(&switch_output_trigger);
 			err = -1;
@@ -1441,6 +1488,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		record__synthesize_workload(rec, true);
 
 out_child:
+	record__mmap_read_all(rec, true);
 	record__aio_mmap_read_sync(rec);
 
 	if (forks) {
@@ -1846,6 +1894,7 @@ static struct record record = {
 			.uses_mmap   = true,
 			.default_per_cpu = true,
 		},
+		.mmap_flush          = MMAP_FLUSH_DEFAULT,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -1912,6 +1961,9 @@ static struct option __record_options[] = {
 	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
 		     "number of mmap data pages and AUX area tracing mmap pages",
 		     record__parse_mmap_pages),
+	OPT_CALLBACK(0, "mmap-flush", &record.opts, "number",
+		     "Minimal number of bytes that is extracted from mmap data pages (default: 1)",
+		     record__mmap_flush_parse),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
 	OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
@@ -2224,6 +2276,7 @@ int cmd_record(int argc, const char **argv)
 		pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
 
 	pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+	pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);
 
 	err = __cmd_record(&record, argc, argv);
 out:
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c3625ec374e0..a3c060878faa 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
 					   process_synthesized_event, NULL);
 }
 
+static int read_single_counter(struct perf_evsel *counter, int cpu,
+			       int thread, struct timespec *rs)
+{
+	if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
+		u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
+		struct perf_counts_values *count =
+			perf_counts(counter->counts, cpu, thread);
+		count->ena = count->run = val;
+		count->val = val;
+		return 0;
+	}
+	return perf_evsel__read_counter(counter, cpu, thread);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
  */
-static int read_counter(struct perf_evsel *counter)
+static int read_counter(struct perf_evsel *counter, struct timespec *rs)
 {
 	int nthreads = thread_map__nr(evsel_list->threads);
 	int ncpus, cpu, thread;
@@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter)
 			 * (via perf_evsel__read_counter) and sets threir count->loaded.
 			 */
 			if (!count->loaded &&
-			    perf_evsel__read_counter(counter, cpu, thread)) {
+			    read_single_counter(counter, cpu, thread, rs)) {
 				counter->counts->scaled = -1;
 				perf_counts(counter->counts, cpu, thread)->ena = 0;
 				perf_counts(counter->counts, cpu, thread)->run = 0;
@@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void read_counters(void)
+static void read_counters(struct timespec *rs)
 {
 	struct perf_evsel *counter;
 	int ret;
 
 	evlist__for_each_entry(evsel_list, counter) {
-		ret = read_counter(counter);
+		ret = read_counter(counter, rs);
 		if (ret)
 			pr_debug("failed to read counter %s\n", counter->name);
 
@@ -323,11 +337,11 @@ static void process_interval(void)
 {
 	struct timespec ts, rs;
 
-	read_counters();
-
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 
+	read_counters(&rs);
+
 	if (STAT_RECORD) {
 		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
 			pr_err("failed to write stat round event\n");
@@ -593,7 +607,7 @@ try_again:
 	 * avoid arbitrary skew, we must read all counters before closing any
 	 * group leaders.
 	 */
-	read_counters();
+	read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
 	perf_evlist__close(evsel_list);
 
 	return WEXITSTATUS(status);
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 50df168be326..f470144d1a70 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -78,6 +78,8 @@ static void library_status(void)
 	STATUS(HAVE_LZMA_SUPPORT, lzma);
 	STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid);
 	STATUS(HAVE_LIBBPF_SUPPORT, bpf);
+	STATUS(HAVE_AIO_SUPPORT, aio);
+	STATUS(HAVE_ZSTD_SUPPORT, zstd);
 }
 
 int cmd_version(int argc, const char **argv)
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index f9b2161e1ca4..2422894a8194 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -15,6 +15,7 @@
  */
 
 #include <unistd.h>
+#include <linux/limits.h>
 #include <pid_filter.h>
 
 /* bpf-output associated map */
@@ -41,32 +42,110 @@ struct syscall_exit_args {
 struct augmented_filename {
 	unsigned int	size;
 	int		reserved;
-	char		value[256];
+	char		value[PATH_MAX];
 };
 
-#define SYS_OPEN 2
-#define SYS_ACCESS 21
-#define SYS_OPENAT 257
+/* syscalls where the first arg is a string */
+#define SYS_OPEN                 2
+#define SYS_STAT                 4
+#define SYS_LSTAT                6
+#define SYS_ACCESS              21
+#define SYS_EXECVE              59
+#define SYS_TRUNCATE            76
+#define SYS_CHDIR               80
+#define SYS_RENAME              82
+#define SYS_MKDIR               83
+#define SYS_RMDIR               84
+#define SYS_CREAT               85
+#define SYS_LINK                86
+#define SYS_UNLINK              87
+#define SYS_SYMLINK             88
+#define SYS_READLINK            89
+#define SYS_CHMOD               90
+#define SYS_CHOWN               92
+#define SYS_LCHOWN              94
+#define SYS_MKNOD              133
+#define SYS_STATFS             137
+#define SYS_PIVOT_ROOT         155
+#define SYS_CHROOT             161
+#define SYS_ACCT               163
+#define SYS_SWAPON             167
+#define SYS_SWAPOFF            168
+#define SYS_DELETE_MODULE      176
+#define SYS_SETXATTR           188
+#define SYS_LSETXATTR          189
+#define SYS_GETXATTR           191
+#define SYS_LGETXATTR          192
+#define SYS_LISTXATTR          194
+#define SYS_LLISTXATTR         195
+#define SYS_REMOVEXATTR        197
+#define SYS_LREMOVEXATTR       198
+#define SYS_MQ_OPEN            240
+#define SYS_MQ_UNLINK          241
+#define SYS_ADD_KEY            248
+#define SYS_REQUEST_KEY        249
+#define SYS_SYMLINKAT          266
+#define SYS_MEMFD_CREATE       319
+
+/* syscalls where the first arg is a string */
+
+#define SYS_PWRITE64            18
+#define SYS_EXECVE              59
+#define SYS_RENAME              82
+#define SYS_QUOTACTL           179
+#define SYS_FSETXATTR          190
+#define SYS_FGETXATTR          193
+#define SYS_FREMOVEXATTR       199
+#define SYS_MQ_TIMEDSEND       242
+#define SYS_REQUEST_KEY        249
+#define SYS_INOTIFY_ADD_WATCH  254
+#define SYS_OPENAT             257
+#define SYS_MKDIRAT            258
+#define SYS_MKNODAT            259
+#define SYS_FCHOWNAT           260
+#define SYS_FUTIMESAT          261
+#define SYS_NEWFSTATAT         262
+#define SYS_UNLINKAT           263
+#define SYS_RENAMEAT           264
+#define SYS_LINKAT             265
+#define SYS_READLINKAT         267
+#define SYS_FCHMODAT           268
+#define SYS_FACCESSAT          269
+#define SYS_UTIMENSAT          280
+#define SYS_NAME_TO_HANDLE_AT  303
+#define SYS_FINIT_MODULE       313
+#define SYS_RENAMEAT2          316
+#define SYS_EXECVEAT           322
+#define SYS_STATX              332
 
 pid_filter(pids_filtered);
 
+struct augmented_args_filename {
+       struct syscall_enter_args args;
+       struct augmented_filename filename;
+};
+
+bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
+
 SEC("raw_syscalls:sys_enter")
 int sys_enter(struct syscall_enter_args *args)
 {
-	struct {
-		struct syscall_enter_args args;
-		struct augmented_filename filename;
-	} augmented_args;
-	struct syscall *syscall;
-	unsigned int len = sizeof(augmented_args);
+	struct augmented_args_filename *augmented_args;
+	unsigned int len = sizeof(*augmented_args);
 	const void *filename_arg = NULL;
+	struct syscall *syscall;
+	int key = 0;
+
+        augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key);
+        if (augmented_args == NULL)
+                return 1;
 
 	if (pid_filter__has(&pids_filtered, getpid()))
 		return 0;
 
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
 
-	syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
+	syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr);
 	if (syscall == NULL || !syscall->enabled)
 		return 0;
 	/*
@@ -109,30 +188,105 @@ int sys_enter(struct syscall_enter_args *args)
 	 *
 	 * 	 after the ctx memory access to prevent their down stream merging.
 	 */
-	switch (augmented_args.args.syscall_nr) {
+	/*
+	 * This table of what args are strings will be provided by userspace,
+	 * in the syscalls map, i.e. we will already have to do the lookup to
+	 * see if this specific syscall is filtered, so we can as well get more
+	 * info about what syscall args are strings or pointers, and how many
+	 * bytes to copy, per arg, etc.
+	 *
+	 * For now hard code it, till we have all the basic mechanisms in place
+	 * to automate everything and make the kernel part be completely driven
+	 * by information obtained in userspace for each kernel version and
+	 * processor architecture, making the kernel part the same no matter what
+	 * kernel version or processor architecture it runs on.
+	 */
+	switch (augmented_args->args.syscall_nr) {
+	case SYS_ACCT:
+	case SYS_ADD_KEY:
+	case SYS_CHDIR:
+	case SYS_CHMOD:
+	case SYS_CHOWN:
+	case SYS_CHROOT:
+	case SYS_CREAT:
+	case SYS_DELETE_MODULE:
+	case SYS_EXECVE:
+	case SYS_GETXATTR:
+	case SYS_LCHOWN:
+	case SYS_LGETXATTR:
+	case SYS_LINK:
+	case SYS_LISTXATTR:
+	case SYS_LLISTXATTR:
+	case SYS_LREMOVEXATTR:
+	case SYS_LSETXATTR:
+	case SYS_LSTAT:
+	case SYS_MEMFD_CREATE:
+	case SYS_MKDIR:
+	case SYS_MKNOD:
+	case SYS_MQ_OPEN:
+	case SYS_MQ_UNLINK:
+	case SYS_PIVOT_ROOT:
+	case SYS_READLINK:
+	case SYS_REMOVEXATTR:
+	case SYS_RENAME:
+	case SYS_REQUEST_KEY:
+	case SYS_RMDIR:
+	case SYS_SETXATTR:
+	case SYS_STAT:
+	case SYS_STATFS:
+	case SYS_SWAPOFF:
+	case SYS_SWAPON:
+	case SYS_SYMLINK:
+	case SYS_SYMLINKAT:
+	case SYS_TRUNCATE:
+	case SYS_UNLINK:
 	case SYS_ACCESS:
 	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
 			__asm__ __volatile__("": : :"memory");
 			 break;
+	case SYS_EXECVEAT:
+	case SYS_FACCESSAT:
+	case SYS_FCHMODAT:
+	case SYS_FCHOWNAT:
+	case SYS_FGETXATTR:
+	case SYS_FINIT_MODULE:
+	case SYS_FREMOVEXATTR:
+	case SYS_FSETXATTR:
+	case SYS_FUTIMESAT:
+	case SYS_INOTIFY_ADD_WATCH:
+	case SYS_LINKAT:
+	case SYS_MKDIRAT:
+	case SYS_MKNODAT:
+	case SYS_MQ_TIMEDSEND:
+	case SYS_NAME_TO_HANDLE_AT:
+	case SYS_NEWFSTATAT:
+	case SYS_PWRITE64:
+	case SYS_QUOTACTL:
+	case SYS_READLINKAT:
+	case SYS_RENAMEAT:
+	case SYS_RENAMEAT2:
+	case SYS_STATX:
+	case SYS_UNLINKAT:
+	case SYS_UTIMENSAT:
 	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
 			 break;
 	}
 
 	if (filename_arg != NULL) {
-		augmented_args.filename.reserved = 0;
-		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
-							      sizeof(augmented_args.filename.value),
+		augmented_args->filename.reserved = 0;
+		augmented_args->filename.size = probe_read_str(&augmented_args->filename.value,
+							      sizeof(augmented_args->filename.value),
 							      filename_arg);
-		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
-			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
-			len &= sizeof(augmented_args.filename.value) - 1;
+		if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) {
+			len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size;
+			len &= sizeof(augmented_args->filename.value) - 1;
 		}
 	} else {
-		len = sizeof(augmented_args.args);
+		len = sizeof(augmented_args->args);
 	}
 
 	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
 }
 
 SEC("raw_syscalls:sys_exit")
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index c59743def8d3..369eae61068d 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -85,6 +85,7 @@ struct record_opts {
 	u64          clockid_res_ns;
 	int	     nr_cblocks;
 	int	     affinity;
+	int	     mmap_flush;
 };
 
 enum perf_affinity {
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index e7a3524b748f..68618152ea2c 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -4,7 +4,7 @@
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
-		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+		"PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
 		"Unit": "CPU-M-CF",
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json
index 935b7dcf067d..ef69540ab61d 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json
@@ -77,7 +77,7 @@
         "UMask": "0x1",
         "EventName": "UOPS.MS_CYCLES",
         "SampleAfterValue": "2000000",
-        "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ. ",
+        "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.",
         "CounterMask": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
index b2e681c78466..09c6de13de20 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
@@ -189,7 +189,7 @@
         "UMask": "0x8",
         "EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL",
         "SampleAfterValue": "200000",
-        "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect. "
+        "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect."
     },
     {
         "EventCode": "0x89",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index 00bfdb5c5acb..212b117a8ffb 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -1,164 +1,352 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
     },
     {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
index 0b080b0352d8..7938bf5689ab 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
@@ -56,10 +56,10 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
@@ -68,7 +68,7 @@
     {
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "RFO requests that hit L2 cache.",
@@ -77,7 +77,7 @@
     {
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
@@ -87,7 +87,7 @@
         "PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "EventName": "L2_RQSTS.L2_PF_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
@@ -433,7 +433,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x41",
@@ -445,7 +445,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x42",
@@ -771,2628 +771,2628 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010001 ",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that have any response type.",
+        "BriefDescription": "Counts demand data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020001 ",
+        "MSRValue": "0x0080020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020001 ",
+        "MSRValue": "0x0100020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020001 ",
+        "MSRValue": "0x0200020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020001 ",
+        "MSRValue": "0x0400020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020001 ",
+        "MSRValue": "0x1000020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020001 ",
+        "MSRValue": "0x3F80020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0001 ",
+        "MSRValue": "0x00803C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0001 ",
+        "MSRValue": "0x01003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0001 ",
+        "MSRValue": "0x02003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0001 ",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0001 ",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0001 ",
+        "MSRValue": "0x3F803C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010002 ",
+        "MSRValue": "0x0000010002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0002 ",
+        "MSRValue": "0x00803C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0002 ",
+        "MSRValue": "0x01003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0002 ",
+        "MSRValue": "0x02003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0002 ",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0002 ",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0002 ",
+        "MSRValue": "0x3F803C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010004 ",
+        "MSRValue": "0x0000010004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that have any response type.",
+        "BriefDescription": "Counts all demand code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020004 ",
+        "MSRValue": "0x0080020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020004 ",
+        "MSRValue": "0x0100020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020004 ",
+        "MSRValue": "0x0200020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020004 ",
+        "MSRValue": "0x0400020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020004 ",
+        "MSRValue": "0x1000020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020004 ",
+        "MSRValue": "0x3F80020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0004 ",
+        "MSRValue": "0x00803C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0004 ",
+        "MSRValue": "0x01003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0004 ",
+        "MSRValue": "0x02003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0004 ",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0004 ",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0004 ",
+        "MSRValue": "0x3F803C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive) have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010008 ",
+        "MSRValue": "0x0000010008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that have any response type.",
+        "BriefDescription": "Counts writebacks (modified to exclusive) have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020008 ",
+        "MSRValue": "0x0080020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020008 ",
+        "MSRValue": "0x0100020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020008 ",
+        "MSRValue": "0x0200020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020008 ",
+        "MSRValue": "0x0400020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020008 ",
+        "MSRValue": "0x1000020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020008 ",
+        "MSRValue": "0x3F80020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0008 ",
+        "MSRValue": "0x00803C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0008 ",
+        "MSRValue": "0x01003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0008 ",
+        "MSRValue": "0x02003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0008 ",
+        "MSRValue": "0x04003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0008 ",
+        "MSRValue": "0x10003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0008 ",
+        "MSRValue": "0x3F803C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010010 ",
+        "MSRValue": "0x0000010010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020010 ",
+        "MSRValue": "0x0080020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020010 ",
+        "MSRValue": "0x0100020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020010 ",
+        "MSRValue": "0x0200020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020010 ",
+        "MSRValue": "0x0400020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020010 ",
+        "MSRValue": "0x1000020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020010 ",
+        "MSRValue": "0x3F80020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0010 ",
+        "MSRValue": "0x00803C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0010 ",
+        "MSRValue": "0x01003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0010 ",
+        "MSRValue": "0x02003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0010 ",
+        "MSRValue": "0x04003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0010 ",
+        "MSRValue": "0x10003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0010 ",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010020 ",
+        "MSRValue": "0x0000010020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020020 ",
+        "MSRValue": "0x0080020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020020 ",
+        "MSRValue": "0x0100020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020020 ",
+        "MSRValue": "0x0200020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020020 ",
+        "MSRValue": "0x0400020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020020 ",
+        "MSRValue": "0x1000020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020020 ",
+        "MSRValue": "0x3F80020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0020 ",
+        "MSRValue": "0x00803C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0020 ",
+        "MSRValue": "0x01003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0020 ",
+        "MSRValue": "0x02003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0020 ",
+        "MSRValue": "0x04003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0020 ",
+        "MSRValue": "0x10003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0020 ",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010040 ",
+        "MSRValue": "0x0000010040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020040 ",
+        "MSRValue": "0x0080020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020040 ",
+        "MSRValue": "0x0100020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020040 ",
+        "MSRValue": "0x0200020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020040 ",
+        "MSRValue": "0x0400020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020040 ",
+        "MSRValue": "0x1000020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020040 ",
+        "MSRValue": "0x3F80020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0040 ",
+        "MSRValue": "0x00803C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0040 ",
+        "MSRValue": "0x01003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0040 ",
+        "MSRValue": "0x02003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0040 ",
+        "MSRValue": "0x04003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0040 ",
+        "MSRValue": "0x10003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0040 ",
+        "MSRValue": "0x3F803C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010080 ",
+        "MSRValue": "0x0000010080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020080 ",
+        "MSRValue": "0x0080020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020080 ",
+        "MSRValue": "0x0100020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020080 ",
+        "MSRValue": "0x0200020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020080 ",
+        "MSRValue": "0x0400020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020080 ",
+        "MSRValue": "0x1000020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020080 ",
+        "MSRValue": "0x3F80020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0080 ",
+        "MSRValue": "0x00803C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0080 ",
+        "MSRValue": "0x01003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0080 ",
+        "MSRValue": "0x02003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0080 ",
+        "MSRValue": "0x04003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0080 ",
+        "MSRValue": "0x10003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0080 ",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010100 ",
+        "MSRValue": "0x0000010100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020100 ",
+        "MSRValue": "0x0080020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020100 ",
+        "MSRValue": "0x0100020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020100 ",
+        "MSRValue": "0x0200020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020100 ",
+        "MSRValue": "0x0400020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020100 ",
+        "MSRValue": "0x1000020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020100 ",
+        "MSRValue": "0x3F80020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0100 ",
+        "MSRValue": "0x00803C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0100 ",
+        "MSRValue": "0x01003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0100 ",
+        "MSRValue": "0x02003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0100 ",
+        "MSRValue": "0x04003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0100 ",
+        "MSRValue": "0x10003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0100 ",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010200 ",
+        "MSRValue": "0x0000010200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020200 ",
+        "MSRValue": "0x0080020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020200 ",
+        "MSRValue": "0x0100020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020200 ",
+        "MSRValue": "0x0200020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020200 ",
+        "MSRValue": "0x0400020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020200 ",
+        "MSRValue": "0x1000020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020200 ",
+        "MSRValue": "0x3F80020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0200 ",
+        "MSRValue": "0x00803C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0200 ",
+        "MSRValue": "0x01003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0200 ",
+        "MSRValue": "0x02003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0200 ",
+        "MSRValue": "0x04003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0200 ",
+        "MSRValue": "0x10003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0200 ",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000018000 ",
+        "MSRValue": "0x0000018000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that have any response type.",
+        "BriefDescription": "Counts any other requests have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080028000 ",
+        "MSRValue": "0x0080028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100028000 ",
+        "MSRValue": "0x0100028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200028000 ",
+        "MSRValue": "0x0200028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400028000 ",
+        "MSRValue": "0x0400028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000028000 ",
+        "MSRValue": "0x1000028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80028000 ",
+        "MSRValue": "0x3F80028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c8000 ",
+        "MSRValue": "0x00803C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c8000 ",
+        "MSRValue": "0x01003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c8000 ",
+        "MSRValue": "0x02003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c8000 ",
+        "MSRValue": "0x04003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c8000 ",
+        "MSRValue": "0x10003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c8000 ",
+        "MSRValue": "0x3F803C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010090 ",
+        "MSRValue": "0x0000010090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that have any response type.",
+        "BriefDescription": "Counts all prefetch data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020090 ",
+        "MSRValue": "0x0080020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020090 ",
+        "MSRValue": "0x0100020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020090 ",
+        "MSRValue": "0x0200020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020090 ",
+        "MSRValue": "0x0400020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020090 ",
+        "MSRValue": "0x1000020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020090 ",
+        "MSRValue": "0x3F80020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0090 ",
+        "MSRValue": "0x00803C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0090 ",
+        "MSRValue": "0x01003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0090 ",
+        "MSRValue": "0x02003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0090 ",
+        "MSRValue": "0x04003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0090 ",
+        "MSRValue": "0x10003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0090 ",
+        "MSRValue": "0x3F803C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010120 ",
+        "MSRValue": "0x0000010120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that have any response type.",
+        "BriefDescription": "Counts prefetch RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020120 ",
+        "MSRValue": "0x0080020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020120 ",
+        "MSRValue": "0x0100020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020120 ",
+        "MSRValue": "0x0200020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020120 ",
+        "MSRValue": "0x0400020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020120 ",
+        "MSRValue": "0x1000020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020120 ",
+        "MSRValue": "0x3F80020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0120 ",
+        "MSRValue": "0x00803C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0120 ",
+        "MSRValue": "0x01003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0120 ",
+        "MSRValue": "0x02003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0120 ",
+        "MSRValue": "0x04003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0120 ",
+        "MSRValue": "0x10003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0120 ",
+        "MSRValue": "0x3F803C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010240 ",
+        "MSRValue": "0x0000010240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that have any response type.",
+        "BriefDescription": "Counts all prefetch code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020240 ",
+        "MSRValue": "0x0080020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020240 ",
+        "MSRValue": "0x0100020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020240 ",
+        "MSRValue": "0x0200020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020240 ",
+        "MSRValue": "0x0400020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020240 ",
+        "MSRValue": "0x1000020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020240 ",
+        "MSRValue": "0x3F80020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0240 ",
+        "MSRValue": "0x00803C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0240 ",
+        "MSRValue": "0x01003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0240 ",
+        "MSRValue": "0x02003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0240 ",
+        "MSRValue": "0x04003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0240 ",
+        "MSRValue": "0x10003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0240 ",
+        "MSRValue": "0x3F803C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010091 ",
+        "MSRValue": "0x0000010091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
+        "BriefDescription": "Counts all demand & prefetch data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020091 ",
+        "MSRValue": "0x0080020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020091 ",
+        "MSRValue": "0x0100020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020091 ",
+        "MSRValue": "0x0200020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020091 ",
+        "MSRValue": "0x0400020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020091 ",
+        "MSRValue": "0x1000020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020091 ",
+        "MSRValue": "0x3F80020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0091 ",
+        "MSRValue": "0x00803C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0091 ",
+        "MSRValue": "0x01003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0091 ",
+        "MSRValue": "0x02003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0091 ",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0091 ",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0091 ",
+        "MSRValue": "0x3F803C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010122 ",
+        "MSRValue": "0x0000010122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
+        "BriefDescription": "Counts all demand & prefetch RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020122 ",
+        "MSRValue": "0x0080020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020122 ",
+        "MSRValue": "0x0100020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020122 ",
+        "MSRValue": "0x0200020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020122 ",
+        "MSRValue": "0x0400020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020122 ",
+        "MSRValue": "0x1000020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020122 ",
+        "MSRValue": "0x3F80020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0122 ",
+        "MSRValue": "0x00803C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0122 ",
+        "MSRValue": "0x01003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0122 ",
+        "MSRValue": "0x02003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0122 ",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0122 ",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0122 ",
+        "MSRValue": "0x3F803C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
index 689d478dae93..15291239c128 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
@@ -1,24 +1,26 @@
 [
     {
-        "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "Errata": "BDM30",
         "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "BDM30",
         "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+        "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -45,7 +47,7 @@
         "UMask": "0x3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -54,7 +56,7 @@
         "UMask": "0x4",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -63,7 +65,7 @@
         "UMask": "0x8",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -72,7 +74,7 @@
         "UMask": "0x10",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -81,7 +83,7 @@
         "UMask": "0x15",
         "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
         "SampleAfterValue": "2000006",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -90,7 +92,7 @@
         "UMask": "0x20",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -99,7 +101,7 @@
         "UMask": "0x2a",
         "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
         "SampleAfterValue": "2000005",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -108,57 +110,62 @@
         "UMask": "0x3c",
         "EventName": "FP_ARITH_INST_RETIRED.PACKED",
         "SampleAfterValue": "2000004",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "FP_ASSIST.X87_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to output value.",
+        "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result  (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "FP_ASSIST.X87_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to input value.",
+        "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand  (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "FP_ASSIST.SIMD_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to Output values",
+        "BriefDescription": "SSE* FP micro-code assist when output value is invalid. (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts any input SSE* floating-point (FP) assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "FP_ASSIST.SIMD_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to input values",
+        "BriefDescription": "Any input SSE* FP Assist -   (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "PEBS": "1",
+        "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1. Uses PEBS.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
         "EventName": "FP_ASSIST.ANY",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "BriefDescription": "Counts any FP_ASSIST umask was incrementing   (Precise Event)",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
index 7142c76d7f11..aa4a5d762f21 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
@@ -211,7 +211,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -274,7 +274,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
         "EventCode": "0xAB",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
index c9154cebbdf0..b6b5247d3d5a 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
@@ -311,7 +311,7 @@
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above four.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above four.",
         "EventCode": "0xCD",
         "MSRValue": "0x4",
         "Counter": "3",
@@ -320,13 +320,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Loads with latency value being above 4",
+        "BriefDescription": "Randomly selected loads with latency value being above 4",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above eight.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above eight.",
         "EventCode": "0xCD",
         "MSRValue": "0x8",
         "Counter": "3",
@@ -335,13 +335,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Loads with latency value being above 8",
+        "BriefDescription": "Randomly selected loads with latency value being above 8",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 16.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 16.",
         "EventCode": "0xCD",
         "MSRValue": "0x10",
         "Counter": "3",
@@ -350,13 +350,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Loads with latency value being above 16",
+        "BriefDescription": "Randomly selected loads with latency value being above 16",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 32.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 32.",
         "EventCode": "0xCD",
         "MSRValue": "0x20",
         "Counter": "3",
@@ -365,13 +365,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Loads with latency value being above 32",
+        "BriefDescription": "Randomly selected loads with latency value being above 32",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 64.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 64.",
         "EventCode": "0xCD",
         "MSRValue": "0x40",
         "Counter": "3",
@@ -380,13 +380,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "2003",
-        "BriefDescription": "Loads with latency value being above 64",
+        "BriefDescription": "Randomly selected loads with latency value being above 64",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 128.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 128.",
         "EventCode": "0xCD",
         "MSRValue": "0x80",
         "Counter": "3",
@@ -395,13 +395,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "1009",
-        "BriefDescription": "Loads with latency value being above 128",
+        "BriefDescription": "Randomly selected loads with latency value being above 128",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 256.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 256.",
         "EventCode": "0xCD",
         "MSRValue": "0x100",
         "Counter": "3",
@@ -410,13 +410,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "503",
-        "BriefDescription": "Loads with latency value being above 256",
+        "BriefDescription": "Randomly selected loads with latency value being above 256",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 512.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 512.",
         "EventCode": "0xCD",
         "MSRValue": "0x200",
         "Counter": "3",
@@ -425,2620 +425,2620 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "101",
-        "BriefDescription": "Loads with latency value being above 512",
+        "BriefDescription": "Randomly selected loads with latency value being above 512",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020001 ",
+        "MSRValue": "0x2000020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0001 ",
+        "MSRValue": "0x20003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000001 ",
+        "MSRValue": "0x0084000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000001 ",
+        "MSRValue": "0x0104000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000001 ",
+        "MSRValue": "0x0204000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000001 ",
+        "MSRValue": "0x0404000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000001 ",
+        "MSRValue": "0x1004000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000001 ",
+        "MSRValue": "0x2004000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000001 ",
+        "MSRValue": "0x3F84000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000001 ",
+        "MSRValue": "0x00BC000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000001 ",
+        "MSRValue": "0x013C000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000001 ",
+        "MSRValue": "0x023C000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000001 ",
+        "MSRValue": "0x043C000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0002 ",
+        "MSRValue": "0x20003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000002 ",
+        "MSRValue": "0x3F84000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000002 ",
+        "MSRValue": "0x00BC000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000002 ",
+        "MSRValue": "0x013C000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000002 ",
+        "MSRValue": "0x023C000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000002 ",
+        "MSRValue": "0x043C000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020004 ",
+        "MSRValue": "0x2000020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0004 ",
+        "MSRValue": "0x20003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000004 ",
+        "MSRValue": "0x0084000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000004 ",
+        "MSRValue": "0x0104000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000004 ",
+        "MSRValue": "0x0204000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000004 ",
+        "MSRValue": "0x0404000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000004 ",
+        "MSRValue": "0x1004000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000004 ",
+        "MSRValue": "0x2004000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000004 ",
+        "MSRValue": "0x3F84000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000004 ",
+        "MSRValue": "0x00BC000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000004 ",
+        "MSRValue": "0x013C000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000004 ",
+        "MSRValue": "0x023C000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000004 ",
+        "MSRValue": "0x043C000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020008 ",
+        "MSRValue": "0x2000020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0008 ",
+        "MSRValue": "0x20003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000008 ",
+        "MSRValue": "0x0084000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000008 ",
+        "MSRValue": "0x0104000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000008 ",
+        "MSRValue": "0x0204000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000008 ",
+        "MSRValue": "0x0404000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000008 ",
+        "MSRValue": "0x1004000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000008 ",
+        "MSRValue": "0x2004000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000008 ",
+        "MSRValue": "0x3F84000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000008 ",
+        "MSRValue": "0x00BC000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000008 ",
+        "MSRValue": "0x013C000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000008 ",
+        "MSRValue": "0x023C000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000008 ",
+        "MSRValue": "0x043C000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020010 ",
+        "MSRValue": "0x2000020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0010 ",
+        "MSRValue": "0x20003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000010 ",
+        "MSRValue": "0x0084000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000010 ",
+        "MSRValue": "0x0104000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000010 ",
+        "MSRValue": "0x0204000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000010 ",
+        "MSRValue": "0x0404000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000010 ",
+        "MSRValue": "0x1004000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000010 ",
+        "MSRValue": "0x2004000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000010 ",
+        "MSRValue": "0x3F84000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000010 ",
+        "MSRValue": "0x00BC000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000010 ",
+        "MSRValue": "0x013C000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000010 ",
+        "MSRValue": "0x023C000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000010 ",
+        "MSRValue": "0x043C000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020020 ",
+        "MSRValue": "0x2000020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0020 ",
+        "MSRValue": "0x20003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000020 ",
+        "MSRValue": "0x0084000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000020 ",
+        "MSRValue": "0x0104000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000020 ",
+        "MSRValue": "0x0204000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000020 ",
+        "MSRValue": "0x0404000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000020 ",
+        "MSRValue": "0x1004000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000020 ",
+        "MSRValue": "0x2004000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000020 ",
+        "MSRValue": "0x3F84000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000020 ",
+        "MSRValue": "0x00BC000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000020 ",
+        "MSRValue": "0x013C000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000020 ",
+        "MSRValue": "0x023C000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000020 ",
+        "MSRValue": "0x043C000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020040 ",
+        "MSRValue": "0x2000020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0040 ",
+        "MSRValue": "0x20003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000040 ",
+        "MSRValue": "0x0084000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000040 ",
+        "MSRValue": "0x0104000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000040 ",
+        "MSRValue": "0x0204000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000040 ",
+        "MSRValue": "0x0404000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000040 ",
+        "MSRValue": "0x1004000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000040 ",
+        "MSRValue": "0x2004000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000040 ",
+        "MSRValue": "0x3F84000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000040 ",
+        "MSRValue": "0x00BC000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000040 ",
+        "MSRValue": "0x013C000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000040 ",
+        "MSRValue": "0x023C000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000040 ",
+        "MSRValue": "0x043C000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020080 ",
+        "MSRValue": "0x2000020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0080 ",
+        "MSRValue": "0x20003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000080 ",
+        "MSRValue": "0x0084000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000080 ",
+        "MSRValue": "0x0104000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000080 ",
+        "MSRValue": "0x0204000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000080 ",
+        "MSRValue": "0x0404000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000080 ",
+        "MSRValue": "0x1004000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000080 ",
+        "MSRValue": "0x2004000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000080 ",
+        "MSRValue": "0x3F84000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000080 ",
+        "MSRValue": "0x00BC000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000080 ",
+        "MSRValue": "0x013C000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000080 ",
+        "MSRValue": "0x023C000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000080 ",
+        "MSRValue": "0x043C000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020100 ",
+        "MSRValue": "0x2000020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0100 ",
+        "MSRValue": "0x20003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000100 ",
+        "MSRValue": "0x0084000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000100 ",
+        "MSRValue": "0x0104000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000100 ",
+        "MSRValue": "0x0204000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000100 ",
+        "MSRValue": "0x0404000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000100 ",
+        "MSRValue": "0x1004000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000100 ",
+        "MSRValue": "0x2004000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000100 ",
+        "MSRValue": "0x3F84000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000100 ",
+        "MSRValue": "0x00BC000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000100 ",
+        "MSRValue": "0x013C000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000100 ",
+        "MSRValue": "0x023C000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000100 ",
+        "MSRValue": "0x043C000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020200 ",
+        "MSRValue": "0x2000020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0200 ",
+        "MSRValue": "0x20003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000200 ",
+        "MSRValue": "0x0084000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000200 ",
+        "MSRValue": "0x0104000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000200 ",
+        "MSRValue": "0x0204000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000200 ",
+        "MSRValue": "0x0404000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000200 ",
+        "MSRValue": "0x1004000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000200 ",
+        "MSRValue": "0x2004000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000200 ",
+        "MSRValue": "0x3F84000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000200 ",
+        "MSRValue": "0x00BC000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000200 ",
+        "MSRValue": "0x013C000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000200 ",
+        "MSRValue": "0x023C000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000200 ",
+        "MSRValue": "0x043C000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000028000 ",
+        "MSRValue": "0x2000028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c8000 ",
+        "MSRValue": "0x20003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084008000 ",
+        "MSRValue": "0x0084008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104008000 ",
+        "MSRValue": "0x0104008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204008000 ",
+        "MSRValue": "0x0204008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404008000 ",
+        "MSRValue": "0x0404008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004008000 ",
+        "MSRValue": "0x1004008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004008000 ",
+        "MSRValue": "0x2004008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84008000 ",
+        "MSRValue": "0x3F84008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc008000 ",
+        "MSRValue": "0x00BC008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c008000 ",
+        "MSRValue": "0x013C008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c008000 ",
+        "MSRValue": "0x023C008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c008000 ",
+        "MSRValue": "0x043C008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020090 ",
+        "MSRValue": "0x2000020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0090 ",
+        "MSRValue": "0x20003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000090 ",
+        "MSRValue": "0x0084000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000090 ",
+        "MSRValue": "0x0104000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000090 ",
+        "MSRValue": "0x0204000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000090 ",
+        "MSRValue": "0x0404000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000090 ",
+        "MSRValue": "0x1004000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000090 ",
+        "MSRValue": "0x2004000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000090 ",
+        "MSRValue": "0x3F84000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000090 ",
+        "MSRValue": "0x00BC000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000090 ",
+        "MSRValue": "0x013C000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000090 ",
+        "MSRValue": "0x023C000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000090 ",
+        "MSRValue": "0x043C000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020120 ",
+        "MSRValue": "0x2000020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0120 ",
+        "MSRValue": "0x20003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000120 ",
+        "MSRValue": "0x0084000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000120 ",
+        "MSRValue": "0x0104000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000120 ",
+        "MSRValue": "0x0204000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000120 ",
+        "MSRValue": "0x0404000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000120 ",
+        "MSRValue": "0x1004000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000120 ",
+        "MSRValue": "0x2004000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000120 ",
+        "MSRValue": "0x3F84000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000120 ",
+        "MSRValue": "0x00BC000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000120 ",
+        "MSRValue": "0x013C000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000120 ",
+        "MSRValue": "0x023C000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000120 ",
+        "MSRValue": "0x043C000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020240 ",
+        "MSRValue": "0x2000020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0240 ",
+        "MSRValue": "0x20003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000240 ",
+        "MSRValue": "0x0084000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000240 ",
+        "MSRValue": "0x0104000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000240 ",
+        "MSRValue": "0x0204000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000240 ",
+        "MSRValue": "0x0404000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000240 ",
+        "MSRValue": "0x1004000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000240 ",
+        "MSRValue": "0x2004000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000240 ",
+        "MSRValue": "0x3F84000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000240 ",
+        "MSRValue": "0x00BC000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000240 ",
+        "MSRValue": "0x013C000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000240 ",
+        "MSRValue": "0x023C000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000240 ",
+        "MSRValue": "0x043C000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020091 ",
+        "MSRValue": "0x2000020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0091 ",
+        "MSRValue": "0x20003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000091 ",
+        "MSRValue": "0x0084000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000091 ",
+        "MSRValue": "0x0104000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000091 ",
+        "MSRValue": "0x0204000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000091 ",
+        "MSRValue": "0x0404000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000091 ",
+        "MSRValue": "0x1004000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000091 ",
+        "MSRValue": "0x2004000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000091 ",
+        "MSRValue": "0x3F84000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000091 ",
+        "MSRValue": "0x00BC000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000091 ",
+        "MSRValue": "0x013C000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000091 ",
+        "MSRValue": "0x023C000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000091 ",
+        "MSRValue": "0x043C000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020122 ",
+        "MSRValue": "0x2000020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0122 ",
+        "MSRValue": "0x20003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000122 ",
+        "MSRValue": "0x0084000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000122 ",
+        "MSRValue": "0x0104000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000122 ",
+        "MSRValue": "0x0204000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000122 ",
+        "MSRValue": "0x0404000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000122 ",
+        "MSRValue": "0x1004000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000122 ",
+        "MSRValue": "0x2004000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000122 ",
+        "MSRValue": "0x3F84000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000122 ",
+        "MSRValue": "0x00BC000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000122 ",
+        "MSRValue": "0x013C000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000122 ",
+        "MSRValue": "0x023C000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000122 ",
+        "MSRValue": "0x043C000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
index 999cf3066363..bb25574b8d21 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -11,7 +10,6 @@
     },
     {
         "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -31,7 +28,6 @@
     },
     {
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -317,7 +313,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "EventCode": "0x87",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -786,8 +782,8 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
-        "EventCode": "0xA2",
+        "PublicDescription": "This event counts resource-related stall cycles.",
+        "EventCode": "0xa2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "RESOURCE_STALLS.ANY",
@@ -973,6 +969,7 @@
         "CounterHTOff": "2"
     },
     {
+        "PublicDescription": "Number of Uops delivered by the LSD.",
         "EventCode": "0xA8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -1147,7 +1144,8 @@
         "CounterHTOff": "1"
     },
     {
-        "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
         "EventCode": "0xC0",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -1157,12 +1155,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PEBS": "1",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1178,26 +1176,28 @@
         "Data_LA": "1"
     },
     {
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts cycles without actually retired uops.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
+        "BriefDescription": "Cycles no executable uops retired (Precise Event)",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "PEBS": "1",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to  PEBS uops retired event.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS uops retired event.",
         "CounterMask": "10",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1320,13 +1320,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts not taken branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired. (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1341,14 +1342,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts far branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "Errata": "BDW98",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired.",
+        "BriefDescription": "Counts the number of far branch instructions retired.(Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
index 4ad425312bdc..bf243fe2a0ec 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
@@ -439,7 +439,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -451,7 +451,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
index 0d04bf9db000..e2f0540625a2 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -10,7 +9,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -30,7 +27,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -322,7 +318,7 @@
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "Counter": "0,1,2,3",
         "EventName": "ILD_STALL.LCP",
-        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 5a7f1ec24200..c6f9762f32c0 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -1,164 +1,370 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
+    },
+    {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
index 141b1080429d..75a3098d5775 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
@@ -57,17 +57,17 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "BriefDescription": "RFO requests that hit L2 cache.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.RFO_HIT",
@@ -76,7 +76,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
@@ -85,7 +85,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.L2_PF_HIT",
@@ -396,24 +396,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This event counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)",
+        "BriefDescription": "Retired store uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This event counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -421,37 +421,37 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops with locked access.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "Errata": "BDM35",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.",
+        "PublicDescription": "This event counts load uops with locked access retired to the architected path.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -459,24 +459,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops. (Precise Event - PEBS)",
+        "BriefDescription": "All retired load uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+        "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
+        "BriefDescription": "All retired store uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+        "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
         "SampleAfterValue": "2000003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -484,69 +484,69 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "Errata": "BDM35",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the mid-level (L2) cache.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This event counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.",
+        "BriefDescription": "Retired load uops misses in L1 cache as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.",
+        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x20",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -558,83 +558,84 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x40",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+        "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
+        "PublicDescription": "This event counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
+        "PublicDescription": "This event counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
+        "PublicDescription": "This event counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
+        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "BDE70, BDM100",
-        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -646,7 +647,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -658,7 +659,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x20",
-        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -810,12 +811,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that hit in the L3",
-        "MSRValue": "0x3f803c8fff",
+        "BriefDescription": "Counts all requests hit in the L3",
+        "MSRValue": "0x3F803C8FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -823,12 +824,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -836,12 +837,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -849,12 +850,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0244",
+        "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -862,12 +863,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -875,12 +876,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -888,12 +889,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -901,12 +902,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -914,12 +915,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
-        "MSRValue": "0x3f803c0200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -927,12 +928,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
-        "MSRValue": "0x3f803c0100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -940,12 +941,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -953,12 +954,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3",
-        "MSRValue": "0x3f803c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3",
+        "MSRValue": "0x3F803C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
index d7b9d9c9c518..ba0e0c4e74eb 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
@@ -42,7 +42,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x3",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
         "SampleAfterValue": "2000003",
@@ -51,7 +51,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x4",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -60,7 +60,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x8",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
@@ -69,7 +69,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x10",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -78,7 +78,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x15",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
         "SampleAfterValue": "2000006",
@@ -87,7 +87,7 @@
     {
         "EventCode": "0xc7",
         "UMask": "0x20",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
@@ -96,7 +96,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x2a",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
         "SampleAfterValue": "2000005",
@@ -105,7 +105,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x3c",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.PACKED",
         "SampleAfterValue": "2000004",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
index d79a5cfea44b..ecb413bb67ca 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
@@ -170,11 +170,11 @@
     {
         "EventCode": "0xc8",
         "UMask": "0x4",
-        "BriefDescription": "Number of times HLE abort was triggered (PEBS)",
+        "BriefDescription": "Number of times HLE abort was triggered",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
-        "PublicDescription": "Number of times HLE abort was triggered (PEBS).",
+        "PublicDescription": "Number of times HLE abort was triggered.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -251,11 +251,11 @@
     {
         "EventCode": "0xc9",
         "UMask": "0x4",
-        "BriefDescription": "Number of times RTM abort was triggered (PEBS)",
+        "BriefDescription": "Number of times RTM abort was triggered",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Number of times RTM abort was triggered (PEBS).",
+        "PublicDescription": "Number of times RTM abort was triggered .",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -312,14 +312,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 4",
+        "BriefDescription": "Randomly selected loads with latency value being above 4",
         "PEBS": "2",
         "MSRValue": "0x4",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above four.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above four.",
         "TakenAlone": "1",
         "SampleAfterValue": "100003",
         "CounterHTOff": "3"
@@ -327,14 +327,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 8",
+        "BriefDescription": "Randomly selected loads with latency value being above 8",
         "PEBS": "2",
         "MSRValue": "0x8",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above eight.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above eight.",
         "TakenAlone": "1",
         "SampleAfterValue": "50021",
         "CounterHTOff": "3"
@@ -342,14 +342,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 16",
+        "BriefDescription": "Randomly selected loads with latency value being above 16",
         "PEBS": "2",
         "MSRValue": "0x10",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 16.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 16.",
         "TakenAlone": "1",
         "SampleAfterValue": "20011",
         "CounterHTOff": "3"
@@ -357,14 +357,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 32",
+        "BriefDescription": "Randomly selected loads with latency value being above 32",
         "PEBS": "2",
         "MSRValue": "0x20",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 32.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 32.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "3"
@@ -372,14 +372,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 64",
+        "BriefDescription": "Randomly selected loads with latency value being above 64",
         "PEBS": "2",
         "MSRValue": "0x40",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 64.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 64.",
         "TakenAlone": "1",
         "SampleAfterValue": "2003",
         "CounterHTOff": "3"
@@ -387,14 +387,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 128",
+        "BriefDescription": "Randomly selected loads with latency value being above 128",
         "PEBS": "2",
         "MSRValue": "0x80",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 128.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 128.",
         "TakenAlone": "1",
         "SampleAfterValue": "1009",
         "CounterHTOff": "3"
@@ -402,14 +402,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 256",
+        "BriefDescription": "Randomly selected loads with latency value being above 256",
         "PEBS": "2",
         "MSRValue": "0x100",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 256.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 256.",
         "TakenAlone": "1",
         "SampleAfterValue": "503",
         "CounterHTOff": "3"
@@ -417,14 +417,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 512",
+        "BriefDescription": "Randomly selected loads with latency value being above 512",
         "PEBS": "2",
         "MSRValue": "0x200",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 512.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 512.",
         "TakenAlone": "1",
         "SampleAfterValue": "101",
         "CounterHTOff": "3"
@@ -433,12 +433,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that miss in the L3",
-        "MSRValue": "0x3fbfc08fff",
+        "BriefDescription": "Counts all requests miss in the L3",
+        "MSRValue": "0x3FBFC08FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -446,12 +446,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x087fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x087FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -459,12 +459,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -472,12 +472,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063bc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063BC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -485,12 +485,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
-        "MSRValue": "0x06040007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
+        "MSRValue": "0x06040007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -498,12 +498,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
-        "MSRValue": "0x3fbfc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
+        "MSRValue": "0x3FBFC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -511,12 +511,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0604000244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -524,12 +524,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00244",
+        "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
+        "MSRValue": "0x3FBFC00244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -537,12 +537,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0604000122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -550,12 +550,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00122",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -563,12 +563,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x087fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x087FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -576,12 +576,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -589,12 +589,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063bc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063BC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -602,12 +602,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0604000091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -615,12 +615,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
+        "MSRValue": "0x3FBFC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -628,12 +628,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
+        "MSRValue": "0x3FBFC00200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -641,12 +641,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -654,12 +654,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -667,12 +667,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
-        "MSRValue": "0x3fbfc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
+        "MSRValue": "0x3FBFC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
index 0d04bf9db000..c2f6932a5817 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -10,7 +9,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -30,7 +27,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -322,7 +318,7 @@
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "Counter": "0,1,2,3",
         "EventName": "ILD_STALL.LCP",
-        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -786,12 +782,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xa2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
         "Counter": "0,1,2,3",
         "EventName": "RESOURCE_STALLS.ANY",
-        "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
+        "PublicDescription": "This event counts resource-related stall cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1168,12 +1164,12 @@
     {
         "EventCode": "0xC2",
         "UMask": "0x1",
-        "BriefDescription": "Actually retired uops. (Precise Event - PEBS)",
+        "BriefDescription": "Actually retired uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
+        "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1204,11 +1200,11 @@
     {
         "EventCode": "0xC2",
         "UMask": "0x2",
-        "BriefDescription": "Retirement slots used. (Precise Event - PEBS)",
+        "BriefDescription": "Retirement slots used.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.",
+        "PublicDescription": "This event counts the number of retirement slots used.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1266,33 +1262,33 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x1",
-        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Conditional branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
+        "PublicDescription": "This event counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x2",
-        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "This event counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x2",
-        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).",
+        "PublicDescription": "This event counts both direct and indirect macro near call instructions retired (captured in ring 3).",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1311,11 +1307,11 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x8",
-        "BriefDescription": "Return instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Return instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
+        "PublicDescription": "This event counts return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1332,11 +1328,11 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x20",
-        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Taken branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
+        "PublicDescription": "This event counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1364,11 +1360,11 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x1",
-        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "This event counts mispredicted conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1386,22 +1382,22 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x8",
-        "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)",
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This event counts mispredicted return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 71e9737f4614..1a1a3501180a 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -1,164 +1,394 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
+    },
+    {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Access_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 1 == 1 else 0 else 0",
+        "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "MEM_PMM_Read_Latency"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Read_BW"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Write_BW"
+    },
+    {
+        "MetricExpr": "cha_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/cache.json b/tools/perf/pmu-events/arch/x86/goldmont/cache.json
index f8bbe087b0f8..52a105666afc 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/cache.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/cache.json
@@ -77,7 +77,8 @@
         "UMask": "0x21",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Locked load uops retired (Precise event capable)"
+        "BriefDescription": "Locked load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -88,7 +89,8 @@
         "UMask": "0x41",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -99,7 +101,8 @@
         "UMask": "0x42",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -110,7 +113,8 @@
         "UMask": "0x43",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -121,7 +125,8 @@
         "UMask": "0x81",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired (Precise event capable)"
+        "BriefDescription": "Load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -132,7 +137,8 @@
         "UMask": "0x82",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired (Precise event capable)"
+        "BriefDescription": "Store uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -143,7 +149,8 @@
         "UMask": "0x83",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired (Precise event capable)"
+        "BriefDescription": "Memory uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -154,7 +161,8 @@
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -165,7 +173,8 @@
         "UMask": "0x2",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -176,7 +185,8 @@
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -187,7 +197,8 @@
         "UMask": "0x10",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -198,7 +209,8 @@
         "UMask": "0x20",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -209,7 +221,8 @@
         "UMask": "0x40",
         "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+        "BriefDescription": "Loads retired that hit WCB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -220,26 +233,14 @@
         "UMask": "0x80",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x40000032b7 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
+        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x36000032b7 ",
+        "MSRValue": "0x36000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.ANY",
@@ -252,7 +253,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x10000032b7 ",
+        "MSRValue": "0x10000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE",
@@ -265,7 +266,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x04000032b7 ",
+        "MSRValue": "0x04000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -278,20 +279,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x02000032b7 ",
+        "MSRValue": "0x02000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x00000432b7 ",
+        "MSRValue": "0x00000432b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT",
@@ -302,35 +303,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x00000132b7 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000022 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000022 ",
+        "MSRValue": "0x3600000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.ANY",
@@ -343,7 +318,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000022 ",
+        "MSRValue": "0x1000000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE",
@@ -356,7 +331,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000022 ",
+        "MSRValue": "0x0400000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -369,20 +344,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000022 ",
+        "MSRValue": "0x0200000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040022 ",
+        "MSRValue": "0x0000040022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT",
@@ -393,32 +368,6 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010022 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000003091",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600003091",
@@ -466,7 +415,7 @@
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -484,35 +433,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000013091",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000003010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600003010 ",
+        "MSRValue": "0x3600003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.ANY",
@@ -525,7 +448,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000003010 ",
+        "MSRValue": "0x1000003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -538,7 +461,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400003010 ",
+        "MSRValue": "0x0400003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -551,20 +474,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200003010 ",
+        "MSRValue": "0x0200003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000043010 ",
+        "MSRValue": "0x0000043010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT",
@@ -575,48 +498,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000013010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x3600008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.ANY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000008000 ",
+        "MSRValue": "0x1000008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE",
@@ -629,7 +513,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400008000 ",
+        "MSRValue": "0x0400008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -642,20 +526,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200008000 ",
+        "MSRValue": "0x0200008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000048000 ",
+        "MSRValue": "0x0000048000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT",
@@ -668,7 +552,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000018000 ",
+        "MSRValue": "0x0000018000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
@@ -679,22 +563,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600004800 ",
+        "MSRValue": "0x3600004800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.ANY",
@@ -705,48 +576,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000044800 ",
+        "MSRValue": "0x0000044800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT",
@@ -757,35 +589,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000014800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000004000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600004000 ",
+        "MSRValue": "0x3600004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.ANY",
@@ -798,7 +604,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000004000 ",
+        "MSRValue": "0x1000004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
@@ -811,7 +617,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400004000 ",
+        "MSRValue": "0x0400004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -824,20 +630,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200004000 ",
+        "MSRValue": "0x0200004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000044000 ",
+        "MSRValue": "0x0000044000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_HIT",
@@ -848,35 +654,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000014000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000002000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600002000 ",
+        "MSRValue": "0x3600002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.ANY",
@@ -889,7 +669,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000002000 ",
+        "MSRValue": "0x1000002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -902,7 +682,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400002000 ",
+        "MSRValue": "0x0400002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -915,20 +695,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200002000 ",
+        "MSRValue": "0x0200002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000042000 ",
+        "MSRValue": "0x0000042000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT",
@@ -939,35 +719,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000012000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000001000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600001000 ",
+        "MSRValue": "0x3600001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.ANY",
@@ -980,7 +734,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000001000 ",
+        "MSRValue": "0x1000001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE",
@@ -993,7 +747,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400001000 ",
+        "MSRValue": "0x0400001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1006,20 +760,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200001000 ",
+        "MSRValue": "0x0200001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000041000 ",
+        "MSRValue": "0x0000041000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT",
@@ -1030,35 +784,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000011000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000800 ",
+        "MSRValue": "0x3600000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.ANY",
@@ -1071,7 +799,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000800 ",
+        "MSRValue": "0x1000000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
@@ -1084,7 +812,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000800 ",
+        "MSRValue": "0x0400000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1097,20 +825,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000800 ",
+        "MSRValue": "0x0200000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040800 ",
+        "MSRValue": "0x0000040800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT",
@@ -1121,100 +849,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x3600000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.ANY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010400 ",
+        "MSRValue": "0x0000010400",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
@@ -1225,113 +862,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x3600000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.ANY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000100 ",
+        "MSRValue": "0x3600000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.ANY",
@@ -1342,87 +875,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000080 ",
+        "MSRValue": "0x3600000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.ANY",
@@ -1433,87 +888,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000020 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000020 ",
+        "MSRValue": "0x3600000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.ANY",
@@ -1526,7 +903,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000020 ",
+        "MSRValue": "0x1000000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE",
@@ -1539,7 +916,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000020 ",
+        "MSRValue": "0x0400000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1552,20 +929,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000020 ",
+        "MSRValue": "0x0200000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040020 ",
+        "MSRValue": "0x0000040020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT",
@@ -1576,35 +953,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010020 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000010 ",
+        "MSRValue": "0x3600000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.ANY",
@@ -1617,7 +968,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000010 ",
+        "MSRValue": "0x1000000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -1630,7 +981,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000010 ",
+        "MSRValue": "0x0400000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1643,20 +994,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000010 ",
+        "MSRValue": "0x0200000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040010 ",
+        "MSRValue": "0x0000040010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT",
@@ -1667,35 +1018,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000008 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000008 ",
+        "MSRValue": "0x3600000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.ANY",
@@ -1708,7 +1033,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000008 ",
+        "MSRValue": "0x1000000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE",
@@ -1721,7 +1046,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000008 ",
+        "MSRValue": "0x0400000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1734,20 +1059,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000008 ",
+        "MSRValue": "0x0200000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040008 ",
+        "MSRValue": "0x0000040008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT",
@@ -1758,22 +1083,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010008 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000004 ",
+        "MSRValue": "0x4000000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
@@ -1786,7 +1098,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000004 ",
+        "MSRValue": "0x3600000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.ANY",
@@ -1797,22 +1109,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000004 ",
+        "MSRValue": "0x0400000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1825,20 +1124,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000004 ",
+        "MSRValue": "0x0200000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040004 ",
+        "MSRValue": "0x0000040004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT",
@@ -1849,22 +1148,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000002 ",
+        "MSRValue": "0x4000000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
@@ -1877,7 +1163,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000002 ",
+        "MSRValue": "0x3600000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.ANY",
@@ -1890,7 +1176,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000002 ",
+        "MSRValue": "0x1000000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE",
@@ -1903,7 +1189,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000002 ",
+        "MSRValue": "0x0400000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1916,20 +1202,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000002 ",
+        "MSRValue": "0x0200000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040002 ",
+        "MSRValue": "0x0000040002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT",
@@ -1940,22 +1226,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000001 ",
+        "MSRValue": "0x4000000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
@@ -1968,7 +1241,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000001 ",
+        "MSRValue": "0x3600000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.ANY",
@@ -1981,7 +1254,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000001 ",
+        "MSRValue": "0x1000000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -1994,7 +1267,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000001 ",
+        "MSRValue": "0x0400000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -2007,20 +1280,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000001 ",
+        "MSRValue": "0x0200000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040001 ",
+        "MSRValue": "0x0000040001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT",
@@ -2028,18 +1301,5 @@
         "SampleAfterValue": "100007",
         "BriefDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache.",
         "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/memory.json b/tools/perf/pmu-events/arch/x86/goldmont/memory.json
index 690cebd12a94..197dc76d49dd 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/memory.json
@@ -30,265 +30,5 @@
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
         "SampleAfterValue": "200003",
         "BriefDescription": "Machine clears due to memory ordering issue"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x20000032b7 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000022 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000003091",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000003010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000004000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000002000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000001000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000020 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000008 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
index 254788af8ab6..6342368accf8 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -10,7 +9,6 @@
     },
     {
         "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.CORE",
@@ -19,7 +17,6 @@
     },
     {
         "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -188,7 +185,7 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
index 9805198d3f5f..343d66bbd777 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
@@ -48,7 +48,8 @@
         "UMask": "0x11",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -59,7 +60,8 @@
         "UMask": "0x12",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -70,6 +72,7 @@
         "UMask": "0x13",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
index b4791b443a66..5a6ac8285ad4 100644
--- a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
@@ -92,7 +92,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Locked load uops retired (Precise event capable)"
+        "BriefDescription": "Locked load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -104,7 +105,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -116,7 +118,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -128,7 +131,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -140,7 +144,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired (Precise event capable)"
+        "BriefDescription": "Load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -152,7 +157,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired (Precise event capable)"
+        "BriefDescription": "Store uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -164,7 +170,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired (Precise event capable)"
+        "BriefDescription": "Memory uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -176,7 +183,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -188,7 +196,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -200,7 +209,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -212,7 +222,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -224,7 +235,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -236,7 +248,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+        "BriefDescription": "Loads retired that hit WCB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -248,7 +261,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
+        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "CollectPEBSRecord": "1",
@@ -292,7 +306,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -367,7 +381,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -442,7 +456,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -517,7 +531,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -592,7 +606,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -667,7 +681,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -742,7 +756,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -817,7 +831,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -892,7 +906,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -967,7 +981,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1042,7 +1056,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1117,7 +1131,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1192,7 +1206,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1267,7 +1281,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1342,7 +1356,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1417,7 +1431,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
index ccf1aed69197..e3fa1a0ba71b 100644
--- a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
@@ -3,7 +3,6 @@
         "PEBS": "2",
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "PEBScounters": "32",
@@ -15,7 +14,6 @@
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "PEBScounters": "33",
@@ -27,7 +25,6 @@
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "PEBScounters": "34",
@@ -231,7 +228,7 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
index 0b53a3b0dfb8..0d32fd26ded1 100644
--- a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
@@ -189,7 +189,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -201,7 +202,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -213,6 +215,7 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json
index da4d6ddd4f92..7fb0ad8d8ca1 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json
@@ -63,10 +63,10 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "Errata": "HSD78",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
@@ -77,7 +77,7 @@
         "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "RFO requests that hit L2 cache",
@@ -87,7 +87,7 @@
         "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
@@ -97,7 +97,7 @@
         "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "EventName": "L2_RQSTS.L2_PF_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
@@ -610,7 +610,7 @@
         "Errata": "HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -623,7 +623,7 @@
         "Errata": "HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -792,7 +792,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "",
         "EventCode": "0xf4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -802,262 +801,262 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c8fff",
+        "MSRValue": "0x3F803C8FFF",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all requests that hit in the L3",
+        "BriefDescription": "Counts all requests hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c07f7",
+        "MSRValue": "0x10003C07F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c07f7",
+        "MSRValue": "0x04003C07F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0244",
+        "MSRValue": "0x04003C0244",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0122",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0122",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0091",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0091",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0200",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0100",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0080",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0040",
+        "MSRValue": "0x3F803C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0020",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0010",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0004",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0004",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0002",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0002",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0001",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0001",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
index f9843e5a9b42..f5a3beaa19fc 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
@@ -1,22 +1,26 @@
 [
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "Errata": "HSD56, HSM57",
         "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "HSD56, HSM57",
         "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+        "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -30,53 +34,58 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of X87 FP assists due to output values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "FP_ASSIST.X87_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to output value.",
+        "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of X87 FP assists due to input values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "FP_ASSIST.X87_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to input value.",
+        "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of SIMD FP assists due to output values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "FP_ASSIST.SIMD_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to Output values",
+        "BriefDescription": "SSE* FP micro-code assist when output value is invalid.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of SIMD FP assists due to input values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "FP_ASSIST.SIMD_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to input values",
+        "BriefDescription": "Any input SSE* FP Assist",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles with any input/output SSE* or FP assists.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
         "EventName": "FP_ASSIST.ANY",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "BriefDescription": "Counts any FP_ASSIST umask was incrementing",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
index 5ab5c78fe580..21b27488b621 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -1,158 +1,322 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json
index e5f9fa6655b3..ef13ed88e2ea 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json
@@ -298,7 +298,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Loads with latency value being above 4.",
+        "BriefDescription": "Randomly selected loads with latency value being above 4.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -312,7 +312,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Loads with latency value being above 8.",
+        "BriefDescription": "Randomly selected loads with latency value being above 8.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -326,7 +326,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Loads with latency value being above 16.",
+        "BriefDescription": "Randomly selected loads with latency value being above 16.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -340,7 +340,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Loads with latency value being above 32.",
+        "BriefDescription": "Randomly selected loads with latency value being above 32.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -354,7 +354,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "2003",
-        "BriefDescription": "Loads with latency value being above 64.",
+        "BriefDescription": "Randomly selected loads with latency value being above 64.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -368,7 +368,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "1009",
-        "BriefDescription": "Loads with latency value being above 128.",
+        "BriefDescription": "Randomly selected loads with latency value being above 128.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -382,7 +382,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "503",
-        "BriefDescription": "Loads with latency value being above 256.",
+        "BriefDescription": "Randomly selected loads with latency value being above 256.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -396,280 +396,280 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "101",
-        "BriefDescription": "Loads with latency value being above 512.",
+        "BriefDescription": "Randomly selected loads with latency value being above 512.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
-        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc08fff",
+        "MSRValue": "0x3FFFC08FFF",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all requests that miss in the L3",
+        "BriefDescription": "Counts all requests miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01004007f7",
+        "MSRValue": "0x01004007F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc007f7",
+        "MSRValue": "0x3FFFC007F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
+        "BriefDescription": "miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400244",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00244",
+        "MSRValue": "0x3FFFC00244",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
+        "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00122",
+        "MSRValue": "0x3FFFC00122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00091",
+        "MSRValue": "0x3FFFC00091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
+        "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00200",
+        "MSRValue": "0x3FFFC00200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00100",
+        "MSRValue": "0x3FFFC00100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00080",
+        "MSRValue": "0x3FFFC00080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00040",
+        "MSRValue": "0x3FFFC00040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00020",
+        "MSRValue": "0x3FFFC00020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00010",
+        "MSRValue": "0x3FFFC00010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00004",
+        "MSRValue": "0x3FFFC00004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss in the L3",
+        "BriefDescription": "Counts all demand code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00002",
+        "MSRValue": "0x3FFFC00002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00001",
+        "MSRValue": "0x3FFFC00001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss in the L3",
+        "BriefDescription": "Counts demand data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
index a4dcfce4a512..734d3873729e 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "Errata": "HSD140, HSD143",
@@ -12,7 +11,6 @@
     },
     {
         "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -21,7 +19,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -32,7 +29,6 @@
     },
     {
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -1071,7 +1067,8 @@
         "CounterHTOff": "1"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
         "EventCode": "0xC0",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -1081,13 +1078,13 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1102,28 +1099,34 @@
         "Data_LA": "1"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
+        "BriefDescription": "Cycles no executable uops retired",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS uops retired event.",
         "CounterMask": "10",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
@@ -1131,7 +1134,7 @@
         "AnyThread": "1",
         "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
+        "BriefDescription": "Cycles no executable uops retired on core",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1245,13 +1248,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of not taken branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1265,13 +1269,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of far branches retired.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Far branch instructions retired.",
+        "BriefDescription": "Counts the number of far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json
index b2fbd617306a..a9e62d4357af 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json
@@ -64,18 +64,18 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "Errata": "HSD78",
-        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "BriefDescription": "RFO requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.RFO_HIT",
@@ -85,7 +85,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
@@ -95,7 +95,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.L2_PF_HIT",
@@ -416,7 +416,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB. (precise Event)",
+        "BriefDescription": "Retired load uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -428,7 +428,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB. (precise Event)",
+        "BriefDescription": "Retired store uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -441,7 +441,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access. (precise Event)",
+        "BriefDescription": "Retired load uops with locked access.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -453,34 +453,32 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "Errata": "HSD29, HSM30",
-        "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "Errata": "HSD29, HSM30",
         "L1_Hit_Indication": "1",
-        "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops. (precise Event)",
+        "BriefDescription": "All retired load uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -492,14 +490,13 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "All retired store uops. (precise Event)",
+        "BriefDescription": "All retired store uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "Errata": "HSD29, HSM30",
         "L1_Hit_Indication": "1",
-        "PublicDescription": "This event counts all store uops retired. This is a precise event.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -530,13 +527,13 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "Retired load uops with L3 cache hits as data sources.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -549,19 +546,20 @@
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "Errata": "HSM30",
-        "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "Retired load uops missed L1 cache as data sources.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
+        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "Errata": "HSD29, HSM30",
+        "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -574,6 +572,7 @@
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
+        "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -604,26 +603,24 @@
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
@@ -642,19 +639,20 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
+        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "HSD74, HSD29, HSD25, HSM30",
-        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -666,7 +664,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -678,7 +676,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x20",
-        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -833,7 +831,6 @@
         "BriefDescription": "Split locks in SQ",
         "Counter": "0,1,2,3",
         "EventName": "SQ_MISC.SPLIT_LOCK",
-        "PublicDescription": "",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -841,12 +838,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0001",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -854,12 +851,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0001",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -867,12 +864,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -880,12 +877,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -893,12 +890,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0004",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -906,12 +903,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0004",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -919,12 +916,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3",
-        "MSRValue": "0x3f803c0010",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -932,12 +929,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3",
-        "MSRValue": "0x3f803c0020",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -945,12 +942,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3",
-        "MSRValue": "0x3f803c0040",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
+        "MSRValue": "0x3F803C0040",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -958,12 +955,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3",
-        "MSRValue": "0x3f803c0080",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -971,12 +968,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
-        "MSRValue": "0x3f803c0100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -984,12 +981,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
-        "MSRValue": "0x3f803c0200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -997,12 +994,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1010,12 +1007,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1023,12 +1020,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1036,12 +1033,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1049,12 +1046,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0244",
+        "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1062,12 +1059,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1075,12 +1072,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1088,12 +1085,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that hit in the L3",
-        "MSRValue": "0x3f803c8fff",
+        "BriefDescription": "Counts all requests hit in the L3",
+        "MSRValue": "0x3F803C8FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index 5ab5c78fe580..e5aac148c941 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -1,158 +1,340 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/memory.json b/tools/perf/pmu-events/arch/x86/haswellx/memory.json
index 56b0f24b8029..a42d5ce86b6f 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/memory.json
@@ -291,7 +291,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 4.",
+        "BriefDescription": "Randomly selected loads with latency value being above 4.",
         "PEBS": "2",
         "MSRValue": "0x4",
         "Counter": "3",
@@ -305,7 +305,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 8.",
+        "BriefDescription": "Randomly selected loads with latency value being above 8.",
         "PEBS": "2",
         "MSRValue": "0x8",
         "Counter": "3",
@@ -319,7 +319,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 16.",
+        "BriefDescription": "Randomly selected loads with latency value being above 16.",
         "PEBS": "2",
         "MSRValue": "0x10",
         "Counter": "3",
@@ -333,7 +333,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 32.",
+        "BriefDescription": "Randomly selected loads with latency value being above 32.",
         "PEBS": "2",
         "MSRValue": "0x20",
         "Counter": "3",
@@ -347,7 +347,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 64.",
+        "BriefDescription": "Randomly selected loads with latency value being above 64.",
         "PEBS": "2",
         "MSRValue": "0x40",
         "Counter": "3",
@@ -361,7 +361,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 128.",
+        "BriefDescription": "Randomly selected loads with latency value being above 128.",
         "PEBS": "2",
         "MSRValue": "0x80",
         "Counter": "3",
@@ -375,7 +375,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 256.",
+        "BriefDescription": "Randomly selected loads with latency value being above 256.",
         "PEBS": "2",
         "MSRValue": "0x100",
         "Counter": "3",
@@ -389,7 +389,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 512.",
+        "BriefDescription": "Randomly selected loads with latency value being above 512.",
         "PEBS": "2",
         "MSRValue": "0x200",
         "Counter": "3",
@@ -404,12 +404,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00001",
+        "BriefDescription": "Counts demand data reads miss in the L3",
+        "MSRValue": "0x3FBFC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -417,12 +417,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -430,12 +430,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
-        "MSRValue": "0x3fbfc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
+        "MSRValue": "0x3FBFC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -443,12 +443,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -456,12 +456,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -469,12 +469,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00004",
+        "BriefDescription": "Counts all demand code reads miss in the L3",
+        "MSRValue": "0x3FBFC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -482,12 +482,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -495,12 +495,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00010",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
+        "MSRValue": "0x3FBFC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -508,12 +508,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00020",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -521,12 +521,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00040",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
+        "MSRValue": "0x3FBFC00040",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -534,12 +534,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00080",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
+        "MSRValue": "0x3FBFC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -547,12 +547,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -560,12 +560,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
+        "MSRValue": "0x3FBFC00200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -573,12 +573,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
+        "MSRValue": "0x3FBFC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -586,12 +586,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -599,12 +599,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063f800091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063F800091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -612,12 +612,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -625,12 +625,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x083fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x083FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -638,12 +638,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00122",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -651,12 +651,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -664,12 +664,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00244",
+        "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
+        "MSRValue": "0x3FBFC00244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -677,12 +677,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -690,12 +690,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
-        "MSRValue": "0x3fbfc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
+        "MSRValue": "0x3FBFC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -703,12 +703,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
-        "MSRValue": "0x06004007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
+        "MSRValue": "0x06004007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -716,12 +716,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063f8007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063F8007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -729,12 +729,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -742,12 +742,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x083fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x083FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -755,12 +755,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that miss in the L3",
-        "MSRValue": "0x3fbfc08fff",
+        "BriefDescription": "Counts all requests miss in the L3",
+        "MSRValue": "0x3FBFC08FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
index 8a18bfe9e3e4..26f2888341ee 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -11,7 +10,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -21,7 +19,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -31,7 +28,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -1098,6 +1094,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
+        "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1142,6 +1139,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1201,6 +1199,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "PublicDescription": "Counts the number of conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1241,6 +1240,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PublicDescription": "Counts the number of near return instructions retired.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1261,6 +1261,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Number of near taken branches retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1312,6 +1313,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
index 999a01bc6467..5f6cb2abc384 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
@@ -1012,7 +1012,7 @@
         "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address ",
+        "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1036,7 +1036,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data reads ",
+        "BriefDescription": "Counts all demand data reads",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1048,7 +1048,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand rfo's ",
+        "BriefDescription": "Counts all demand rfo's",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1084,7 +1084,7 @@
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch prefetch RFOs ",
+        "BriefDescription": "Counts all demand & prefetch prefetch RFOs",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1096,7 +1096,7 @@
         "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo references (demand & prefetch) ",
+        "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)",
         "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index 7c2679514efb..bc4d5fc284a0 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -1,164 +1,340 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
index 0afbfd95ea30..2a0aad91d83d 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -9,7 +8,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -19,7 +17,6 @@
     },
     {
         "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -29,7 +26,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
index 7c2679514efb..f3874b5f9995 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -1,164 +1,346 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
index 0afbfd95ea30..2a0aad91d83d 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -9,7 +8,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -19,7 +17,6 @@
     },
     {
         "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -29,7 +26,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/cache.json b/tools/perf/pmu-events/arch/x86/jaketown/cache.json
index ee22e4a5e30d..52dc6ef40e63 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/cache.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/cache.json
@@ -31,7 +31,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x41",
@@ -42,7 +42,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x42",
@@ -179,7 +179,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.  ",
+        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
         "EventCode": "0x51",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
index fd7d7c438226..98c73e430b05 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -1,140 +1,232 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json
index 34a519d9bfa0..783a5b4a67b1 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
-        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.",
         "Counter": "Fixed counter 1",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -10,8 +9,7 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -20,8 +18,7 @@
         "CounterHTOff": "Fixed counter 2"
     },
     {
-        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "Counter": "Fixed counter 3",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -778,7 +775,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store.  See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store.  See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
         "EventCode": "0x03",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -1098,7 +1095,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "AnyThread": "1",
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json
index e434ec723001..e847b0fd696d 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json
@@ -32,16 +32,16 @@
         "BriefDescription": "Counts the number of L2 cache misses"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses. ",
+        "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.",
         "EventCode": "0x86",
         "Counter": "0,1",
         "UMask": "0x4",
         "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses. "
+        "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses."
     },
     {
-        "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted. ",
+        "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted.",
         "EventCode": "0x04",
         "Counter": "0,1",
         "UMask": "0x1",
@@ -115,29 +115,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000070 ",
+        "MSRValue": "0x4000000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400070 ",
+        "MSRValue": "0x1000400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400070 ",
+        "MSRValue": "0x0800400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_E_F",
@@ -148,29 +148,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080070 ",
+        "MSRValue": "0x1000080070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080070 ",
+        "MSRValue": "0x0800080070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010070 ",
+        "MSRValue": "0x0000010070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.ANY_RESPONSE",
@@ -181,29 +181,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x40000032f7 ",
+        "MSRValue": "0x40000032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts any Read request  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x10004032f7 ",
+        "MSRValue": "0x10004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x08004032f7 ",
+        "MSRValue": "0x08004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_E_F",
@@ -214,29 +214,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x10000832f7 ",
+        "MSRValue": "0x10000832f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x08000832f7 ",
+        "MSRValue": "0x08000832f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00000132f7 ",
+        "MSRValue": "0x00000132f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
@@ -247,29 +247,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000044 ",
+        "MSRValue": "0x4000000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400044 ",
+        "MSRValue": "0x1000400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400044 ",
+        "MSRValue": "0x0800400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_E_F",
@@ -280,29 +280,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080044 ",
+        "MSRValue": "0x1000080044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080044 ",
+        "MSRValue": "0x0800080044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010044 ",
+        "MSRValue": "0x0000010044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.ANY_RESPONSE",
@@ -313,29 +313,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000022 ",
+        "MSRValue": "0x4000000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400022 ",
+        "MSRValue": "0x1000400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400022 ",
+        "MSRValue": "0x0800400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_E_F",
@@ -346,29 +346,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080022 ",
+        "MSRValue": "0x1000080022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080022 ",
+        "MSRValue": "0x0800080022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010022 ",
+        "MSRValue": "0x0000010022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
@@ -379,29 +379,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000003091 ",
+        "MSRValue": "0x4000003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000403091 ",
+        "MSRValue": "0x1000403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800403091 ",
+        "MSRValue": "0x0800403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_E_F",
@@ -412,29 +412,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000083091 ",
+        "MSRValue": "0x1000083091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800083091 ",
+        "MSRValue": "0x0800083091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000013091 ",
+        "MSRValue": "0x0000013091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
@@ -445,29 +445,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000008000 ",
+        "MSRValue": "0x4000008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000408000 ",
+        "MSRValue": "0x1000408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800408000 ",
+        "MSRValue": "0x0800408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_E_F",
@@ -478,29 +478,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000088000 ",
+        "MSRValue": "0x1000088000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800088000 ",
+        "MSRValue": "0x0800088000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000018000 ",
+        "MSRValue": "0x0000018000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
@@ -511,7 +511,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000014800 ",
+        "MSRValue": "0x0000014800",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
@@ -522,7 +522,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000014000 ",
+        "MSRValue": "0x0000014000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
@@ -533,29 +533,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000002000 ",
+        "MSRValue": "0x4000002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000402000 ",
+        "MSRValue": "0x1000402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800402000 ",
+        "MSRValue": "0x0800402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_E_F",
@@ -566,29 +566,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000082000 ",
+        "MSRValue": "0x1000082000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800082000 ",
+        "MSRValue": "0x0800082000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000012000 ",
+        "MSRValue": "0x0000012000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
@@ -599,29 +599,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000001000 ",
+        "MSRValue": "0x4000001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000401000 ",
+        "MSRValue": "0x1000401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800401000 ",
+        "MSRValue": "0x0800401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_E_F",
@@ -632,29 +632,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000081000 ",
+        "MSRValue": "0x1000081000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800081000 ",
+        "MSRValue": "0x0800081000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000011000 ",
+        "MSRValue": "0x0000011000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE",
@@ -665,7 +665,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010800 ",
+        "MSRValue": "0x0000010800",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
@@ -676,29 +676,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000400 ",
+        "MSRValue": "0x4000000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400400 ",
+        "MSRValue": "0x1000400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400400 ",
+        "MSRValue": "0x0800400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_E_F",
@@ -709,29 +709,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080400 ",
+        "MSRValue": "0x1000080400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080400 ",
+        "MSRValue": "0x0800080400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010400 ",
+        "MSRValue": "0x0000010400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
@@ -742,29 +742,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000200 ",
+        "MSRValue": "0x4000000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400200 ",
+        "MSRValue": "0x1000400200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400200 ",
+        "MSRValue": "0x0800400200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_E_F",
@@ -775,29 +775,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080200 ",
+        "MSRValue": "0x1000080200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080200 ",
+        "MSRValue": "0x0800080200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010200 ",
+        "MSRValue": "0x0000010200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.ANY_RESPONSE",
@@ -808,18 +808,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400100 ",
+        "MSRValue": "0x1000400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400100 ",
+        "MSRValue": "0x0800400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_E_F",
@@ -830,29 +830,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080100 ",
+        "MSRValue": "0x1000080100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080100 ",
+        "MSRValue": "0x0800080100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010100 ",
+        "MSRValue": "0x0000010100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
@@ -863,29 +863,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000080 ",
+        "MSRValue": "0x4000000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400080 ",
+        "MSRValue": "0x1000400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400080 ",
+        "MSRValue": "0x0800400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_E_F",
@@ -896,29 +896,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080080 ",
+        "MSRValue": "0x1000080080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080080 ",
+        "MSRValue": "0x0800080080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010080 ",
+        "MSRValue": "0x0000010080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
@@ -929,29 +929,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000040 ",
+        "MSRValue": "0x4000000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400040 ",
+        "MSRValue": "0x1000400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400040 ",
+        "MSRValue": "0x0800400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_E_F",
@@ -962,29 +962,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080040 ",
+        "MSRValue": "0x1000080040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080040 ",
+        "MSRValue": "0x0800080040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010040 ",
+        "MSRValue": "0x0000010040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE",
@@ -995,18 +995,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400020 ",
+        "MSRValue": "0x1000400020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400020 ",
+        "MSRValue": "0x0800400020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_E_F",
@@ -1017,29 +1017,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080020 ",
+        "MSRValue": "0x1000080020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080020 ",
+        "MSRValue": "0x0800080020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000020020 ",
+        "MSRValue": "0x0000020020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE",
@@ -1050,7 +1050,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010020 ",
+        "MSRValue": "0x0000010020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
@@ -1061,29 +1061,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000004 ",
+        "MSRValue": "0x4000000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400004 ",
+        "MSRValue": "0x1000400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400004 ",
+        "MSRValue": "0x0800400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_E_F",
@@ -1094,29 +1094,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080004 ",
+        "MSRValue": "0x1000080004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080004 ",
+        "MSRValue": "0x0800080004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010004 ",
+        "MSRValue": "0x0000010004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
@@ -1127,29 +1127,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000002 ",
+        "MSRValue": "0x4000000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400002 ",
+        "MSRValue": "0x1000400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400002 ",
+        "MSRValue": "0x0800400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_E_F",
@@ -1160,29 +1160,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080002 ",
+        "MSRValue": "0x1000080002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080002 ",
+        "MSRValue": "0x0800080002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010002 ",
+        "MSRValue": "0x0000010002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
@@ -1193,29 +1193,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000001 ",
+        "MSRValue": "0x4000000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400001 ",
+        "MSRValue": "0x1000400001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400001 ",
+        "MSRValue": "0x0800400001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_E_F",
@@ -1226,29 +1226,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080001 ",
+        "MSRValue": "0x1000080001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080001 ",
+        "MSRValue": "0x0800080001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010001 ",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
@@ -1259,722 +1259,722 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000001 ",
+        "MSRValue": "0x0002000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000002 ",
+        "MSRValue": "0x0002000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000004 ",
+        "MSRValue": "0x0002000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000020 ",
+        "MSRValue": "0x0002000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000080 ",
+        "MSRValue": "0x0002000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000100 ",
+        "MSRValue": "0x0002000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000200 ",
+        "MSRValue": "0x0002000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000400 ",
+        "MSRValue": "0x0002000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002001000 ",
+        "MSRValue": "0x0002001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002002000 ",
+        "MSRValue": "0x0002002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002008000 ",
+        "MSRValue": "0x0002008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002003091 ",
+        "MSRValue": "0x0002003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000022 ",
+        "MSRValue": "0x0002000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000044 ",
+        "MSRValue": "0x0002000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00020032f7 ",
+        "MSRValue": "0x00020032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000070 ",
+        "MSRValue": "0x0002000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000001 ",
+        "MSRValue": "0x0004000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000002 ",
+        "MSRValue": "0x0004000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000004 ",
+        "MSRValue": "0x0004000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000020 ",
+        "MSRValue": "0x0004000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000040 ",
+        "MSRValue": "0x0004000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000080 ",
+        "MSRValue": "0x0004000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000100 ",
+        "MSRValue": "0x0004000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000200 ",
+        "MSRValue": "0x0004000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000400 ",
+        "MSRValue": "0x0004000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004001000 ",
+        "MSRValue": "0x0004001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004002000 ",
+        "MSRValue": "0x0004002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004008000 ",
+        "MSRValue": "0x0004008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004003091 ",
+        "MSRValue": "0x0004003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000022 ",
+        "MSRValue": "0x0004000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000044 ",
+        "MSRValue": "0x0004000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00040032f7 ",
+        "MSRValue": "0x00040032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000070 ",
+        "MSRValue": "0x0004000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000001 ",
+        "MSRValue": "0x0008000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000002 ",
+        "MSRValue": "0x0008000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000004 ",
+        "MSRValue": "0x0008000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000020 ",
+        "MSRValue": "0x0008000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000080 ",
+        "MSRValue": "0x0008000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000100 ",
+        "MSRValue": "0x0008000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000200 ",
+        "MSRValue": "0x0008000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000400 ",
+        "MSRValue": "0x0008000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008001000 ",
+        "MSRValue": "0x0008001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008002000 ",
+        "MSRValue": "0x0008002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008008000 ",
+        "MSRValue": "0x0008008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008003091 ",
+        "MSRValue": "0x0008003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000022 ",
+        "MSRValue": "0x0008000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000044 ",
+        "MSRValue": "0x0008000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00080032f7 ",
+        "MSRValue": "0x00080032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000001 ",
+        "MSRValue": "0x0010000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000002 ",
+        "MSRValue": "0x0010000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000004 ",
+        "MSRValue": "0x0010000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000020 ",
+        "MSRValue": "0x0010000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000040 ",
+        "MSRValue": "0x0010000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000080 ",
+        "MSRValue": "0x0010000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000100 ",
+        "MSRValue": "0x0010000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000200 ",
+        "MSRValue": "0x0010000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000400 ",
+        "MSRValue": "0x0010000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010001000 ",
+        "MSRValue": "0x0010001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010002000 ",
+        "MSRValue": "0x0010002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010008000 ",
+        "MSRValue": "0x0010008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010003091 ",
+        "MSRValue": "0x0010003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000022 ",
+        "MSRValue": "0x0010000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000044 ",
+        "MSRValue": "0x0010000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00100032f7 ",
+        "MSRValue": "0x00100032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000070 ",
+        "MSRValue": "0x0010000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180002 ",
+        "MSRValue": "0x1800180002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE",
@@ -1985,7 +1985,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180004 ",
+        "MSRValue": "0x1800180004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE",
@@ -1996,7 +1996,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180020 ",
+        "MSRValue": "0x1800180020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE",
@@ -2007,7 +2007,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180040 ",
+        "MSRValue": "0x1800180040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE",
@@ -2018,7 +2018,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180080 ",
+        "MSRValue": "0x1800180080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE",
@@ -2029,7 +2029,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180100 ",
+        "MSRValue": "0x1800180100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE",
@@ -2040,7 +2040,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180200 ",
+        "MSRValue": "0x1800180200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE",
@@ -2051,7 +2051,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180400 ",
+        "MSRValue": "0x1800180400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE",
@@ -2062,7 +2062,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800181000 ",
+        "MSRValue": "0x1800181000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE",
@@ -2073,7 +2073,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800182000 ",
+        "MSRValue": "0x1800182000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE",
@@ -2084,7 +2084,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800188000 ",
+        "MSRValue": "0x1800188000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE",
@@ -2095,7 +2095,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800183091 ",
+        "MSRValue": "0x1800183091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE",
@@ -2106,7 +2106,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180022 ",
+        "MSRValue": "0x1800180022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE",
@@ -2117,7 +2117,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180044 ",
+        "MSRValue": "0x1800180044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE",
@@ -2128,7 +2128,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x18001832f7 ",
+        "MSRValue": "0x18001832f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE",
@@ -2139,7 +2139,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180070 ",
+        "MSRValue": "0x1800180070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE",
@@ -2150,7 +2150,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400002 ",
+        "MSRValue": "0x1800400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE",
@@ -2161,7 +2161,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400004 ",
+        "MSRValue": "0x1800400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE",
@@ -2172,7 +2172,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400040 ",
+        "MSRValue": "0x1800400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE",
@@ -2183,7 +2183,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400080 ",
+        "MSRValue": "0x1800400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE",
@@ -2194,7 +2194,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400100 ",
+        "MSRValue": "0x1800400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE",
@@ -2205,7 +2205,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400400 ",
+        "MSRValue": "0x1800400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE",
@@ -2216,7 +2216,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800401000 ",
+        "MSRValue": "0x1800401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE",
@@ -2227,7 +2227,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800402000 ",
+        "MSRValue": "0x1800402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE",
@@ -2238,7 +2238,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800408000 ",
+        "MSRValue": "0x1800408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE",
@@ -2249,7 +2249,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800403091 ",
+        "MSRValue": "0x1800403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE",
@@ -2260,7 +2260,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400022 ",
+        "MSRValue": "0x1800400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE",
@@ -2271,7 +2271,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400044 ",
+        "MSRValue": "0x1800400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE",
@@ -2282,7 +2282,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x18004032f7 ",
+        "MSRValue": "0x18004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE",
@@ -2293,7 +2293,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400070 ",
+        "MSRValue": "0x1800400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE",
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json
index 700652566200..c6bb16ba0f86 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json
@@ -9,18 +9,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400070 ",
+        "MSRValue": "0x0100400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200070 ",
+        "MSRValue": "0x0080200070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_NEAR",
@@ -31,18 +31,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000070 ",
+        "MSRValue": "0x0101000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800070 ",
+        "MSRValue": "0x0080800070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_NEAR",
@@ -53,18 +53,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01004032f7 ",
+        "MSRValue": "0x01004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts any Read request  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00802032f7 ",
+        "MSRValue": "0x00802032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_NEAR",
@@ -75,18 +75,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01010032f7 ",
+        "MSRValue": "0x01010032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts any Read request  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00808032f7 ",
+        "MSRValue": "0x00808032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_NEAR",
@@ -97,18 +97,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400044 ",
+        "MSRValue": "0x0100400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200044 ",
+        "MSRValue": "0x0080200044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_NEAR",
@@ -119,18 +119,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000044 ",
+        "MSRValue": "0x0101000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800044 ",
+        "MSRValue": "0x0080800044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_NEAR",
@@ -141,18 +141,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400022 ",
+        "MSRValue": "0x0100400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200022 ",
+        "MSRValue": "0x0080200022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_NEAR",
@@ -163,18 +163,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000022 ",
+        "MSRValue": "0x0101000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800022 ",
+        "MSRValue": "0x0080800022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_NEAR",
@@ -185,18 +185,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100403091 ",
+        "MSRValue": "0x0100403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080203091 ",
+        "MSRValue": "0x0080203091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_NEAR",
@@ -207,18 +207,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101003091 ",
+        "MSRValue": "0x0101003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080803091 ",
+        "MSRValue": "0x0080803091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_NEAR",
@@ -229,18 +229,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100408000 ",
+        "MSRValue": "0x0100408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080208000 ",
+        "MSRValue": "0x0080208000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_NEAR",
@@ -251,18 +251,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101008000 ",
+        "MSRValue": "0x0101008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts any request that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080808000 ",
+        "MSRValue": "0x0080808000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_NEAR",
@@ -273,18 +273,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100402000 ",
+        "MSRValue": "0x0100402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080202000 ",
+        "MSRValue": "0x0080202000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_NEAR",
@@ -295,18 +295,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101002000 ",
+        "MSRValue": "0x0101002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080802000 ",
+        "MSRValue": "0x0080802000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_NEAR",
@@ -317,18 +317,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100401000 ",
+        "MSRValue": "0x0100401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080201000 ",
+        "MSRValue": "0x0080201000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_NEAR",
@@ -339,18 +339,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101001000 ",
+        "MSRValue": "0x0101001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080801000 ",
+        "MSRValue": "0x0080801000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_NEAR",
@@ -361,18 +361,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400400 ",
+        "MSRValue": "0x0100400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200400 ",
+        "MSRValue": "0x0080200400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_NEAR",
@@ -383,18 +383,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000400 ",
+        "MSRValue": "0x0101000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800400 ",
+        "MSRValue": "0x0080800400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_NEAR",
@@ -405,18 +405,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400200 ",
+        "MSRValue": "0x0100400200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200200 ",
+        "MSRValue": "0x0080200200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_NEAR",
@@ -427,18 +427,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000200 ",
+        "MSRValue": "0x0101000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800200 ",
+        "MSRValue": "0x0080800200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_NEAR",
@@ -449,18 +449,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400100 ",
+        "MSRValue": "0x0100400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_FAR",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200100 ",
+        "MSRValue": "0x0080200100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_NEAR",
@@ -471,18 +471,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000100 ",
+        "MSRValue": "0x0101000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_FAR",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800100 ",
+        "MSRValue": "0x0080800100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_NEAR",
@@ -493,7 +493,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x2000020080 ",
+        "MSRValue": "0x2000020080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.NON_DRAM",
@@ -504,18 +504,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400080 ",
+        "MSRValue": "0x0100400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200080 ",
+        "MSRValue": "0x0080200080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_NEAR",
@@ -526,18 +526,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000080 ",
+        "MSRValue": "0x0101000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800080 ",
+        "MSRValue": "0x0080800080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_NEAR",
@@ -548,18 +548,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400040 ",
+        "MSRValue": "0x0100400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200040 ",
+        "MSRValue": "0x0080200040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_NEAR",
@@ -570,18 +570,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000040 ",
+        "MSRValue": "0x0101000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800040 ",
+        "MSRValue": "0x0080800040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_NEAR",
@@ -592,7 +592,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x2000020020 ",
+        "MSRValue": "0x2000020020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.NON_DRAM",
@@ -603,18 +603,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400020 ",
+        "MSRValue": "0x0100400020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200020 ",
+        "MSRValue": "0x0080200020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_NEAR",
@@ -625,18 +625,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000020 ",
+        "MSRValue": "0x0101000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800020 ",
+        "MSRValue": "0x0080800020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_NEAR",
@@ -647,18 +647,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400004 ",
+        "MSRValue": "0x0100400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200004 ",
+        "MSRValue": "0x0080200004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_NEAR",
@@ -669,18 +669,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000004 ",
+        "MSRValue": "0x0101000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800004 ",
+        "MSRValue": "0x0080800004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_NEAR",
@@ -691,18 +691,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400002 ",
+        "MSRValue": "0x0100400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200002 ",
+        "MSRValue": "0x0080200002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_NEAR",
@@ -713,18 +713,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000002 ",
+        "MSRValue": "0x0101000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800002 ",
+        "MSRValue": "0x0080800002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_NEAR",
@@ -735,18 +735,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400001 ",
+        "MSRValue": "0x0100400001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200001 ",
+        "MSRValue": "0x0080200001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_NEAR",
@@ -757,18 +757,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000001 ",
+        "MSRValue": "0x0101000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800001 ",
+        "MSRValue": "0x0080800001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_NEAR",
@@ -779,7 +779,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600001 ",
+        "MSRValue": "0x0180600001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM",
@@ -790,7 +790,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600002 ",
+        "MSRValue": "0x0180600002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM",
@@ -801,7 +801,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600004 ",
+        "MSRValue": "0x0180600004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM",
@@ -812,7 +812,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600020 ",
+        "MSRValue": "0x0180600020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM",
@@ -823,7 +823,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600080 ",
+        "MSRValue": "0x0180600080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM",
@@ -834,7 +834,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600100 ",
+        "MSRValue": "0x0180600100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM",
@@ -845,7 +845,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600200 ",
+        "MSRValue": "0x0180600200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM",
@@ -856,7 +856,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600400 ",
+        "MSRValue": "0x0180600400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM",
@@ -867,7 +867,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180601000 ",
+        "MSRValue": "0x0180601000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM",
@@ -878,7 +878,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180608000 ",
+        "MSRValue": "0x0180608000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM",
@@ -889,7 +889,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180603091 ",
+        "MSRValue": "0x0180603091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM",
@@ -900,7 +900,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600022 ",
+        "MSRValue": "0x0180600022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM",
@@ -911,7 +911,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600044 ",
+        "MSRValue": "0x0180600044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM",
@@ -922,7 +922,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01806032f7 ",
+        "MSRValue": "0x01806032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM",
@@ -933,7 +933,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600070 ",
+        "MSRValue": "0x0180600070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM",
@@ -944,7 +944,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800001 ",
+        "MSRValue": "0x0181800001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR",
@@ -955,7 +955,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800002 ",
+        "MSRValue": "0x0181800002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR",
@@ -966,7 +966,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800004 ",
+        "MSRValue": "0x0181800004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR",
@@ -977,7 +977,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800020 ",
+        "MSRValue": "0x0181800020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR",
@@ -988,7 +988,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800040 ",
+        "MSRValue": "0x0181800040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR",
@@ -999,7 +999,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800080 ",
+        "MSRValue": "0x0181800080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR",
@@ -1010,7 +1010,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800200 ",
+        "MSRValue": "0x0181800200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR",
@@ -1021,7 +1021,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800400 ",
+        "MSRValue": "0x0181800400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR",
@@ -1032,7 +1032,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181801000 ",
+        "MSRValue": "0x0181801000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR",
@@ -1043,7 +1043,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181802000 ",
+        "MSRValue": "0x0181802000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR",
@@ -1054,7 +1054,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181808000 ",
+        "MSRValue": "0x0181808000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR",
@@ -1065,7 +1065,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181803091 ",
+        "MSRValue": "0x0181803091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR",
@@ -1076,7 +1076,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800022 ",
+        "MSRValue": "0x0181800022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR",
@@ -1087,7 +1087,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800044 ",
+        "MSRValue": "0x0181800044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR",
@@ -1098,7 +1098,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01818032f7 ",
+        "MSRValue": "0x01818032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR",
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json
index bb5494cfb5ae..92e4ef2e22c6 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json
@@ -144,7 +144,7 @@
         "BriefDescription": "Counts the number of micro-ops retired that are from the complex flows issued by the micro-sequencer (MS)."
     },
     {
-        "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists. ",
+        "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists.",
         "EventCode": "0xC2",
         "Counter": "0,1",
         "UMask": "0x10",
@@ -218,7 +218,7 @@
         "UMask": "0x20",
         "EventName": "NO_ALLOC_CYCLES.RAT_STALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted.  "
+        "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted."
     },
     {
         "PublicDescription": "This event counts the number of core cycles when no uops are allocated, the instruction queue is empty and the alloc pipe is stalled waiting for instructions to be fetched.",
@@ -251,7 +251,7 @@
         "UMask": "0x1f",
         "EventName": "RS_FULL_STALL.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full. "
+        "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full."
     },
     {
         "EventCode": "0xC0",
@@ -268,11 +268,10 @@
         "UMask": "0x1",
         "EventName": "CYCLES_DIV_BUSY.ALL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles the number of core cycles when divider is busy.  Does not imply a stall waiting for the divider.  "
+        "BriefDescription": "Cycles the number of core cycles when divider is busy.  Does not imply a stall waiting for the divider."
     },
     {
         "PublicDescription": "This event counts the number of instructions that retire.  For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires.  The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -296,8 +295,7 @@
         "BriefDescription": "Counts the number of unhalted reference clock cycles"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter\r\n",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -305,7 +303,6 @@
         "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 3",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -343,7 +340,7 @@
         "UMask": "0x1",
         "EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store ",
+        "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store",
         "Data_LA": "1"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json
index f31594507f8c..9e493977771f 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json
@@ -36,7 +36,7 @@
         "EdgeDetect": "1"
     },
     {
-        "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress. ",
+        "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress.",
         "EventCode": "0x05",
         "Counter": "0,1",
         "UMask": "0x2",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
index 16b04a20bc12..bb79e89c2049 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
@@ -1,207 +1,200 @@
 [
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x11",
-        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that miss the STLB.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x12",
-        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that miss the STLB.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with locked access.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that miss L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xc",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests to L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of load uops retired",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load uops.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x10",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of store uops retired.",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store uops.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x20",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache misses when fetching instructions.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x30",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 code requests.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x40",
+        "EventName": "L2_RQSTS.PF_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x80",
+        "EventName": "L2_RQSTS.PF_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xc0",
+        "EventName": "L2_RQSTS.ALL_PF",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests from L2 hardware prefetchers.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD2",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a non-modified state.",
-        "EventCode": "0xD2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_STORE_LOCK_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that miss cache lines.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.",
-        "EventCode": "0xD2",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_STORE_LOCK_RQSTS.HIT_E",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that hit cache lines in E state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD2",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_STORE_LOCK_RQSTS.HIT_M",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that hit cache lines in M state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired demand loads that missed the  last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops.",
-        "EventCode": "0xD4",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xf",
+        "EventName": "L2_STORE_LOCK_RQSTS.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that access cache lines in any state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.  ",
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "L1D.REPLACEMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D data line replacements.",
+        "EventName": "L2_L1D_WB_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "L1D.ALLOCATED_IN_M",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Allocated L1D data cache lines in M state.",
+        "EventName": "L2_L1D_WB_RQSTS.HIT_S",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "L1D.EVICTION",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D data cache lines in M state evicted due to replacement.",
+        "EventName": "L2_L1D_WB_RQSTS.HIT_E",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "L1D.ALL_M_REPLACEMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.",
+        "EventName": "L2_L1D_WB_RQSTS.HIT_M",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf",
+        "EventName": "L2_L1D_WB_RQSTS.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Core-originated cacheable demand requests missed LLC.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4f",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -224,12 +217,61 @@
         "CounterHTOff": "2"
     },
     {
-        "EventCode": "0x63",
+        "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when L1D is locked.",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "L1D.REPLACEMENT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "L1D data line replacements.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "L1D.ALLOCATED_IN_M",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Allocated L1D data cache lines in M state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "L1D.EVICTION",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "L1D data cache lines in M state evicted due to replacement.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "L1D.ALL_M_REPLACEMENT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -254,6 +296,16 @@
     {
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
         "SampleAfterValue": "2000003",
@@ -263,6 +315,16 @@
     {
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "SampleAfterValue": "2000003",
@@ -280,6 +342,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x63",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when L1D is locked.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xB0",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -325,148 +396,182 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
+        "EventCode": "0xBF",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache.",
+        "UMask": "0x5",
+        "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that hit L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x11",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x12",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x21",
+        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache misses when fetching instructions.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x41",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "L2_RQSTS.PF_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x42",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of load uops retired (Precise Event)",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "L2_RQSTS.PF_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x81",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "All retired load uops. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of store uops retired. (Precise Event - PEBS)",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "All retired store uops. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "L2_STORE_LOCK_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that miss cache lines.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_STORE_LOCK_RQSTS.HIT_E",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that hit cache lines in E state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required. (Precise Event - PEBS)",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "L2_STORE_LOCK_RQSTS.HIT_M",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that hit cache lines in M state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
+        "SampleAfterValue": "50021",
+        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0xf",
-        "EventName": "L2_STORE_LOCK_RQSTS.ALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that access cache lines in any state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x40",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "L2_L1D_WB_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a non-modified state. (Precise Event - PEBS)",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "L2_L1D_WB_RQSTS.HIT_S",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2. (Precise Event - PEBS)",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "L2_L1D_WB_RQSTS.HIT_E",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "L2_L1D_WB_RQSTS.HIT_M",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired demand loads that missed the  last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops. (Precise Event - PEBS)",
+        "EventCode": "0xD4",
         "Counter": "0,1,2,3",
-        "UMask": "0xf",
-        "EventName": "L2_L1D_WB_RQSTS.ALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xF0",
@@ -623,24 +728,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x2E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "LONGEST_LAT_CACHE.MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests missed LLC.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x2E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xF4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -650,93 +737,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "L2_RQSTS.ALL_RFO",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests to L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 code requests.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xc0",
-        "EventName": "L2_RQSTS.ALL_PF",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from L2 hardware prefetchers.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xBF",
-        "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0244",
         "Counter": "0,1,2,3",
@@ -1825,7 +1825,7 @@
         "EventName": "OFFCORE_RESPONSE.DATA_IN.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1837,7 +1837,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT_M.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM",
+        "BriefDescription": "REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1849,7 +1849,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_IFETCH.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1861,7 +1861,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1873,7 +1873,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
index 982eda48785e..ce26537c7d47 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
@@ -1,68 +1,5 @@
 [
     {
-        "EventCode": "0xC1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OTHER_ASSISTS.AVX_STORE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "FP_ASSIST.X87_OUTPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to output value.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "FP_ASSIST.X87_INPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to input value.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "FP_ASSIST.SIMD_OUTPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to Output values.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "FP_ASSIST.SIMD_INPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to input values.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x10",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -126,6 +63,69 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xC1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "OTHER_ASSISTS.AVX_STORE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "FP_ASSIST.X87_OUTPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of X87 assists due to output value.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "FP_ASSIST.X87_INPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of X87 assists due to input value.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "FP_ASSIST.SIMD_OUTPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of SIMD FP assists due to Output values.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "FP_ASSIST.SIMD_INPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of SIMD FP assists due to input values.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
index 1b7b1dd36c68..e58ed14a204c 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
@@ -1,24 +1,5 @@
 [
     {
-        "EventCode": "0x80",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ICACHE.HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
-        "EventCode": "0x80",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ICACHE.MISSES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -39,159 +20,201 @@
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_UOPS",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.  See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more information.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled.  In the ideal case 4 uops can be delivered each cycle.  The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them.  This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
-        "EventCode": "0x9C",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "UMask": "0x10",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_DSB_OCCUR",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x9C",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "UMask": "0x18",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.",
         "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x9C",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "UMask": "0x18",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xAB",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "DSB2MITE_SWITCHES.COUNT",
+        "UMask": "0x20",
+        "EventName": "IDQ.MS_MITE_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline.  It excludes cycles when the back-end cannot  accept new micro-ops.  The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
-        "EventCode": "0xAB",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+        "UMask": "0x24",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xAC",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DSB_FILL.OTHER_CANCEL",
+        "UMask": "0x24",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.",
+        "BriefDescription": "Cycles MITE is delivering any Uop.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xAC",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "DSB_FILL.EXCEED_DSB_LINES",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.  See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more information.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_CYCLES",
+        "UMask": "0x3c",
+        "EventName": "IDQ.MITE_ALL_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
-        "CounterMask": "1",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x79",
+        "EventCode": "0x80",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_DSB_OCCUR",
+        "UMask": "0x1",
+        "EventName": "ICACHE.HIT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
-        "CounterMask": "1",
+        "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "ICACHE.MISSES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled.  In the ideal case 4 uops can be delivered each cycle.  The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them.  This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -223,83 +246,60 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
+        "EventCode": "0x9C",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x79",
+        "EventCode": "0xAB",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "UMask": "0x1",
+        "EventName": "DSB2MITE_SWITCHES.COUNT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering 4 Uops.",
-        "CounterMask": "4",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x79",
+        "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline.  It excludes cycles when the back-end cannot  accept new micro-ops.  The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
+        "EventCode": "0xAB",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "UMask": "0x2",
+        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering any Uop.",
-        "CounterMask": "1",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xAC",
         "Counter": "0,1,2,3",
-        "UMask": "0xa",
-        "EventName": "DSB_FILL.ALL_CANCEL",
+        "UMask": "0x2",
+        "EventName": "DSB_FILL.OTHER_CANCEL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.",
+        "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x9C",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x79",
+        "EventCode": "0xAC",
         "Counter": "0,1,2,3",
-        "UMask": "0x3c",
-        "EventName": "IDQ.MITE_ALL_UOPS",
+        "UMask": "0x8",
+        "EventName": "DSB_FILL.EXCEED_DSB_LINES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x79",
+        "EventCode": "0xAC",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
+        "UMask": "0xa",
+        "EventName": "DSB_FILL.ALL_CANCEL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "CounterMask": "1",
+        "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
index e6dfa89d00f3..78c1a987f9a2 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
@@ -1,5 +1,32 @@
 [
     {
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "MISALIGN_MEM_REF.LOADS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "MISALIGN_MEM_REF.STORES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBE",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "PAGE_WALKS.LLC_MISS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers.  Machine clears can have a significant performance impact if they are happening frequently.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -126,33 +153,6 @@
         "CounterHTOff": "3"
     },
     {
-        "EventCode": "0xBE",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "PAGE_WALKS.LLC_MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MISALIGN_MEM_REF.LOADS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MISALIGN_MEM_REF.STORES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x300400244",
         "Counter": "0,1,2,3",
@@ -367,7 +367,7 @@
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -379,7 +379,7 @@
         "EventName": "OFFCORE_RESPONSE.DATA_IN_SOCKET.LLC_MISS_LOCAL.ANY_LLC_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT",
+        "BriefDescription": "REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -391,7 +391,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_IFETCH.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -403,7 +403,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_DATA_RD.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -415,7 +415,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_IFETCH.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -427,7 +427,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -439,7 +439,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
index 64b195b82c50..874eb40a2e0f 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
@@ -9,6 +9,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x4E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "HW_PRE_REQ.DL1_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x5C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -38,15 +47,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x4E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "HW_PRE_REQ.DL1_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
index 34a519d9bfa0..b7150f65f16d 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
@@ -1,289 +1,307 @@
 [
     {
-        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "Counter": "Fixed counter 2",
+        "UMask": "0x3",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the core is not in halt state.",
+        "CounterHTOff": "Fixed counter 2"
+    },
+    {
+        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
     },
     {
-        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
-        "UMask": "0x3",
-        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
-    },
-    {
-        "EventCode": "0x88",
-        "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not taken macro-conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired macro-conditional branches.",
+        "UMask": "0x1",
+        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store.  See the table of not supported store forwards in the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.",
+        "UMask": "0x2",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.",
+        "UMask": "0x8",
+        "EventName": "LD_BLOCKS.NO_SR",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x88",
-        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.",
+        "UMask": "0x10",
+        "EventName": "LD_BLOCKS.ALL_BLOCK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K.  This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline.  The enhanced address check typically has a performance penalty of 5 cycles.",
+        "EventCode": "0x07",
         "Counter": "0,1,2,3",
-        "UMask": "0x90",
-        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired direct near calls.",
+        "UMask": "0x1",
+        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "False dependencies in MOB due to partial compare.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x07",
         "Counter": "0,1,2,3",
-        "UMask": "0xa0",
-        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired indirect calls.",
+        "UMask": "0x8",
+        "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc1",
-        "EventName": "BR_INST_EXEC.ALL_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired macro-conditional branches.",
+        "UMask": "0x3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc2",
-        "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.",
+        "UMask": "0x3",
+        "EdgeDetect": "1",
+        "EventName": "INT_MISC.RECOVERY_STALLS_COUNT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc4",
-        "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.",
+        "UMask": "0x3",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc8",
-        "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired indirect return branches.",
+        "UMask": "0x40",
+        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.",
+        "EventCode": "0x0E",
         "Counter": "0,1,2,3",
-        "UMask": "0xd0",
-        "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired direct near calls.",
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x0E",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x0E",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x14",
         "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.",
+        "UMask": "0x1",
+        "EventName": "ARITH.FPU_DIV_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when divider is busy executing divide operations.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "PublicDescription": "This event counts the number of the divide operations executed.",
+        "EventCode": "0x14",
         "Counter": "0,1,2,3",
-        "UMask": "0x88",
-        "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "ARITH.FPU_DIV",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Divide operations executed.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x90",
-        "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted direct near calls.",
+        "UMask": "0x0",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Thread cycles when thread is not in halt state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xa0",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xc1",
-        "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xc4",
-        "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Mispredicted indirect branches excluding calls and returns.",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xd0",
-        "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired mispredicted direct near calls.",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Thread cycles when thread is not in halt state.",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.UOPS",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of Uops delivered by the LSD.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA8",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_ACTIVE",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "1",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x87",
+        "EventCode": "0x4C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "ILD_STALL.LCP",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+        "EventName": "LOAD_HIT_PRE.SW_PF",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x87",
+        "EventCode": "0x4C",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ILD_STALL.IQ_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Stall cycles because IQ is full.",
+        "UMask": "0x2",
+        "EventName": "LOAD_HIT_PRE.HW_PF",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "EventCode": "0x59",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "UMask": "0x20",
+        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.",
+        "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.",
         "EventCode": "0x59",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
-        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP",
+        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.",
+        "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
+        "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
         "EventCode": "0x59",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
@@ -302,48 +320,21 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "RESOURCE_STALLS.ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource-related stall cycles.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "RESOURCE_STALLS.LB",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the cycles of stall due to lack of load buffers.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "RESOURCE_STALLS.RS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to no eligible RS entry available.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA2",
+        "EventCode": "0x5B",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "RESOURCE_STALLS.SB",
+        "UMask": "0xc",
+        "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
+        "BriefDescription": "Cycles with either free list is empty.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0x5B",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "RESOURCE_STALLS.ROB",
+        "UMask": "0xf",
+        "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to re-order buffer full.",
+        "BriefDescription": "Resource stalls2 control structures full for physical registers.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -356,702 +347,663 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.",
-        "EventCode": "0x0E",
+        "EventCode": "0x5B",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.ANY",
+        "UMask": "0x4f",
+        "EventName": "RESOURCE_STALLS2.OOO_RSRC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).",
+        "BriefDescription": "Resource stalls out of order resources full.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0E",
-        "Invert": "1",
+        "EventCode": "0x5E",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0E",
+        "EventCode": "0x5E",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
+        "EventCode": "0x87",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "EventName": "ILD_STALL.LCP",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xCC",
+        "EventCode": "0x87",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "UMask": "0x4",
+        "EventName": "ILD_STALL.IQ_FULL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Count cases of saving new LBR.",
+        "BriefDescription": "Stall cycles because IQ is full.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear.  Machine clears can have a significant performance impact if they are happening frequently.",
-        "EventCode": "0xC3",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MACHINE_CLEARS.SMC",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Self-modifying code (SMC) detected.",
+        "UMask": "0x41",
+        "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not taken macro-conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.",
-        "EventCode": "0xC3",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "MACHINE_CLEARS.MASKMOV",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+        "UMask": "0x81",
+        "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired macro-conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "INST_RETIRED.ANY_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event.",
+        "UMask": "0x82",
+        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of micro-ops retired.",
-        "EventCode": "0xC2",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.ALL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Actually retired uops.",
+        "UMask": "0x84",
+        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle.  This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization.",
-        "EventCode": "0xC2",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used.",
+        "UMask": "0x88",
+        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.STALL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x90",
+        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired direct near calls.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
-        "CounterMask": "10",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xa0",
+        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired indirect calls.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired.",
+        "UMask": "0xc1",
+        "EventName": "BR_INST_EXEC.ALL_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired macro-conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "UMask": "0xc2",
+        "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
+        "UMask": "0xc4",
+        "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired.",
+        "UMask": "0xc8",
+        "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired indirect return branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "UMask": "0xd0",
+        "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired direct near calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired.",
+        "UMask": "0xff",
+        "EventName": "BR_INST_EXEC.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired  branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired.",
+        "UMask": "0x41",
+        "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "EventCode": "0xC4",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x81",
+        "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
+        "UMask": "0x84",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect mispredicted near call instructions retired.",
+        "UMask": "0x88",
+        "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All mispredicted macro branch instructions retired.",
+        "UMask": "0x90",
+        "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted direct near calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "BR_MISP_RETIRED.NOT_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted not taken branch instructions retired.",
+        "UMask": "0xa0",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_MISP_RETIRED.TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted taken branch instructions retired.",
+        "UMask": "0xc1",
+        "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xc4",
+        "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Mispredicted indirect branches excluding calls and returns.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC1",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired instructions experiencing ITLB misses.",
+        "UMask": "0xd0",
+        "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired mispredicted direct near calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x14",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ARITH.FPU_DIV_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when divider is busy executing divide operations.",
+        "UMask": "0xff",
+        "EventName": "BR_MISP_EXEC.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of the divide operations executed.",
-        "EventCode": "0x14",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "ARITH.FPU_DIV",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Divide operations executed.",
-        "CounterMask": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 0.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_DISPATCHED.THREAD",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops dispatched per thread.",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 0.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED.CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops dispatched from any thread.",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 1.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 0.",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 1.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "UMask": "0xc",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 1.",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "UMask": "0xc",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 4.",
+        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "UMask": "0x30",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 5.",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH",
+        "UMask": "0x30",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
-        "CounterMask": "2",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 4.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING",
+        "UMask": "0x40",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.",
-        "CounterMask": "1",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 4.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
-        "CounterMask": "6",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING",
+        "UMask": "0x80",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.",
-        "CounterMask": "5",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles per core when uops are dispatched to port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x4C",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "LOAD_HIT_PRE.SW_PF",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.",
+        "EventName": "RESOURCE_STALLS.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource-related stall cycles.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x4C",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "LOAD_HIT_PRE.HW_PF",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x03",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.",
+        "EventName": "RESOURCE_STALLS.LB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the cycles of stall due to lack of load buffers.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store.  See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
-        "EventCode": "0x03",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.",
+        "UMask": "0x4",
+        "EventName": "RESOURCE_STALLS.RS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles stalled due to no eligible RS entry available.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x03",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "LD_BLOCKS.NO_SR",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "EventName": "RESOURCE_STALLS.SB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x03",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "LD_BLOCKS.ALL_BLOCK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).",
+        "UMask": "0xa",
+        "EventName": "RESOURCE_STALLS.LB_SB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource stalls due to load or store buffers all being in use.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K.  This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline.  The enhanced address check typically has a performance penalty of 5 cycles.",
-        "EventCode": "0x07",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "False dependencies in MOB due to partial compare.",
+        "UMask": "0xe",
+        "EventName": "RESOURCE_STALLS.MEM_RS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x07",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.",
+        "UMask": "0x10",
+        "EventName": "RESOURCE_STALLS.ROB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles stalled due to re-order buffer full.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB6",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "AGU_BYPASS_CANCEL.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.",
+        "UMask": "0xf0",
+        "EventName": "RESOURCE_STALLS.OOO_RSRC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
+        "EventCode": "0xA3",
+        "Counter": "2",
         "UMask": "0x2",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
+        "CounterMask": "2",
+        "CounterHTOff": "2"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
+        "UMask": "0x4",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 0.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
+        "UMask": "0x5",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 1.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.",
+        "CounterMask": "5",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x6",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 4.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
+        "CounterMask": "6",
+        "CounterHTOff": "2"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
+        "UMask": "0x1",
+        "EventName": "LSD.UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 5.",
+        "BriefDescription": "Number of Uops delivered by the LSD.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
+        "UMask": "0x1",
+        "EventName": "UOPS_DISPATCHED.THREAD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.",
+        "BriefDescription": "Uops dispatched per thread.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
+        "UMask": "0x2",
+        "EventName": "UOPS_DISPATCHED.CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+        "BriefDescription": "Uops dispatched from any thread.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "EventCode": "0xC0",
-        "Counter": "1",
-        "UMask": "0x1",
-        "EventName": "INST_RETIRED.PREC_DIST",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Instructions retired. (Precise Event - PEBS).",
-        "TakenAlone": "1",
-        "CounterHTOff": "1"
-    },
-    {
-        "EventCode": "0x5B",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xf",
-        "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls2 control structures full for physical registers.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5B",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with either free list is empty.",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "CounterMask": "2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "RESOURCE_STALLS.MEM_RS",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "CounterMask": "3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xf0",
-        "EventName": "RESOURCE_STALLS.OOO_RSRC",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5B",
+        "EventCode": "0xB1",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "EventName": "RESOURCE_STALLS2.OOO_RSRC",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls out of order resources full.",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xB6",
         "Counter": "0,1,2,3",
-        "UMask": "0xa",
-        "EventName": "RESOURCE_STALLS.LB_SB",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls due to load or store buffers all being in use.",
+        "UMask": "0x1",
+        "EventName": "AGU_BYPASS_CANCEL.COUNT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "EventCode": "0xC0",
         "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "UMask": "0x0",
+        "EventName": "INST_RETIRED.ANY_P",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
-        "CounterMask": "1",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel? 64 and IA-32 Architectures Optimization Reference Manual.",
-        "EventCode": "0x59",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
+        "PEBS": "2",
+        "EventCode": "0xC0",
+        "Counter": "1",
+        "UMask": "0x1",
+        "EventName": "INST_RETIRED.PREC_DIST",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Instructions retired. (Precise Event - PEBS).",
+        "TakenAlone": "1",
+        "CounterHTOff": "1"
     },
     {
-        "EventCode": "0x0D",
+        "EventCode": "0xC1",
         "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EdgeDetect": "1",
-        "EventName": "INT_MISC.RECOVERY_STALLS_COUNT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
-        "CounterMask": "1",
+        "UMask": "0x2",
+        "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired instructions experiencing ITLB misses.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xE6",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of micro-ops retired. (Precise Event)",
+        "EventCode": "0xC2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1f",
-        "EventName": "BACLEARS.ANY",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+        "UMask": "0x1",
+        "EventName": "UOPS_RETIRED.ALL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Actually retired uops. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0xC2",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "EventName": "BR_INST_EXEC.ALL_BRANCHES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired  branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "EventName": "UOPS_RETIRED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles without actually retired uops.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0xC2",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "EventName": "BR_MISP_EXEC.ALL_BRANCHES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "CounterMask": "10",
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xC2",
@@ -1065,13 +1017,14 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA8",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle.  This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization. (Precise Event - PEBS)",
+        "EventCode": "0xC2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "4",
+        "BriefDescription": "Retirement slots used. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1086,135 +1039,188 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
-        "Invert": "1",
+        "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear.  Machine clears can have a significant performance impact if they are happening frequently.",
+        "EventCode": "0xC3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
+        "UMask": "0x4",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Self-modifying code (SMC) detected.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "MACHINE_CLEARS.MASKMOV",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "CounterMask": "1",
+        "UMask": "0x2",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "CounterMask": "1",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "2",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "CounterMask": "2",
+        "UMask": "0x4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Return instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "CounterMask": "3",
+        "UMask": "0x10",
+        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Not taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "CounterMask": "4",
+        "UMask": "0x20",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "UMask": "0x40",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "EventCode": "0x3C",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "UMask": "0x0",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect mispredicted near call instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "2",
+        "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "BR_MISP_RETIRED.NOT_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted not taken branch instructions retired.(Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "BR_MISP_RETIRED.TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted taken branch instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCC",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "BriefDescription": "Count cases of saving new LBR.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1f",
+        "EventName": "BACLEARS.ANY",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
index fd7d7c438226..cfeba5067bab 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -1,140 +1,226 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
index a654ab771fce..b8eccce5d75d 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
@@ -1,131 +1,131 @@
 [
     {
-        "EventCode": "0xAE",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ITLB.ITLB_FLUSH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x4F",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "EPT.WALK_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycle count for an Extended Page table walk.  The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Misses at all ITLB levels that cause page walks.",
+        "BriefDescription": "Load misses in all DTLB levels that cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x85",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
+        "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.",
-        "EventCode": "0x85",
+        "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "ITLB_MISSES.WALK_DURATION",
+        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when PMH is busy with page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x85",
+        "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "ITLB_MISSES.STLB_HIT",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load misses in all DTLB levels that cause page walks.",
+        "BriefDescription": "Store misses in all DTLB levels that cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
+        "EventName": "DTLB_STORE_MISSES.WALK_DURATION",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when PMH is busy with page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.",
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "EventCode": "0x4F",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "EPT.WALK_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycle count for an Extended Page table walk.  The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause page walks.",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "DTLB_STORE_MISSES.WALK_DURATION",
+        "EventName": "ITLB_MISSES.WALK_DURATION",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when PMH is busy with page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "EventName": "ITLB_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAE",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/cache.json b/tools/perf/pmu-events/arch/x86/silvermont/cache.json
index 82be7d1b8b81..805ef1436539 100644
--- a/tools/perf/pmu-events/arch/x86/silvermont/cache.json
+++ b/tools/perf/pmu-events/arch/x86/silvermont/cache.json
@@ -36,7 +36,7 @@
         "BriefDescription": "L2 cache request misses"
     },
     {
-        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events. \r\n",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
         "EventCode": "0x86",
         "Counter": "0,1",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/other.json b/tools/perf/pmu-events/arch/x86/silvermont/other.json
new file mode 100644
index 000000000000..47814046fa9d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/silvermont/other.json
@@ -0,0 +1,20 @@
+[
+    {
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss.  Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
+        "EventCode": "0x86",
+        "Counter": "0,1",
+        "UMask": "0x2",
+        "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss."
+    },
+    {
+        "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
+        "EventCode": "0x86",
+        "Counter": "0,1",
+        "UMask": "0x3f",
+        "EventName": "FETCH_STALL.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to any reason."
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json
index 7468af99190a..1ed62ad4cf77 100644
--- a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json
@@ -210,7 +210,7 @@
         "UMask": "0x4",
         "EventName": "NO_ALLOC_CYCLES.MISPREDICTS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire.  After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted "
+        "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire.  After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted"
     },
     {
         "EventCode": "0xCA",
@@ -275,7 +275,6 @@
     },
     {
         "PublicDescription": "This event counts the number of instructions that retire.  For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires.  The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.  Background: Modern microprocessors employ extensive pipelining and speculative techniques.  Since sometimes an instruction is started but never completed, the notion of \"retirement\" is introduced.  A retired instruction is one that commits its states. Or stated differently, an instruction might be abandoned at some point. No instruction is truly finished until it retires.  This counter measures the number of completed instructions.  The fixed event is INST_RETIRED.ANY and the programmable event is INST_RETIRED.ANY_P.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -284,7 +283,6 @@
     },
     {
         "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios.  The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. In systems with a constant core frequency, this event can give you a measurement of the elapsed time while the core was not in halt state by dividing the event count by the core frequency. This event is architecturally defined and is a designated fixed counter.  CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time.  CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.CORE",
@@ -293,7 +291,6 @@
     },
     {
         "PublicDescription": "Counts the number of reference cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios.  The core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  Divide this event count by core frequency to determine the elapsed time while the core was not in halt state.  Divide this event count by core frequency to determine the elapsed time while the core was not in halt state.  This event is architecturally defined and is a designated fixed counter.  CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time.  CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 3",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json
index 54bfe9e4045c..720458139049 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json
@@ -60,10 +60,10 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
@@ -73,7 +73,7 @@
         "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "RFO requests that hit L2 cache",
@@ -83,7 +83,7 @@
         "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
@@ -482,7 +482,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -554,7 +554,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
@@ -661,13 +661,13 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "EventCode": "0xF2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "L2_LINES_OUT.USELESS_PREF",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -690,249 +690,2238 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC01C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x10001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x04001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x02001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x01001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00801C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400001 ",
+        "MSRValue": "0x0200028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests have any response type.",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0000018000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests have any response type.",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC01C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x10001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x04001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x02001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x01001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00801C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0000010004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC01C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x10001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x04001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x02001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x01001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00801C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0000010002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400001 ",
+        "MSRValue": "0x1000400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400001 ",
+        "MSRValue": "0x0400400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400001 ",
+        "MSRValue": "0x0200400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400001 ",
+        "MSRValue": "0x0100400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400001 ",
+        "MSRValue": "0x0080400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0001 ",
+        "MSRValue": "0x3FC01C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0001 ",
+        "MSRValue": "0x10001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0001 ",
+        "MSRValue": "0x04001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0001 ",
+        "MSRValue": "0x02001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0001 ",
+        "MSRValue": "0x01001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0001 ",
+        "MSRValue": "0x00801C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C0001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020001 ",
+        "MSRValue": "0x0080100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020001 ",
+        "MSRValue": "0x1000020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020001 ",
+        "MSRValue": "0x0400020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020001 ",
+        "MSRValue": "0x0200020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020001 ",
+        "MSRValue": "0x0100020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020001 ",
+        "MSRValue": "0x0080020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040020001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010001 ",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that have any response type.",
+        "BriefDescription": "Counts demand data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
index 578dff5bd823..7fa95a35e3ca 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
@@ -177,7 +177,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -242,7 +242,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
         "EventCode": "0xAB",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -253,7 +253,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "EventCode": "0xC6",
         "MSRValue": "0x11",
         "Counter": "0,1,2,3",
@@ -360,7 +360,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "EventCode": "0xC6",
         "MSRValue": "0x400806",
         "Counter": "0,1,2,3",
@@ -374,7 +374,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "EventCode": "0xC6",
         "MSRValue": "0x401006",
         "Counter": "0,1,2,3",
@@ -388,7 +388,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "EventCode": "0xC6",
         "MSRValue": "0x402006",
         "Counter": "0,1,2,3",
@@ -454,7 +454,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "EventCode": "0xC6",
         "MSRValue": "0x100206",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json
index 3bd8b712c889..f197b4c7695b 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json
@@ -215,7 +215,7 @@
         "UMask": "0x4",
         "EventName": "HLE_RETIRED.ABORTED",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -237,6 +237,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "EventCode": "0xC8",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -292,7 +293,7 @@
         "UMask": "0x4",
         "EventName": "RTM_RETIRED.ABORTED",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -346,7 +347,7 @@
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x4",
         "Counter": "0,1,2,3",
@@ -354,13 +355,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x8",
         "Counter": "0,1,2,3",
@@ -368,13 +369,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x10",
         "Counter": "0,1,2,3",
@@ -382,13 +383,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x20",
         "Counter": "0,1,2,3",
@@ -396,13 +397,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x40",
         "Counter": "0,1,2,3",
@@ -410,13 +411,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "2003",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x80",
         "Counter": "0,1,2,3",
@@ -424,13 +425,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "1009",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x100",
         "Counter": "0,1,2,3",
@@ -438,13 +439,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "503",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x200",
         "Counter": "0,1,2,3",
@@ -452,163 +453,1151 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "101",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000001 ",
+        "MSRValue": "0x3FFC408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x103C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x043C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x023C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x013C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00BC408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x007C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1004008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0404008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0204008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0104008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0084008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FFC400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x103C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x043C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x023C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x013C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00BC400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x007C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1004000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0404000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0204000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0104000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0084000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FFC400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x103C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x043C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x023C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x013C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00BC400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x007C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1004000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0404000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0204000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0104000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0084000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FFC400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000001 ",
+        "MSRValue": "0x103C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000001 ",
+        "MSRValue": "0x043C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000001 ",
+        "MSRValue": "0x023C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000001 ",
+        "MSRValue": "0x013C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000001 ",
+        "MSRValue": "0x00BC400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000001 ",
+        "MSRValue": "0x007C400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000001 ",
+        "MSRValue": "0x1004000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000001 ",
+        "MSRValue": "0x0404000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000001 ",
+        "MSRValue": "0x0204000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000001 ",
+        "MSRValue": "0x0104000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000001 ",
+        "MSRValue": "0x0084000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C0001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000020001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
index bc6d2afbcd8a..4a891fbbc4bb 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -11,7 +10,6 @@
     },
     {
         "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -31,7 +28,6 @@
     },
     {
         "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -121,7 +117,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -248,6 +244,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
+        "EventCode": "0x59",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
         "EventCode": "0x5E",
         "Counter": "0,1,2,3",
@@ -361,8 +367,8 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
-        "EventCode": "0xA2",
+        "PublicDescription": "Counts resource-related stall cycles.",
+        "EventCode": "0xa2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "RESOURCE_STALLS.ANY",
@@ -735,7 +741,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
@@ -759,6 +765,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Number of machine clears (nukes) of any type.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -839,14 +846,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "SKL091",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -924,7 +932,7 @@
         "UMask": "0x20",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -938,6 +946,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xCC",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
         "EventCode": "0xE6",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index 71e9737f4614..2c95417a4dae 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -1,164 +1,364 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
     },
     {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Access_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
index 5c9940866acd..24df183693fa 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -61,17 +61,17 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "BriefDescription": "RFO requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.RFO_HIT",
@@ -81,7 +81,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
@@ -165,6 +165,7 @@
         "BriefDescription": "Core-originated cacheable demand requests missed L3",
         "Counter": "0,1,2,3",
         "EventName": "LONGEST_LAT_CACHE.MISS",
+        "Errata": "SKL057",
         "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
@@ -175,28 +176,29 @@
         "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
         "Counter": "0,1,2,3",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
+        "Errata": "SKL057",
+        "PublicDescription": "Counts core-originated cacheable requests to the  L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x48",
         "UMask": "0x1",
-        "BriefDescription": "L1D miss outstandings duration in cycles",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
         "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x48",
         "UMask": "0x1",
-        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
         "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "EventName": "L1D_PEND_MISS.PENDING",
+        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -234,21 +236,21 @@
     {
         "EventCode": "0x60",
         "UMask": "0x1",
-        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "UMask": "0x1",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -307,21 +309,21 @@
     {
         "EventCode": "0x60",
         "UMask": "0x8",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
-        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "UMask": "0x8",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -486,7 +488,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -558,7 +560,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -690,6 +692,7 @@
         "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -699,17 +702,18 @@
         "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped.",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xF2",
         "UMask": "0x4",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
+        "Deprecated": "1",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.USELESS_PREF",
-        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -736,12 +740,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that have any response type.",
-        "MSRValue": "0x0000010001 ",
+        "BriefDescription": "Counts demand data reads have any response type.",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -749,12 +753,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x01003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -762,25 +766,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0001 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -788,12 +779,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -801,12 +792,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x3F803C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -814,12 +805,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
-        "MSRValue": "0x0000010002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "MSRValue": "0x0000010002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -827,12 +818,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x01003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -840,12 +831,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -853,25 +844,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0002 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -879,12 +857,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
-        "MSRValue": "0x3f803c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x3F803C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -892,12 +870,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that have any response type.",
-        "MSRValue": "0x0000010004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "MSRValue": "0x0000010004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -905,12 +883,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x01003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -918,12 +896,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -931,25 +909,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0004 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -957,12 +922,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3.",
-        "MSRValue": "0x3f803c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x3F803C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -970,12 +935,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
-        "MSRValue": "0x0000010010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
+        "MSRValue": "0x0000010010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -983,12 +948,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x01003C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -996,12 +961,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x04003C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1009,25 +974,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0010 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x10003C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1035,12 +987,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1048,12 +1000,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
-        "MSRValue": "0x0000010020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
+        "MSRValue": "0x0000010020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1061,12 +1013,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x01003C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1074,12 +1026,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x04003C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1087,25 +1039,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0020 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x10003C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1113,12 +1052,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1126,12 +1065,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
-        "MSRValue": "0x0000010080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
+        "MSRValue": "0x0000010080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1139,12 +1078,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x01003C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1152,25 +1091,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x04003C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0080 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1178,12 +1104,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x10003C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1191,12 +1117,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1204,12 +1130,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
-        "MSRValue": "0x0000010100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
+        "MSRValue": "0x0000010100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1217,12 +1143,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x01003C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1230,12 +1156,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x04003C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1243,12 +1169,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x10003C0100",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1256,12 +1182,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1269,12 +1195,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0100 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.",
+        "MSRValue": "0x0000010400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1282,12 +1208,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.",
-        "MSRValue": "0x0000010400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x01003C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1295,12 +1221,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x04003C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1308,12 +1234,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x10003C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1321,12 +1247,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x3F803C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1334,12 +1260,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0400 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1347,12 +1273,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.",
-        "MSRValue": "0x3f803c0400 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1360,12 +1286,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that have any response type.",
-        "MSRValue": "0x0000018000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1373,12 +1299,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1386,12 +1312,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1399,12 +1325,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c8000 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1412,12 +1338,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1425,12 +1351,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3.",
-        "MSRValue": "0x3f803c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1438,12 +1364,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that have any response type.",
-        "MSRValue": "0x0000010490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1451,12 +1377,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1464,12 +1390,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0490 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1477,12 +1403,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1490,12 +1416,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1503,12 +1429,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1516,12 +1442,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that have any response type.",
-        "MSRValue": "0x0000010120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1529,12 +1455,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0120 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1542,12 +1468,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1555,12 +1481,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1568,12 +1494,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1581,12 +1507,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1594,12 +1520,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
-        "MSRValue": "0x0000010491 ",
+        "BriefDescription": "Counts demand data reads",
+        "MSRValue": "0x08007C0001",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts demand data reads",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1607,12 +1532,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0491 ",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "MSRValue": "0x08007C0002",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1620,12 +1544,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0491 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "MSRValue": "0x08007C0004",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1633,12 +1556,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0491 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
+        "MSRValue": "0x08007C0010",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1646,12 +1568,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0491 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
+        "MSRValue": "0x08007C0020",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1659,12 +1580,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0491 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
+        "MSRValue": "0x08007C0080",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1672,12 +1592,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
-        "MSRValue": "0x0000010122 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
+        "MSRValue": "0x08007C0100",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1685,12 +1604,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0122 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests",
+        "MSRValue": "0x08007C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1698,12 +1616,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1711,12 +1628,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1724,12 +1640,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1737,12 +1652,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
index 286ed1a37ec9..c5d0babe89fc 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
@@ -59,7 +59,6 @@
         "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -69,7 +68,6 @@
         "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
index 403a4f89e9b2..4dc583cfb545 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
@@ -2,16 +2,6 @@
     {
         "EventCode": "0x79",
         "UMask": "0x4",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x4",
         "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MITE_CYCLES",
@@ -22,11 +12,11 @@
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "UMask": "0x4",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "EventName": "IDQ.MITE_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -43,6 +33,16 @@
     },
     {
         "EventCode": "0x79",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
         "UMask": "0x10",
         "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
@@ -55,22 +55,22 @@
     {
         "EventCode": "0x79",
         "UMask": "0x18",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "UMask": "0x18",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
-        "CounterMask": "1",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -87,22 +87,22 @@
     {
         "EventCode": "0x79",
         "UMask": "0x24",
-        "BriefDescription": "Cycles MITE is delivering 4 Uops",
+        "BriefDescription": "Cycles MITE is delivering any Uop",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "UMask": "0x24",
-        "BriefDescription": "Cycles MITE is delivering any Uop",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
-        "CounterMask": "1",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -118,24 +118,24 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EdgeDetect": "1",
         "EventCode": "0x79",
         "UMask": "0x30",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_SWITCHES",
-        "CounterMask": "1",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
         "EventCode": "0x79",
         "UMask": "0x30",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -177,67 +177,67 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "CounterMask": "4",
-        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
-        "CounterMask": "3",
-        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
-        "CounterMask": "2",
-        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "CounterMask": "3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
-        "CounterMask": "1",
-        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "CounterMask": "4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
-        "CounterMask": "1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -247,20 +247,19 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "Counter": "0,1,2,3",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x11",
+        "MSRValue": "0x400406",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -268,11 +267,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x12",
+        "MSRValue": "0x200206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.L1I_MISS",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -281,11 +280,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x13",
+        "MSRValue": "0x400206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -294,13 +293,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x14",
+        "MSRValue": "0x15",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+        "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -308,13 +307,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x15",
+        "MSRValue": "0x14",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.STLB_MISS",
+        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -322,11 +321,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x400206",
+        "MSRValue": "0x13",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
+        "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -335,11 +334,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x200206",
+        "MSRValue": "0x12",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
+        "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -348,12 +347,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x400406",
+        "MSRValue": "0x11",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
+        "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -361,13 +361,12 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x400806",
+        "MSRValue": "0x300206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -375,13 +374,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x401006",
+        "MSRValue": "0x100206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -389,13 +388,12 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x402006",
+        "MSRValue": "0x420006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -403,11 +401,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x404006",
+        "MSRValue": "0x410006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -429,11 +427,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x410006",
+        "MSRValue": "0x404006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -442,12 +440,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x420006",
+        "MSRValue": "0x402006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -455,13 +454,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x100206",
+        "MSRValue": "0x401006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -469,12 +468,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
         "PEBS": "1",
-        "MSRValue": "0x300206",
+        "MSRValue": "0x400806",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
index e7f1aa31226d..48a9cdf81307 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
@@ -129,20 +129,20 @@
     {
         "EventCode": "0x60",
         "UMask": "0x10",
-        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
-        "CounterMask": "1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "UMask": "0x10",
-        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
+        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
-        "CounterMask": "6",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -210,7 +210,7 @@
     {
         "EventCode": "0xC8",
         "UMask": "0x4",
-        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
@@ -242,6 +242,7 @@
         "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -287,7 +288,7 @@
     {
         "EventCode": "0xC9",
         "UMask": "0x4",
-        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
@@ -347,125 +348,125 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x4",
+        "MSRValue": "0x200",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "100003",
+        "SampleAfterValue": "101",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x8",
+        "MSRValue": "0x100",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "50021",
+        "SampleAfterValue": "503",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x10",
+        "MSRValue": "0x80",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "20011",
+        "SampleAfterValue": "1009",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x20",
+        "MSRValue": "0x40",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "100007",
+        "SampleAfterValue": "2003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x40",
+        "MSRValue": "0x20",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "2003",
+        "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x80",
+        "MSRValue": "0x10",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "1009",
+        "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x100",
+        "MSRValue": "0x8",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "503",
+        "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x200",
+        "MSRValue": "0x4",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "101",
+        "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x3FBC000001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -473,12 +474,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x083FC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -486,12 +487,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x103FC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -499,12 +500,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x063FC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -512,12 +513,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x063B800001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -525,12 +526,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x0604000001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -538,12 +539,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.",
-        "MSRValue": "0x3fbc000002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x3FBC000002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -551,12 +552,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x083FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -564,12 +565,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x103FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -577,12 +578,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x063FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -590,12 +591,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x063B800002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -603,12 +604,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x0604000002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -616,12 +617,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss in the L3.",
-        "MSRValue": "0x3fbc000004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x3FBC000004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -629,12 +630,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x083FC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -642,12 +643,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x103FC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -655,12 +656,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x063FC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -668,12 +669,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x063B800004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -681,12 +682,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x0604000004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -694,12 +695,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x3FBC000010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -707,12 +708,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x083FC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -720,12 +721,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x103FC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -733,12 +734,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x063FC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -746,12 +747,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x063B800010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -759,12 +760,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x0604000010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -772,12 +773,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x3FBC000020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -785,12 +786,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x083FC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -798,12 +799,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x103FC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -811,12 +812,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x063FC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -824,12 +825,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x063B800020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -837,12 +838,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x0604000020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -850,12 +851,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x3FBC000080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -863,12 +864,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x083FC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -876,12 +877,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x103FC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -889,12 +890,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x063FC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -902,12 +903,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x063B800080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -915,12 +916,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x0604000080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -928,12 +929,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x3FBC000100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -941,12 +942,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x083FC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -954,12 +955,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x103FC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -967,12 +968,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x063FC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -980,12 +981,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x063B800100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -993,12 +994,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x0604000100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1006,12 +1007,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.",
-        "MSRValue": "0x3fbc000400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x3FBC000400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1019,12 +1020,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x083FC00400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1032,12 +1033,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x103FC00400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1045,12 +1046,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x063FC00400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1058,12 +1059,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x063B800400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1071,90 +1072,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x0604000400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss in the L3.",
-        "MSRValue": "0x3fbc008000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc08000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc08000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc08000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b808000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604008000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1162,12 +1085,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1175,12 +1098,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1188,12 +1111,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1201,12 +1124,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1214,12 +1137,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1227,12 +1150,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1240,12 +1163,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1253,12 +1176,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1266,12 +1189,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1279,12 +1202,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1292,12 +1215,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1305,12 +1228,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1318,12 +1241,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000491 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1331,12 +1254,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1344,12 +1267,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1357,12 +1280,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1370,12 +1293,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1383,12 +1306,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1396,12 +1319,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000122 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1409,12 +1332,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1422,12 +1345,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1435,12 +1358,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1448,12 +1371,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1461,12 +1384,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
index f99f7ae27820..369f56c1d1b5 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -10,7 +9,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -30,7 +27,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -99,24 +95,24 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0x0E",
         "UMask": "0x1",
-        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0x0E",
         "UMask": "0x1",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -126,7 +122,7 @@
         "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
-        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -203,19 +199,19 @@
     {
         "EventCode": "0x3C",
         "UMask": "0x1",
-        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
         "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
         "SampleAfterValue": "2503",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x3C",
         "UMask": "0x1",
-        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
         "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
         "SampleAfterValue": "2503",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -248,12 +244,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
+        "EventCode": "0x59",
         "UMask": "0x1",
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
         "Counter": "0,1,2,3",
-        "EventName": "RS_EVENTS.EMPTY_CYCLES",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+        "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -271,6 +267,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "UMask": "0x1",
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
@@ -361,12 +367,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xa2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
         "Counter": "0,1,2,3",
         "EventName": "RESOURCE_STALLS.ANY",
-        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts resource-related stall cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -522,6 +528,17 @@
     {
         "EventCode": "0xA8",
         "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
         "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
         "Counter": "0,1,2,3",
         "EventName": "LSD.CYCLES_ACTIVE",
@@ -531,35 +548,35 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_4_UOPS",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
         "CounterMask": "4",
-        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.THREAD",
-        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -575,35 +592,24 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "CounterMask": "2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "CounterMask": "3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "CounterMask": "4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -618,11 +624,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
         "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
@@ -630,10 +637,10 @@
     {
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "CounterMask": "2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -650,20 +657,19 @@
     {
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "CounterMask": "4",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
@@ -725,12 +731,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0xC2",
         "UMask": "0x2",
-        "BriefDescription": "Retirement slots used.",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "Counts the retirement slots used.",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "CounterMask": "10",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -742,19 +750,17 @@
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0xC2",
         "UMask": "0x2",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "BriefDescription": "Retirement slots used.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
-        "CounterMask": "10",
-        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "Counts the retirement slots used.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -766,6 +772,7 @@
         "Counter": "0,1,2,3",
         "EventName": "MACHINE_CLEARS.COUNT",
         "CounterMask": "1",
+        "PublicDescription": "Number of machine clears (nukes) of any type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -841,11 +848,12 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x10",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired.",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -919,7 +927,7 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
@@ -938,6 +946,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xCC",
+        "UMask": "0x40",
+        "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
+        "Counter": "0,1,2,3",
+        "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xE6",
         "UMask": "0x1",
         "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 71e9737f4614..56e03ba771f4 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -1,164 +1,394 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
+    },
+    {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Access_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0",
+        "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "MEM_PMM_Read_Latency"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Read_BW"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Write_BW"
+    },
+    {
+        "MetricExpr": "cha_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/trace/beauty/renameat.c b/tools/perf/trace/beauty/renameat.c
index 6dab340cc506..852d2e271833 100644
--- a/tools/perf/trace/beauty/renameat.c
+++ b/tools/perf/trace/beauty/renameat.c
@@ -2,7 +2,6 @@
 // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 #include "trace/beauty/beauty.h"
-#include <uapi/linux/fs.h>
 
 static size_t renameat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
diff --git a/tools/perf/trace/strace/groups/string b/tools/perf/trace/strace/groups/string
new file mode 100644
index 000000000000..c87129a3e3c4
--- /dev/null
+++ b/tools/perf/trace/strace/groups/string
@@ -0,0 +1,65 @@
+access
+acct
+add_key
+chdir
+chmod
+chown
+chroot
+creat
+delete_module
+execve
+execveat
+faccessat
+fchmodat
+fchownat
+fgetxattr
+finit_module
+fremovexattr
+fsetxattr
+futimesat
+getxattr
+inotify_add_watch
+lchown
+lgetxattr
+link
+linkat
+listxattr
+llistxattr
+lremovexattr
+lsetxattr
+lstat
+memfd_create
+mkdir
+mkdirat
+mknod
+mknodat
+mq_open
+mq_timedsend
+mq_unlink
+name_to_handle_at
+newfstatat
+open
+openat
+pivot_root
+pwrite64
+quotactl
+readlink
+readlinkat
+removexattr
+rename
+renameat
+renameat2
+request_key
+rmdir
+setxattr
+stat
+statfs
+statx
+swapoff
+swapon
+symlink
+symlinkat
+truncate
+unlink
+unlinkat
+utimensat
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index c8b01176c9e1..09762985c713 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1714,8 +1714,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return -1;
 
-	pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
-		 sym->name, sym->start, sym->end - sym->start);
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
 
 	memset(tpath, 0, sizeof(tpath));
 	perf_exe(tpath, sizeof(tpath));
@@ -1740,7 +1740,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
-	info.buffer = (void *)(info_linear->info.jited_prog_insns);
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
 	info.buffer_length = info_linear->info.jited_prog_len;
 
 	if (info_linear->info.nr_line_info)
@@ -1776,7 +1776,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		const char *srcline;
 		u64 addr;
 
-		addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
 		count = disassemble(pc, &info);
 
 		if (prog_linfo)
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index ca0fff6272be..06f48312c5ed 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,7 +7,6 @@
 #include "asm/bug.h"
 #include "debug.h"
 #include <unistd.h>
-#include <asm/unistd.h>
 #include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 110804936fc3..de488b43f440 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -422,11 +422,9 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
 	if (!etmq->packet)
 		goto out_free;
 
-	if (etm->synth_opts.last_branch || etm->sample_branches) {
-		etmq->prev_packet = zalloc(szp);
-		if (!etmq->prev_packet)
-			goto out_free;
-	}
+	etmq->prev_packet = zalloc(szp);
+	if (!etmq->prev_packet)
+		goto out_free;
 
 	if (etm->synth_opts.last_branch) {
 		size_t sz = sizeof(struct branch_stack);
@@ -981,7 +979,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 	 * PREV_PACKET is a branch.
 	 */
 	if (etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
 	    etmq->prev_packet->last_instr_taken_branch)
 		cs_etm__update_last_branch_rb(etmq);
@@ -1014,7 +1011,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches && etmq->prev_packet) {
+	if (etm->sample_branches) {
 		bool generate_sample = false;
 
 		/* Generate sample for tracing on packet */
@@ -1071,9 +1068,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
-	if (!etmq->prev_packet)
-		return 0;
-
 	/* Handle start tracing packet */
 	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
 		goto swap_packet;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 26af43ad9ddd..e0311c9750ad 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -310,7 +310,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	if (flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
-		tmp_val = tep_read_number(fmtf->event->pevent,
+		tmp_val = tep_read_number(fmtf->event->tep,
 					  data + offset, len);
 		offset = tmp_val;
 		len = offset >> 16;
@@ -354,7 +354,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			unsigned long long value_int;
 
 			value_int = tep_read_number(
-					fmtf->event->pevent,
+					fmtf->event->tep,
 					data + offset + i * len, len);
 
 			if (!(flags & TEP_FIELD_IS_SIGNED))
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9494f9dc61ec..6a3eaf7d9353 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -115,8 +115,8 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 	}
 	node = NULL;
 
-	up_read(&env->bpf_progs.lock);
 out:
+	up_read(&env->bpf_progs.lock);
 	return node;
 }
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 36ae7e92dab1..4e908ec1ef64 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
+#include <linux/perf_event.h>
 
 #include "../perf.h"
 #include "build-id.h"
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 51ead577533f..4b6783ff5813 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1009,7 +1009,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks, int affinity)
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1019,7 +1019,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
+	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush };
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1051,7 +1051,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6a94785b9100..c9a0f72677fd 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -177,7 +177,8 @@ unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks, int affinity);
+			 bool auxtrace_overwrite, int nr_cblocks,
+			 int affinity, int flush);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 966360844fff..a10cf4cde920 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -580,6 +580,12 @@ static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
+static int perf_evsel__tool_name(char *bf, size_t size)
+{
+	int ret = scnprintf(bf, size, "duration_time");
+	return ret;
+}
+
 const char *perf_evsel__name(struct perf_evsel *evsel)
 {
 	char bf[128];
@@ -601,7 +607,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 		break;
 
 	case PERF_TYPE_SOFTWARE:
-		perf_evsel__sw_name(evsel, bf, sizeof(bf));
+		if (evsel->tool_event)
+			perf_evsel__tool_name(bf, sizeof(bf));
+		else
+			perf_evsel__sw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_TRACEPOINT:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0f2c6c93d721..6d190cbf1070 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -75,6 +75,11 @@ struct perf_stat_evsel;
 
 typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
 
+enum perf_tool_event {
+	PERF_TOOL_NONE		= 0,
+	PERF_TOOL_DURATION_TIME = 1,
+};
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -121,6 +126,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	enum perf_tool_event	tool_event;
 	bool			uniquified_name;
 	bool			snapshot;
 	bool 			supported;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index cdc7740fc181..ef3d79b2c90b 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -440,6 +440,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
 
 	perf_mmap__setup_affinity_mask(map, mp);
 
+	map->flush = mp->flush;
+
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))
 		return -1;
@@ -492,7 +494,7 @@ static int __perf_mmap__read_init(struct perf_mmap *md)
 	md->start = md->overwrite ? head : old;
 	md->end = md->overwrite ? old : head;
 
-	if (md->start == md->end)
+	if ((md->end - md->start) < md->flush)
 		return -EAGAIN;
 
 	size = md->end - md->start;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index e566c19b242b..b82f8c2d55c4 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,6 +39,7 @@ struct perf_mmap {
 	} aio;
 #endif
 	cpu_set_t	affinity_mask;
+	u64		flush;
 };
 
 /*
@@ -70,7 +71,7 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-	int			    prot, mask, nr_cblocks, affinity;
+	int			    prot, mask, nr_cblocks, affinity, flush;
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5ef4939408f2..4432bfe039fd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -317,10 +317,12 @@ static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
 	    char *name, struct perf_pmu *pmu,
-	    struct list_head *config_terms, bool auto_merge_stats)
+	    struct list_head *config_terms, bool auto_merge_stats,
+	    const char *cpu_list)
 {
 	struct perf_evsel *evsel;
-	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
+	struct cpu_map *cpus = pmu ? pmu->cpus :
+			       cpu_list ? cpu_map__new(cpu_list) : NULL;
 
 	event_attr_init(attr);
 
@@ -348,7 +350,25 @@ static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, char *name,
 		     struct list_head *config_terms)
 {
-	return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
+	return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM;
+}
+
+static int add_event_tool(struct list_head *list, int *idx,
+			  enum perf_tool_event tool_event)
+{
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_DUMMY,
+	};
+
+	evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0");
+	if (!evsel)
+		return -ENOMEM;
+	evsel->tool_event = tool_event;
+	if (tool_event == PERF_TOOL_DURATION_TIME)
+		evsel->unit = strdup("ns");
+	return 0;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -1233,6 +1253,13 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			 get_config_name(head_config), &config_terms);
 }
 
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event)
+{
+	return add_event_tool(list, &parse_state->idx, tool_event);
+}
+
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config,
@@ -1267,7 +1294,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL,
+				    auto_merge_stats, NULL);
 		if (evsel) {
 			evsel->pmu_name = name;
 			evsel->use_uncore_alias = use_uncore_alias;
@@ -1295,7 +1323,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
 			    get_config_name(head_config), pmu,
-			    &config_terms, auto_merge_stats);
+			    &config_terms, auto_merge_stats, NULL);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
@@ -2429,6 +2457,25 @@ out_enomem:
 	return evt_num;
 }
 
+static void print_tool_event(const char *name, const char *event_glob,
+			     bool name_only)
+{
+	if (event_glob && !strglobmatch(name, event_glob))
+		return;
+	if (name_only)
+		printf("%s ", name);
+	else
+		printf("  %-50s [%s]\n", name, "Tool event");
+
+}
+
+void print_tool_events(const char *event_glob, bool name_only)
+{
+	print_tool_event("duration_time", event_glob, name_only);
+	if (pager_in_use())
+		printf("\n");
+}
+
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only)
@@ -2512,6 +2559,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
 			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
+	print_tool_events(event_glob, name_only);
 
 	print_hwcache_events(event_glob, name_only);
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 5ed035cbcbb7..a052cd6ac63e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -160,6 +160,10 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
+enum perf_tool_event;
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2,
 			   struct parse_events_error *error,
@@ -200,6 +204,7 @@ extern struct event_symbol event_symbols_sw[];
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only);
+void print_tool_events(const char *event_glob, bool name_only);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 7805c71aaae2..c54bfe88626c 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -15,6 +15,7 @@
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
+#include "evsel.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -154,6 +155,14 @@ static int sym(yyscan_t scanner, int type, int config)
 	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
+static int tool(yyscan_t scanner, enum perf_tool_event event)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = event;
+	return PE_VALUE_SYM_TOOL;
+}
+
 static int term(yyscan_t scanner, int type)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -322,7 +331,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-duration_time					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 44819bdb037d..6ad8d4914969 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include "util.h"
 #include "pmu.h"
+#include "evsel.h"
 #include "debug.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -45,6 +46,7 @@ static void inc_group_count(struct list_head *list,
 
 %token PE_START_EVENTS PE_START_TERMS
 %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
+%token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_NAME
 %token PE_BPF_OBJECT PE_BPF_SOURCE
@@ -58,6 +60,7 @@ static void inc_group_count(struct list_head *list,
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
+%type <num> PE_VALUE_SYM_TOOL
 %type <num> PE_RAW
 %type <num> PE_TERM
 %type <str> PE_NAME
@@ -321,6 +324,15 @@ value_sym sep_slash_slash_dc
 	ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL));
 	$$ = list;
 }
+|
+PE_VALUE_SYM_TOOL sep_slash_slash_dc
+{
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+	$$ = list;
+}
 
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index dda0ac978b1e..6aa7e2352e16 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -342,7 +342,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 static PyObject*
 tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 {
-	struct tep_handle *pevent = field->event->pevent;
+	struct tep_handle *pevent = field->event->tep;
 	void *data = pe->sample.raw_data;
 	PyObject *ret = NULL;
 	unsigned long long val;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 5f06378a482b..61aa7f3df915 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -372,7 +372,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
-	scripting_context->pevent = evsel->tp_format->pevent;
+	scripting_context->pevent = evsel->tp_format->tep;
 
 	ENTER;
 	SAVETMPS;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 09604c6508f0..22f52b669871 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -837,7 +837,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
-	scripting_context->pevent = evsel->tp_format->pevent;
+	scripting_context->pevent = evsel->tp_format->tep;
 
 	context = _PyCapsule_New(scripting_context, NULL, NULL);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b17f1c9bc965..bad5f87ae001 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1928,12 +1928,14 @@ more:
 
 	size = event->header.size;
 
+	skip = -EINVAL;
+
 	if (size < sizeof(struct perf_event_header) ||
 	    (skip = rd->process(session, event, file_pos)) < 0) {
-		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       file_offset + head, event->header.size,
-		       event->header.type);
-		err = -EINVAL;
+		       event->header.type, strerror(-skip));
+		err = skip;
 		goto out;
 	}
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 6d043c78f3c2..3324f23c7efc 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -18,11 +18,6 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
-static bool is_duration_time(struct perf_evsel *evsel)
-{
-	return !strcmp(evsel->name, "duration_time");
-}
-
 static void print_running(struct perf_stat_config *config,
 			  u64 run, u64 ena)
 {
@@ -628,9 +623,6 @@ static void print_aggr(struct perf_stat_config *config,
 		ad.id = id = config->aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-
 			ad.val = ad.ena = ad.run = 0;
 			ad.nr = 0;
 			if (!collect_data(config, counter, aggr_cb, &ad))
@@ -848,8 +840,6 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 		if (prefix)
 			fputs(prefix, config->output);
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			if (first) {
 				aggr_printout(config, counter, cpu, 0);
 				first = false;
@@ -906,8 +896,6 @@ static void print_metric_headers(struct perf_stat_config *config,
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evlist, counter) {
-		if (is_duration_time(counter))
-			continue;
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
@@ -1136,15 +1124,11 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		break;
 	case AGGR_THREAD:
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			print_aggr_thread(config, _target, counter, prefix);
 		}
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			print_counter_aggr(config, counter, prefix);
 		}
 		if (metric_only)
@@ -1155,8 +1139,6 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 			print_no_aggr_metric(config, evlist, prefix);
 		else {
 			evlist__for_each_entry(evlist, counter) {
-				if (is_duration_time(counter))
-					continue;
 				print_counter(config, counter, prefix);
 			}
 		}
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index ad74be1f0e42..863955e4094e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -111,7 +111,7 @@ raw_field_value(struct tep_event *event, const char *name, void *data)
 
 unsigned long long read_size(struct tep_event *event, void *ptr, int size)
 {
-	return tep_read_number(event->pevent, ptr, size);
+	return tep_read_number(event->tep, ptr, size);
 }
 
 void event_format__fprintf(struct tep_event *event,
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index efe2f58cff4e..48d53d8e3e16 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -442,7 +442,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 
 	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
 	tep_set_file_bigendian(pevent, file_bigendian);
-	tep_set_host_bigendian(pevent, host_bigendian);
+	tep_set_local_bigendian(pevent, host_bigendian);
 
 	if (do_read(buf, 1) < 0)
 		goto out;
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index cbe0dd758e3a..01b9d89bf5bf 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -40,7 +40,7 @@ int trace_event__init(struct trace_event *t)
 
 static int trace_event__init2(void)
 {
-	int be = tep_host_bigendian();
+	int be = tep_is_bigendian();
 	struct tep_handle *pevent;
 
 	if (trace_event__init(&tevent))
@@ -49,7 +49,7 @@ static int trace_event__init2(void)
 	pevent = tevent.pevent;
 	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
 	tep_set_file_bigendian(pevent, be);
-	tep_set_host_bigendian(pevent, be);
+	tep_set_local_bigendian(pevent, be);
 	tevent_initialized = true;
 	return 0;
 }
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index 2a1fd9182f94..d1f3d44e315e 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -19,7 +19,7 @@ ACPI_MODULE_NAME("oslinuxtbl")
 typedef struct osl_table_info {
 	struct osl_table_info *next;
 	u32 instance;
-	char signature[ACPI_NAME_SIZE];
+	char signature[ACPI_NAMESEG_SIZE];
 
 } osl_table_info;
 
@@ -286,14 +286,14 @@ static acpi_status osl_add_table_to_list(char *signature, u32 instance)
 		return (AE_NO_MEMORY);
 	}
 
-	ACPI_MOVE_NAME(new_info->signature, signature);
+	ACPI_COPY_NAMESEG(new_info->signature, signature);
 
 	if (!gbl_table_list_head) {
 		gbl_table_list_head = new_info;
 	} else {
 		next = gbl_table_list_head;
 		while (1) {
-			if (ACPI_COMPARE_NAME(next->signature, signature)) {
+			if (ACPI_COMPARE_NAMESEG(next->signature, signature)) {
 				if (next->instance == instance) {
 					found = TRUE;
 				}
@@ -782,11 +782,11 @@ osl_get_bios_table(char *signature,
 
 	/* Handle special tables whose addresses are not in RSDT/XSDT */
 
-	if (ACPI_COMPARE_NAME(signature, ACPI_RSDP_NAME) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_RSDT) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) {
+	if (ACPI_COMPARE_NAMESEG(signature, ACPI_RSDP_NAME) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_RSDT) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_XSDT) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_DSDT) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_FACS)) {
 
 find_next_instance:
 
@@ -797,7 +797,7 @@ find_next_instance:
 		 * careful about the FADT length and validate table addresses.
 		 * Note: The 64-bit addresses have priority.
 		 */
-		if (ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT)) {
+		if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_DSDT)) {
 			if (current_instance < 2) {
 				if ((gbl_fadt->header.length >=
 				     MIN_FADT_FOR_XDSDT) && gbl_fadt->Xdsdt
@@ -815,7 +815,7 @@ find_next_instance:
 					    dsdt;
 				}
 			}
-		} else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) {
+		} else if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_FACS)) {
 			if (current_instance < 2) {
 				if ((gbl_fadt->header.length >=
 				     MIN_FADT_FOR_XFACS) && gbl_fadt->Xfacs
@@ -833,7 +833,7 @@ find_next_instance:
 					    facs;
 				}
 			}
-		} else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT)) {
+		} else if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_XSDT)) {
 			if (!gbl_revision) {
 				return (AE_BAD_SIGNATURE);
 			}
@@ -842,7 +842,7 @@ find_next_instance:
 				    (acpi_physical_address)gbl_rsdp.
 				    xsdt_physical_address;
 			}
-		} else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_RSDT)) {
+		} else if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_RSDT)) {
 			if (current_instance == 0) {
 				table_address =
 				    (acpi_physical_address)gbl_rsdp.
@@ -931,7 +931,7 @@ find_next_instance:
 
 			/* Does this table match the requested signature? */
 
-			if (!ACPI_COMPARE_NAME
+			if (!ACPI_COMPARE_NAMESEG
 			    (mapped_table->signature, signature)) {
 				osl_unmap_table(mapped_table);
 				mapped_table = NULL;
@@ -995,7 +995,7 @@ static acpi_status osl_list_customized_tables(char *directory)
 {
 	void *table_dir;
 	u32 instance;
-	char temp_name[ACPI_NAME_SIZE];
+	char temp_name[ACPI_NAMESEG_SIZE];
 	char *filename;
 	acpi_status status = AE_OK;
 
@@ -1086,8 +1086,8 @@ osl_map_table(acpi_size address,
 				return (AE_BAD_SIGNATURE);
 			}
 		} else
-		    if (!ACPI_COMPARE_NAME(signature, mapped_table->signature))
-		{
+		    if (!ACPI_COMPARE_NAMESEG
+			(signature, mapped_table->signature)) {
 			acpi_os_unmap_memory(mapped_table,
 					     sizeof(struct acpi_table_header));
 			return (AE_BAD_SIGNATURE);
@@ -1158,15 +1158,15 @@ osl_table_name_from_file(char *filename, char *signature, u32 *instance)
 
 	/* Ignore meaningless files */
 
-	if (strlen(filename) < ACPI_NAME_SIZE) {
+	if (strlen(filename) < ACPI_NAMESEG_SIZE) {
 		return (AE_BAD_SIGNATURE);
 	}
 
 	/* Extract instance number */
 
-	if (isdigit((int)filename[ACPI_NAME_SIZE])) {
-		sscanf(&filename[ACPI_NAME_SIZE], "%u", instance);
-	} else if (strlen(filename) != ACPI_NAME_SIZE) {
+	if (isdigit((int)filename[ACPI_NAMESEG_SIZE])) {
+		sscanf(&filename[ACPI_NAMESEG_SIZE], "%u", instance);
+	} else if (strlen(filename) != ACPI_NAMESEG_SIZE) {
 		return (AE_BAD_SIGNATURE);
 	} else {
 		*instance = 0;
@@ -1174,7 +1174,7 @@ osl_table_name_from_file(char *filename, char *signature, u32 *instance)
 
 	/* Extract signature */
 
-	ACPI_MOVE_NAME(signature, filename);
+	ACPI_COPY_NAMESEG(signature, filename);
 	return (AE_OK);
 }
 
@@ -1236,7 +1236,7 @@ osl_read_table_from_file(char *filename,
 				status = AE_BAD_SIGNATURE;
 				goto exit;
 			}
-		} else if (!ACPI_COMPARE_NAME(signature, header.signature)) {
+		} else if (!ACPI_COMPARE_NAMESEG(signature, header.signature)) {
 			fprintf(stderr,
 				"Incorrect signature: Expecting %4.4s, found %4.4s\n",
 				signature, header.signature);
@@ -1311,7 +1311,7 @@ osl_get_customized_table(char *pathname,
 {
 	void *table_dir;
 	u32 current_instance = 0;
-	char temp_name[ACPI_NAME_SIZE];
+	char temp_name[ACPI_NAMESEG_SIZE];
 	char table_filename[PATH_MAX];
 	char *filename;
 	acpi_status status;
@@ -1329,7 +1329,7 @@ osl_get_customized_table(char *pathname,
 
 		/* Ignore meaningless files */
 
-		if (!ACPI_COMPARE_NAME(filename, signature)) {
+		if (!ACPI_COMPARE_NAMESEG(filename, signature)) {
 			continue;
 		}
 
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index e256c2ac5ddc..820baeb5092b 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -289,14 +289,14 @@ int ap_dump_table_by_address(char *ascii_address)
 
 int ap_dump_table_by_name(char *signature)
 {
-	char local_signature[ACPI_NAME_SIZE + 1];
+	char local_signature[ACPI_NAMESEG_SIZE + 1];
 	u32 instance;
 	struct acpi_table_header *table;
 	acpi_physical_address address;
 	acpi_status status;
 	int table_status;
 
-	if (strlen(signature) != ACPI_NAME_SIZE) {
+	if (strlen(signature) != ACPI_NAMESEG_SIZE) {
 		fprintf(stderr,
 			"Invalid table signature [%s]: must be exactly 4 characters\n",
 			signature);
@@ -310,9 +310,9 @@ int ap_dump_table_by_name(char *signature)
 
 	/* To be friendly, handle tables whose signatures do not match the name */
 
-	if (ACPI_COMPARE_NAME(local_signature, "FADT")) {
+	if (ACPI_COMPARE_NAMESEG(local_signature, "FADT")) {
 		strcpy(local_signature, ACPI_SIG_FADT);
-	} else if (ACPI_COMPARE_NAME(local_signature, "MADT")) {
+	} else if (ACPI_COMPARE_NAMESEG(local_signature, "MADT")) {
 		strcpy(local_signature, ACPI_SIG_MADT);
 	}
 
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index 49972bc78bc5..a42cfcaa3293 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -97,7 +97,7 @@ int ap_open_output_file(char *pathname)
 
 int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance)
 {
-	char filename[ACPI_NAME_SIZE + 16];
+	char filename[ACPI_NAMESEG_SIZE + 16];
 	char instance_str[16];
 	ACPI_FILE file;
 	acpi_size actual;
@@ -110,16 +110,16 @@ int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance)
 	/* Construct lower-case filename from the table local signature */
 
 	if (ACPI_VALIDATE_RSDP_SIG(table->signature)) {
-		ACPI_MOVE_NAME(filename, ACPI_RSDP_NAME);
+		ACPI_COPY_NAMESEG(filename, ACPI_RSDP_NAME);
 	} else {
-		ACPI_MOVE_NAME(filename, table->signature);
+		ACPI_COPY_NAMESEG(filename, table->signature);
 	}
 
 	filename[0] = (char)tolower((int)filename[0]);
 	filename[1] = (char)tolower((int)filename[1]);
 	filename[2] = (char)tolower((int)filename[2]);
 	filename[3] = (char)tolower((int)filename[3]);
-	filename[ACPI_NAME_SIZE] = 0;
+	filename[ACPI_NAMESEG_SIZE] = 0;
 
 	/* Handle multiple SSDts - create different filenames for each */
 
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index fb11240b758b..9093a8f64dc6 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -375,6 +375,31 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"calls: ptr null check in subprog",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.fixup_map_hash_48b = { 3 },
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+	.retval = 0,
+},
+{
 	"calls: two calls with args",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c
index e3fc22e672c2..d5c596fdc4b9 100644
--- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c
@@ -631,3 +631,25 @@
 	.errstr = "invalid access to packet",
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
+{
+	"direct packet access: test29 (reg > pkt_end in subprog)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 4715cfba20dc..93f99c6b7d79 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -288,8 +288,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 #endif
 	max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
 	guest_page_size = (1ul << guest_page_shift);
-	/* 1G of guest page sized pages */
-	guest_num_pages = (1ul << (30 - guest_page_shift));
+	/*
+	 * A little more than 1G of guest page sized pages.  Cover the
+	 * case where the size is not aligned to 64 pages.
+	 */
+	guest_num_pages = (1ul << (30 - guest_page_shift)) + 3;
 	host_page_size = getpagesize();
 	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
 			 !!((guest_num_pages * guest_page_size) % host_page_size);
@@ -359,7 +362,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
 #ifdef USE_CLEAR_DIRTY_LOG
 		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       DIV_ROUND_UP(host_num_pages, 64) * 64);
+				       host_num_pages);
 #endif
 		vm_dirty_log_verify(bmap);
 		iteration++;
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 264425f75806..9a21e912097c 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -141,7 +141,13 @@ int main(int argc, char *argv[])
 
 	free(hv_cpuid_entries);
 
-	vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+	if (rv) {
+		fprintf(stderr,
+			"Enlightened VMCS is unsupported, skip related test\n");
+		goto vm_free;
+	}
 
 	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
 	if (!hv_cpuid_entries)
@@ -151,6 +157,7 @@ int main(int argc, char *argv[])
 
 	free(hv_cpuid_entries);
 
+vm_free:
 	kvm_vm_free(vm);
 
 	return 0;
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index d4cfb6a7a086..4b7e107865bf 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -27,6 +27,7 @@ log_test()
 		nsuccess=$((nsuccess+1))
 		printf "\n    TEST: %-50s  [ OK ]\n" "${msg}"
 	else
+		ret=1
 		nfail=$((nfail+1))
 		printf "\n    TEST: %-50s  [FAIL]\n" "${msg}"
 		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
@@ -147,8 +148,8 @@ fib_rule6_test()
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
-		match="ipproto icmp"
-		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+		match="ipproto ipv6-icmp"
+		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match"
 	fi
 }
 
@@ -245,4 +246,9 @@ setup
 run_fibrule_tests
 cleanup
 
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
+
 exit $ret
diff --git a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
index 43540f1828cc..2deea2169fc2 100755
--- a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
+++ b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Extract the number of CPUs expected from the specified Kconfig-file
 # fragment by checking CONFIG_SMP and CONFIG_NR_CPUS.  If the specified
@@ -7,23 +8,9 @@
 #
 # Usage: configNR_CPUS.sh config-frag
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 cf=$1
 if test ! -r $cf
diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh
index ef7fcbac3d42..90016c359e83 100755
--- a/tools/testing/selftests/rcutorture/bin/config_override.sh
+++ b/tools/testing/selftests/rcutorture/bin/config_override.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # config_override.sh base override
 #
@@ -6,23 +7,9 @@
 # that conflict with any in override, concatenating what remains and
 # sending the result to standard output.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2017
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 base=$1
 if test -r $base
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
index 197deece7c7c..31584cee84d7 100755
--- a/tools/testing/selftests/rcutorture/bin/configcheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -1,23 +1,11 @@
 #!/bin/bash
-# Usage: configcheck.sh .config .config-template
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
+# SPDX-License-Identifier: GPL-2.0+
 #
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
+# Usage: configcheck.sh .config .config-template
 #
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/abat-chk-config.sh.$$
 trap 'rm -rf $T' 0
@@ -26,6 +14,7 @@ mkdir $T
 cat $1 > $T/.config
 
 cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' |
+grep -v '^CONFIG_INITRAMFS_SOURCE' |
 awk	'
 {
 		print "if grep -q \"" $0 "\" < '"$T/.config"'";
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 65541c21a544..40359486b3a8 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Usage: configinit.sh config-spec-file build-output-dir results-dir
 #
@@ -14,23 +15,9 @@
 # for example, "O=/tmp/foo".  If this argument is omitted, the .config
 # file will be generated directly in the current directory.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/configinit.sh.$$
 trap 'rm -rf $T' 0
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
index bb99cde3f5f9..ff7102212703 100755
--- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Get an estimate of how CPU-hoggy to be.
 #
 # Usage: cpus2use.sh
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
 idlecpus=`mpstat | tail -1 | \
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 65f6655026f0..6bcb8b5b2ff2 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # bootparam_hotplug_cpu bootparam-string
 #
diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh
index 3633828375e3..435b60933985 100755
--- a/tools/testing/selftests/rcutorture/bin/jitter.sh
+++ b/tools/testing/selftests/rcutorture/bin/jitter.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Alternate sleeping and spinning on randomly selected CPUs.  The purpose
 # of this script is to inflict random OS jitter on a concurrently running
@@ -11,23 +12,9 @@
 # sleepmax: Maximum microseconds to sleep, defaults to one second.
 # spinmax: Maximum microseconds to spin, defaults to one millisecond.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2016
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 me=$(($1 * 1000))
 duration=$2
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 9115fcdb5617..c27a0bbb9c02 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
 # Usage: kvm-build.sh config-template build-dir resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 config_template=${1}
 if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index 98f650c9bf54..8426fe1f15ee 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Invoke a text editor on all console.log files for all runs with diagnostics,
 # that is, on all such files having a console.log.diags counterpart.
@@ -10,6 +11,10 @@
 #
 # The "directory" above should end with the date/time directory, for example,
 # "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+#
+# Copyright (C) IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 rundir="${1}"
 if test -z "$rundir" -o ! -d "$rundir"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
index 2de92f43ee8c..f3a7a5e2b89d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for locktorture progress.
 #
 # Usage: kvm-recheck-lock.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2014
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 if test -d "$i" -a -r "$i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 0fa8a61ccb7b..2a7f3f4756a7 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for rcutorture progress.
 #
 # Usage: kvm-recheck-rcu.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2014
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 if test -d "$i" -a -r "$i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
index 8948f7926b21..7d3c2be66c64 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for rcuperf performance measurements,
 # looking for ftrace data.  Exits with 0 if data was found, analyzed, and
@@ -7,23 +8,9 @@
 #
 # Usage: kvm-recheck-rcuperf-ftrace.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2016
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 . functions.sh
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh
index ccebf772fa1e..db0375a57f28 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for rcuperf performance measurements.
 #
 # Usage: kvm-recheck-rcuperf.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2016
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 if test -d "$i" -a -r "$i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index c9bab57a77eb..2adde6aaafdb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Given the results directories for previous KVM-based torture runs,
 # check the build and console output for errors.  Given a directory
@@ -6,23 +7,9 @@
 #
 # Usage: kvm-recheck.sh resdir ...
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
 . functions.sh
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 58ca758a5786..0eb1ec16d78a 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Run a kvm-based test of the specified tree on the specified configs.
 # Fully automated run and error checking, no graphics console.
@@ -20,23 +21,9 @@
 #
 # More sophisticated argument parsing is clearly needed.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 19864f1cb27a..8f1e337b9b54 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Run a series of tests under KVM.  By default, this series is specified
 # by the relevant CFLIST file, but can be overridden by the --configs
@@ -6,23 +7,9 @@
 #
 # Usage: kvm.sh [ options ]
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 scriptname=$0
 args="$*"
diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
index 83552bb007b4..6fa9bd1ddc09 100755
--- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
+++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
@@ -1,21 +1,8 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Create an initrd directory if one does not already exist.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
 # Author: Connor Shu <Connor.Shu@ibm.com>
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 24fe5f822b28..0701b3bf6ade 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Check the build output from an rcutorture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
@@ -8,23 +9,9 @@
 #
 # Usage: parse-build.sh file title
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 F=$1
 title=$2
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 84933f6aed77..4508373a922f 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Check the console output from an rcutorture run for oopses.
 # The "file" is a pathname on the local system, and "title" is
@@ -6,23 +7,9 @@
 #
 # Usage: parse-console.sh file title
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/parse-console.sh.$$
 file="$1"
diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
index 80eb646e1319..d3e4b2971f92 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Kernel-version-dependent shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2014
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # locktorture_param_onoff bootparam-string config-file
 #
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 7bab8246392b..effa415f9b92 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Kernel-version-dependent shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # rcutorture_param_n_barrier_cbs bootparam-string
 #
diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
index d36b8fd6f0fc..777d5b0c190f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Torture-suite-dependent shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2015
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # per_version_boot_params bootparam-string config-file seconds
 #
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 1069e85258ce..0afdf7957974 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: LGPL-2.1 OR MIT */
 
-#define RSEQ_SIG	0x53053053
+/*
+ * RSEQ_SIG uses the trap4 instruction. As Linux does not make use of the
+ * access-register mode nor the linkage stack this instruction will always
+ * cause a special-operation exception (the trap-enabled bit in the DUCT
+ * is and will stay 0). The instruction pattern is
+ *	b2 ff 0f ff	trap4	4095(%r0)
+ */
+#define RSEQ_SIG	0xB2FF0FFF
 
 #define rseq_smp_mb()	__asm__ __volatile__ ("bcr 15,0" ::: "memory")
 #define rseq_smp_rmb()	rseq_smp_mb()
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index f69d2ee29742..5019cdae5d0b 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -2166,11 +2166,14 @@ TEST(detect_seccomp_filter_flags)
 				 SECCOMP_FILTER_FLAG_LOG,
 				 SECCOMP_FILTER_FLAG_SPEC_ALLOW,
 				 SECCOMP_FILTER_FLAG_NEW_LISTENER };
-	unsigned int flag, all_flags;
+	unsigned int exclusive[] = {
+				SECCOMP_FILTER_FLAG_TSYNC,
+				SECCOMP_FILTER_FLAG_NEW_LISTENER };
+	unsigned int flag, all_flags, exclusive_mask;
 	int i;
 	long ret;
 
-	/* Test detection of known-good filter flags */
+	/* Test detection of individual known-good filter flags */
 	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
 		int bits = 0;
 
@@ -2197,16 +2200,29 @@ TEST(detect_seccomp_filter_flags)
 		all_flags |= flag;
 	}
 
-	/* Test detection of all known-good filter flags */
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
-	EXPECT_EQ(-1, ret);
-	EXPECT_EQ(EFAULT, errno) {
-		TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
-		       all_flags);
+	/*
+	 * Test detection of all known-good filter flags combined. But
+	 * for the exclusive flags we need to mask them out and try them
+	 * individually for the "all flags" testing.
+	 */
+	exclusive_mask = 0;
+	for (i = 0; i < ARRAY_SIZE(exclusive); i++)
+		exclusive_mask |= exclusive[i];
+	for (i = 0; i < ARRAY_SIZE(exclusive); i++) {
+		flag = all_flags & ~exclusive_mask;
+		flag |= exclusive[i];
+
+		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+		EXPECT_EQ(-1, ret);
+		EXPECT_EQ(EFAULT, errno) {
+			TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+			       flag);
+		}
 	}
 
-	/* Test detection of an unknown filter flag */
+	/* Test detection of an unknown filter flags, without exclusives. */
 	flag = -1;
+	flag &= ~exclusive_mask;
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
 	EXPECT_EQ(-1, ret);
 	EXPECT_EQ(EINVAL, errno) {
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 3417f2dbc366..7fc272ecae16 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -508,6 +508,14 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 
 	/*
+	 * Update the timer output so that it is likely to match the
+	 * state we're about to restore. If the timer expires between
+	 * this point and the register restoration, we'll take the
+	 * interrupt anyway.
+	 */
+	kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer);
+
+	/*
 	 * When using a userspace irqchip with the architected timers and a
 	 * host interrupt controller that doesn't support an active state, we
 	 * must still prevent continuously exiting from the guest, and
@@ -730,7 +738,6 @@ static void kvm_timer_init_interrupt(void *info)
 int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
 {
 	struct arch_timer_context *timer;
-	bool level;
 
 	switch (regid) {
 	case KVM_REG_ARM_TIMER_CTL:
@@ -758,10 +765,6 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
 		return -1;
 	}
 
-	level = kvm_timer_should_fire(timer);
-	kvm_timer_update_irq(vcpu, level, timer);
-	timer_emulate(timer);
-
 	return 0;
 }
 
@@ -812,7 +815,7 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		val = kvm_phys_timer_read() - timer->cntvoff - timer->cnt_cval;
+		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
 		break;
 
 	case TIMER_REG_CTL:
@@ -858,7 +861,7 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = val - kvm_phys_timer_read() - timer->cntvoff;
+		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val;
 		break;
 
 	case TIMER_REG_CTL:
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 99c37384ba7b..f412ebc90610 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -934,7 +934,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			       const struct kvm_vcpu_init *init)
 {
-	unsigned int i;
+	unsigned int i, ret;
 	int phys_target = kvm_target_cpu();
 
 	if (init->target != phys_target)
@@ -969,9 +969,14 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	vcpu->arch.target = phys_target;
 
 	/* Now we know what it is, we can reset it. */
-	return kvm_reset_vcpu(vcpu);
-}
+	ret = kvm_reset_vcpu(vcpu);
+	if (ret) {
+		vcpu->arch.target = -1;
+		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
+	}
 
+	return ret;
+}
 
 static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 					 struct kvm_vcpu_init *init)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 27c958306449..74b6582eaa3c 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -189,7 +189,7 @@ static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pte_free_kernel(NULL, pte_table);
+	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
 
@@ -1781,8 +1781,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		 * Only PMD_SIZE transparent hugepages(THP) are
 		 * currently supported. This code will need to be
 		 * updated to support other THP sizes.
+		 *
+		 * Make sure the host VA and the guest IPA are sufficiently
+		 * aligned and that the block is contained within the memslot.
 		 */
-		if (transparent_hugepage_adjust(&pfn, &fault_ipa))
+		if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+		    transparent_hugepage_adjust(&pfn, &fault_ipa))
 			vma_pagesize = PMD_SIZE;
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 4a12322bf7df..9f4843fe9cda 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -200,6 +200,9 @@ static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
 
 	vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;
 
+	if (was_enabled && !vgic_cpu->lpis_enabled)
+		vgic_flush_pending_lpis(vcpu);
+
 	if (!was_enabled && vgic_cpu->lpis_enabled)
 		vgic_enable_lpis(vcpu);
 }
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 3af69f2a3866..191deccf60bf 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -151,6 +151,27 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 	kfree(irq);
 }
 
+void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_irq *irq, *tmp;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);
+
+	list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
+		if (irq->intid >= VGIC_MIN_LPI) {
+			raw_spin_lock(&irq->irq_lock);
+			list_del(&irq->ap_list);
+			irq->vcpu = NULL;
+			raw_spin_unlock(&irq->irq_lock);
+			vgic_put_irq(vcpu->kvm, irq);
+		}
+	}
+
+	raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);
+}
+
 void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
 {
 	WARN_ON(irq_set_irqchip_state(irq->host_irq,
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index a90024718ca4..abeeffabc456 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -238,6 +238,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
 void vgic_enable_lpis(struct kvm_vcpu *vcpu);
+void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu);
 int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
 int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
 int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dc8edc97ba85..a704d1f9bd96 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1240,7 +1240,7 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
-	if ((log->first_page & 63) || (log->num_pages & 63))
+	if (log->first_page & 63)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -1253,8 +1253,9 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	n = kvm_dirty_bitmap_bytes(memslot);
 
 	if (log->first_page > memslot->npages ||
-	    log->num_pages > memslot->npages - log->first_page)
-			return -EINVAL;
+	    log->num_pages > memslot->npages - log->first_page ||
+	    (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
+	    return -EINVAL;
 
 	*flush = false;
 	dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);