Merge remote-tracking branch 'tip/auto-latest'

Conflicts:
	drivers/acpi/acpi_extlog.c
	drivers/acpi/processor_idle.c

422 files changed, 14886 insertions, 2549 deletions

diff --git a/Documentation/ABI/testing/sysfs-firmware-efi b/Documentation/ABI/testing/sysfs-firmware-efi
new file mode 100644
index 000000000000..05874da7ce80
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi
@@ -0,0 +1,20 @@
+What:		/sys/firmware/efi/fw_vendor
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of firmware vendor field in the
+		EFI system table.
+Users:		Kexec
+
+What:		/sys/firmware/efi/runtime
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of runtime service table entry in
+		the EFI system table.
+Users:		Kexec
+
+What:		/sys/firmware/efi/config_table
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of config table entry in the EFI
+		system table.
+Users:		Kexec
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
new file mode 100644
index 000000000000..c61b9b348e99
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
@@ -0,0 +1,34 @@
+What:		/sys/firmware/efi/runtime-map/
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	Switching efi runtime services to virtual mode requires
+		that all efi memory ranges which have the runtime attribute
+		bit set to be mapped to virtual addresses.
+
+		The efi runtime services can only be switched to virtual
+		mode once without rebooting. The kexec kernel must maintain
+		the same physical to virtual address mappings as the first
+		kernel. The mappings are exported to sysfs so userspace tools
+		can reassemble them and pass them into the kexec kernel.
+
+		/sys/firmware/efi/runtime-map/ is the directory the kernel
+		exports that information in.
+
+		subdirectories are named with the number of the memory range:
+
+			/sys/firmware/efi/runtime-map/0
+			/sys/firmware/efi/runtime-map/1
+			/sys/firmware/efi/runtime-map/2
+			/sys/firmware/efi/runtime-map/3
+			...
+
+		Each subdirectory contains five files:
+
+		attribute : The attributes of the memory range.
+		num_pages : The size of the memory range in pages.
+		phys_addr : The physical address of the memory range.
+		type      : The type of the memory range.
+		virt_addr : The virtual address of the memory range.
+
+		Above values are all hexadecimal numbers with the '0x' prefix.
+Users:		Kexec
diff --git a/Documentation/ABI/testing/sysfs-kernel-boot_params b/Documentation/ABI/testing/sysfs-kernel-boot_params
new file mode 100644
index 000000000000..eca38ce2852d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-boot_params
@@ -0,0 +1,38 @@
+What:		/sys/kernel/boot_params
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	The /sys/kernel/boot_params directory contains two
+		files: "data" and "version" and one subdirectory "setup_data".
+		It is used to export the kernel boot parameters of an x86
+		platform to userspace for kexec and debugging purpose.
+
+		If there's no setup_data in boot_params the subdirectory will
+		not be created.
+
+		"data" file is the binary representation of struct boot_params.
+
+		"version" file is the string representation of boot
+		protocol version.
+
+		"setup_data" subdirectory contains the setup_data data
+		structure in boot_params. setup_data is maintained in kernel
+		as a link list. In "setup_data" subdirectory there's one
+		subdirectory for each link list node named with the number
+		of the list nodes. The list node subdirectory contains two
+		files "type" and "data". "type" file is the string
+		representation of setup_data type. "data" file is the binary
+		representation of setup_data payload.
+
+		The whole boot_params directory structure is like below:
+		/sys/kernel/boot_params
+		|__ data
+		|__ setup_data
+		|   |__ 0
+		|   |   |__ data
+		|   |   |__ type
+		|   |__ 1
+		|       |__ data
+		|       |__ type
+		|__ version
+
+Users:		Kexec
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index f3778f8952da..910870b15acd 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -396,14 +396,14 @@ o	Each element of the form "3/3 ..>. 0:7 ^0" represents one rcu_node
 
 The output of "cat rcu/rcu_sched/rcu_pending" looks as follows:
 
-  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903
-  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113
-  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889
-  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469
-  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042
-  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422
-  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699
-  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147
+  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903 ndw=0
+  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113 ndw=0
+  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889 ndw=0
+  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469 ndw=0
+  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042 ndw=0
+  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422 ndw=0
+  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699 ndw=0
+  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147 ndw=0
 
 The fields are as follows:
 
@@ -432,6 +432,10 @@ o	"gpc" is the number of times that an old grace period had
 o	"gps" is the number of times that a new grace period had started,
 	but this CPU was not yet aware of it.
 
+o	"ndw" is the number of times that a wakeup of an rcuo
+	callback-offload kthread had to be deferred in order to avoid
+	deadlock.
+
 o	"nn" is the number of times that this CPU needed nothing.
 
 
@@ -443,7 +447,7 @@ The output of "cat rcu/rcuboost" looks as follows:
     balk: nt=0 egt=6541 bt=0 nb=0 ny=126 nos=0
 
 This information is output only for rcu_preempt.  Each two-line entry
-corresponds to a leaf rcu_node strcuture.  The fields are as follows:
+corresponds to a leaf rcu_node structure.  The fields are as follows:
 
 o	"n:m" is the CPU-number range for the corresponding two-line
 	entry.  In the sample output above, the first entry covers
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/acpi/apei/einj.txt
index a58b63da1a36..f51861bcb07b 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/acpi/apei/einj.txt
@@ -45,11 +45,22 @@ directory apei/einj. The following files are provided.
   injection. Before this, please specify all necessary error
   parameters.
 
+- flags
+  Present for kernel version 3.13 and above. Used to specify which
+  of param{1..4} are valid and should be used by BIOS during 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 (param4 below)
+  If set to zero, legacy behaviour is used where the type of injection
+  specifies just one bit set, and param1 is multiplexed.
+
 - param1
   This file is used to set the first error parameter value. Effect of
   parameter depends on error_type specified. For example, if error
   type is memory related type, the param1 should be a valid physical
-  memory address.
+  memory address. [Unless "flag" is set - see above]
 
 - param2
   This file is used to set the second error parameter value. Effect of
@@ -58,6 +69,12 @@ directory apei/einj. The following files are provided.
   address mask. Linux requires page or narrower granularity, say,
   0xfffffffffffff000.
 
+- param3
+  Used when the 0x1 bit is set in "flag" to specify the APIC id
+
+- param4
+  Used when the 0x4 bit is set in "flag" to specify target PCIe device
+
 - notrigger
   The EINJ mechanism is a two step process. First inject the error, then
   perform some actions to trigger it. Setting "notrigger" to 1 skips the
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
index 8117e5bf6065..88951b179262 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/circular-buffers.txt
@@ -160,6 +160,7 @@ The producer will look something like this:
 	spin_lock(&producer_lock);
 
 	unsigned long head = buffer->head;
+	/* The spin_unlock() and next spin_lock() provide needed ordering. */
 	unsigned long tail = ACCESS_ONCE(buffer->tail);
 
 	if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
@@ -168,9 +169,8 @@ The producer will look something like this:
 
 		produce_item(item);
 
-		smp_wmb(); /* commit the item before incrementing the head */
-
-		buffer->head = (head + 1) & (buffer->size - 1);
+		smp_store_release(buffer->head,
+				  (head + 1) & (buffer->size - 1));
 
 		/* wake_up() will make sure that the head is committed before
 		 * waking anyone up */
@@ -183,9 +183,14 @@ This will instruct the CPU that the contents of the new item must be written
 before the head index makes it available to the consumer and then instructs the
 CPU that the revised head index must be written before the consumer is woken.
 
-Note that wake_up() doesn't have to be the exact mechanism used, but whatever
-is used must guarantee a (write) memory barrier between the update of the head
-index and the change of state of the consumer, if a change of state occurs.
+Note that wake_up() does not guarantee any sort of barrier unless something
+is actually awakened.  We therefore cannot rely on it for ordering.  However,
+there is always one element of the array left empty.  Therefore, the
+producer must produce two elements before it could possibly corrupt the
+element currently being read by the consumer.  Therefore, the unlock-lock
+pair between consecutive invocations of the consumer provides the necessary
+ordering between the read of the index indicating that the consumer has
+vacated a given element and the write by the producer to that same element.
 
 
 THE CONSUMER
@@ -195,21 +200,20 @@ The consumer will look something like this:
 
 	spin_lock(&consumer_lock);
 
-	unsigned long head = ACCESS_ONCE(buffer->head);
+	/* Read index before reading contents at that index. */
+	unsigned long head = smp_load_acquire(buffer->head);
 	unsigned long tail = buffer->tail;
 
 	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
-		/* read index before reading contents at that index */
-		smp_read_barrier_depends();
 
 		/* extract one item from the buffer */
 		struct item *item = buffer[tail];
 
 		consume_item(item);
 
-		smp_mb(); /* finish reading descriptor before incrementing tail */
-
-		buffer->tail = (tail + 1) & (buffer->size - 1);
+		/* Finish reading descriptor before incrementing tail. */
+		smp_store_release(buffer->tail,
+				  (tail + 1) & (buffer->size - 1));
 	}
 
 	spin_unlock(&consumer_lock);
@@ -218,12 +222,17 @@ This will instruct the CPU to make sure the index is up to date before reading
 the new item, and then it shall make sure the CPU has finished reading the item
 before it writes the new tail pointer, which will erase the item.
 
-
-Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
-This prevents the compiler from discarding and reloading its cached value -
-which some compilers will do across smp_read_barrier_depends().  This isn't
-strictly needed if you can be sure that the opposition index will _only_ be
-used the once.
+Note the use of ACCESS_ONCE() and smp_load_acquire() to read the
+opposition index.  This prevents the compiler from discarding and
+reloading its cached value - which some compilers will do across
+smp_read_barrier_depends().  This isn't strictly needed if you can
+be sure that the opposition index will _only_ be used the once.
+The smp_load_acquire() additionally forces the CPU to order against
+subsequent memory references.  Similarly, smp_store_release() is used
+in both algorithms to write the thread's index.  This documents the
+fact that we are writing to something that can be read concurrently,
+prevents the compiler from tearing the store, and enforces ordering
+against previous accesses.
 
 
 ===============
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 50a58adfeaf9..e0ebffef5183 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -888,6 +888,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 			The xen output can only be used by Xen PV guests.
 
+	edac_report=	[HW,EDAC] Control how to report EDAC event
+			Format: {"on" | "off" | "force"}
+			on: enable EDAC to report H/W event. May be overridden
+			by other higher priority error reporting module.
+			off: disable H/W event reporting through EDAC.
+			force: enforce the use of EDAC to report H/W event.
+			default: on.
+
 	ekgdboc=	[X86,KGDB] Allow early kernel console debugging
 			ekgdboc=kbd
 
@@ -897,6 +905,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
+	efi=		[EFI]
+			Format: { "old_map" }
+			old_map [X86-64]: switch to the old ioremap-based EFI
+			runtime services mapping. 32-bit still uses this one by
+			default.
+
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
 			your efi variable storage. Use this parameter only if
@@ -2001,6 +2015,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
+	nokaslr		[X86]
+			Disable kernel base offset ASLR (Address Space
+			Layout Randomization) if built into the kernel.
+
 	noautogroup	Disable scheduler automatic task group creation.
 
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
@@ -2634,7 +2652,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			for RCU-preempt, and "s" for RCU-sched, and "N"
 			is the CPU number.  This reduces OS jitter on the
 			offloaded CPUs, which can be useful for HPC and
-
 			real-time workloads.  It can also improve energy
 			efficiency for asymmetric multiprocessors.
 
@@ -2650,8 +2667,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			periodically wake up to do the polling.
 
 	rcutree.blimit=	[KNL]
-			Set maximum number of finished RCU callbacks to process
-			in one batch.
+			Set maximum number of finished RCU callbacks to
+			process in one batch.
 
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
@@ -2670,8 +2687,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			value is one, and maximum value is HZ.
 
 	rcutree.qhimark= [KNL]
-			Set threshold of queued
-			RCU callbacks over which batch limiting is disabled.
+			Set threshold of queued RCU callbacks beyond which
+			batch limiting is disabled.
 
 	rcutree.qlowmark= [KNL]
 			Set threshold of queued RCU callbacks below which
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index c8c42e64e953..cb753c8158f2 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -194,18 +194,22 @@ There are some minimal guarantees that may be expected of a CPU:
  (*) On any given CPU, dependent memory accesses will be issued in order, with
      respect to itself.  This means that for:
 
-	Q = P; D = *Q;
+	ACCESS_ONCE(Q) = P; smp_read_barrier_depends(); D = ACCESS_ONCE(*Q);
 
      the CPU will issue the following memory operations:
 
 	Q = LOAD P, D = LOAD *Q
 
-     and always in that order.
+     and always in that order.  On most systems, smp_read_barrier_depends()
+     does nothing, but it is required for DEC Alpha.  The ACCESS_ONCE()
+     is required to prevent compiler mischief.  Please note that you
+     should normally use something like rcu_dereference() instead of
+     open-coding smp_read_barrier_depends().
 
  (*) Overlapping loads and stores within a particular CPU will appear to be
      ordered within that CPU.  This means that for:
 
-	a = *X; *X = b;
+	a = ACCESS_ONCE(*X); ACCESS_ONCE(*X) = b;
 
      the CPU will only issue the following sequence of memory operations:
 
@@ -213,7 +217,7 @@ There are some minimal guarantees that may be expected of a CPU:
 
      And for:
 
-	*X = c; d = *X;
+	ACCESS_ONCE(*X) = c; d = ACCESS_ONCE(*X);
 
      the CPU will only issue:
 
@@ -224,6 +228,12 @@ There are some minimal guarantees that may be expected of a CPU:
 
 And there are a number of things that _must_ or _must_not_ be assumed:
 
+ (*) It _must_not_ be assumed that the compiler will do what you want with
+     memory references that are not protected by ACCESS_ONCE().  Without
+     ACCESS_ONCE(), the compiler is within its rights to do all sorts
+     of "creative" transformations, which are covered in the Compiler
+     Barrier section.
+
  (*) It _must_not_ be assumed that independent loads and stores will be issued
      in the order given.  This means that for:
 
@@ -392,12 +402,18 @@ And a couple of implicit varieties:
      Memory operations that occur after an UNLOCK operation may appear to
      happen before it completes.
 
-     LOCK and UNLOCK operations are guaranteed to appear with respect to each
-     other strictly in the order specified.
-
      The use of LOCK and UNLOCK operations generally precludes the need for
      other sorts of memory barrier (but note the exceptions mentioned in the
-     subsection "MMIO write barrier").
+     subsection "MMIO write barrier").  In addition, an UNLOCK+LOCK pair
+     is -not- guaranteed to act as a full memory barrier.  However,
+     after a LOCK on a given lock variable, all memory accesses preceding any
+     prior UNLOCK on that same variable are guaranteed to be visible.
+     In other words, within a given lock variable's critical section,
+     all accesses of all previous critical sections for that lock variable
+     are guaranteed to have completed.
+
+     This means that LOCK acts as a minimal "acquire" operation and
+     UNLOCK acts as a minimal "release" operation.
 
 
 Memory barriers are only required where there's a possibility of interaction
@@ -450,14 +466,14 @@ The usage requirements of data dependency barriers are a little subtle, and
 it's not always obvious that they're needed.  To illustrate, consider the
 following sequence of events:
 
-	CPU 1		CPU 2
-	===============	===============
+	CPU 1		      CPU 2
+	===============	      ===============
 	{ A == 1, B == 2, C = 3, P == &A, Q == &C }
 	B = 4;
 	<write barrier>
-	P = &B
-			Q = P;
-			D = *Q;
+	ACCESS_ONCE(P) = &B
+			      Q = ACCESS_ONCE(P);
+			      D = *Q;
 
 There's a clear data dependency here, and it would seem that by the end of the
 sequence, Q must be either &A or &B, and that:
@@ -477,15 +493,15 @@ Alpha).
 To deal with this, a data dependency barrier or better must be inserted
 between the address load and the data load:
 
-	CPU 1		CPU 2
-	===============	===============
+	CPU 1		      CPU 2
+	===============	      ===============
 	{ A == 1, B == 2, C = 3, P == &A, Q == &C }
 	B = 4;
 	<write barrier>
-	P = &B
-			Q = P;
-			<data dependency barrier>
-			D = *Q;
+	ACCESS_ONCE(P) = &B
+			      Q = ACCESS_ONCE(P);
+			      <data dependency barrier>
+			      D = *Q;
 
 This enforces the occurrence of one of the two implications, and prevents the
 third possibility from arising.
@@ -500,25 +516,26 @@ odd-numbered bank is idle, one can see the new value of the pointer P (&B),
 but the old value of the variable B (2).
 
 
-Another example of where data dependency barriers might by required is where a
+Another example of where data dependency barriers might be required is where a
 number is read from memory and then used to calculate the index for an array
 access:
 
-	CPU 1		CPU 2
-	===============	===============
+	CPU 1		      CPU 2
+	===============	      ===============
 	{ M[0] == 1, M[1] == 2, M[3] = 3, P == 0, Q == 3 }
 	M[1] = 4;
 	<write barrier>
-	P = 1
-			Q = P;
-			<data dependency barrier>
-			D = M[Q];
+	ACCESS_ONCE(P) = 1
+			      Q = ACCESS_ONCE(P);
+			      <data dependency barrier>
+			      D = M[Q];
 
 
-The data dependency barrier is very important to the RCU system, for example.
-See rcu_dereference() in include/linux/rcupdate.h.  This permits the current
-target of an RCU'd pointer to be replaced with a new modified target, without
-the replacement target appearing to be incompletely initialised.
+The data dependency barrier is very important to the RCU system,
+for example.  See rcu_assign_pointer() and rcu_dereference() in
+include/linux/rcupdate.h.  This permits the current target of an RCU'd
+pointer to be replaced with a new modified target, without the replacement
+target appearing to be incompletely initialised.
 
 See also the subsection on "Cache Coherency" for a more thorough example.
 
@@ -530,24 +547,190 @@ A control dependency requires a full read memory barrier, not simply a data
 dependency barrier to make it work correctly.  Consider the following bit of
 code:
 
-	q = &a;
-	if (p) {
-		<data dependency barrier>
-		q = &b;
+	q = ACCESS_ONCE(a);
+	if (q) {
+		<data dependency barrier>  /* BUG: No data dependency!!! */
+		p = ACCESS_ONCE(b);
 	}
-	x = *q;
 
 This will not have the desired effect because there is no actual data
-dependency, but rather a control dependency that the CPU may short-circuit by
-attempting to predict the outcome in advance.  In such a case what's actually
-required is:
+dependency, but rather a control dependency that the CPU may short-circuit
+by attempting to predict the outcome in advance, so that other CPUs see
+the load from b as having happened before the load from a.  In such a
+case what's actually required is:
 
-	q = &a;
-	if (p) {
+	q = ACCESS_ONCE(a);
+	if (q) {
 		<read barrier>
-		q = &b;
+		p = ACCESS_ONCE(b);
+	}
+
+However, stores are not speculated.  This means that ordering -is- provided
+in the following example:
+
+	q = ACCESS_ONCE(a);
+	if (ACCESS_ONCE(q)) {
+		ACCESS_ONCE(b) = p;
+	}
+
+Please note that ACCESS_ONCE() is not optional!  Without the ACCESS_ONCE(),
+the compiler is within its rights to transform this example:
+
+	q = a;
+	if (q) {
+		b = p;  /* BUG: Compiler can reorder!!! */
+		do_something();
+	} else {
+		b = p;  /* BUG: Compiler can reorder!!! */
+		do_something_else();
+	}
+
+into this, which of course defeats the ordering:
+
+	b = p;
+	q = a;
+	if (q)
+		do_something();
+	else
+		do_something_else();
+
+Worse yet, if the compiler is able to prove (say) that the value of
+variable 'a' is always non-zero, it would be well within its rights
+to optimize the original example by eliminating the "if" statement
+as follows:
+
+	q = a;
+	b = p;  /* BUG: Compiler can reorder!!! */
+	do_something();
+
+The solution is again ACCESS_ONCE(), which preserves the ordering between
+the load from variable 'a' and the store to variable 'b':
+
+	q = ACCESS_ONCE(a);
+	if (q) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = p;
+		do_something_else();
 	}
-	x = *q;
+
+You could also use barrier() to prevent the compiler from moving
+the stores to variable 'b', but barrier() would not prevent the
+compiler from proving to itself that a==1 always, so ACCESS_ONCE()
+is also needed.
+
+It is important to note that control dependencies absolutely require a
+a conditional.  For example, the following "optimized" version of
+the above example breaks ordering:
+
+	q = ACCESS_ONCE(a);
+	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
+	if (q) {
+		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+		do_something();
+	} else {
+		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+		do_something_else();
+	}
+
+It is of course legal for the prior load to be part of the conditional,
+for example, as follows:
+
+	if (ACCESS_ONCE(a) > 0) {
+		ACCESS_ONCE(b) = q / 2;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = q / 3;
+		do_something_else();
+	}
+
+This will again ensure that the load from variable 'a' is ordered before the
+stores to variable 'b'.
+
+In addition, you need to be careful what you do with the local variable 'q',
+otherwise the compiler might be able to guess the value and again remove
+the needed conditional.  For example:
+
+	q = ACCESS_ONCE(a);
+	if (q % MAX) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = p;
+		do_something_else();
+	}
+
+If MAX is defined to be 1, then the compiler knows that (q % MAX) is
+equal to zero, in which case the compiler is within its rights to
+transform the above code into the following:
+
+	q = ACCESS_ONCE(a);
+	ACCESS_ONCE(b) = p;
+	do_something_else();
+
+This transformation loses the ordering between the load from variable 'a'
+and the store to variable 'b'.  If you are relying on this ordering, you
+should do something like the following:
+
+	q = ACCESS_ONCE(a);
+	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
+	if (q % MAX) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = p;
+		do_something_else();
+	}
+
+Finally, control dependencies do -not- provide transitivity.  This is
+demonstrated by two related examples:
+
+	CPU 0                     CPU 1
+	=====================     =====================
+	r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
+	if (r1 >= 0)              if (r2 >= 0)
+	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
+
+	assert(!(r1 == 1 && r2 == 1));
+
+The above two-CPU example will never trigger the assert().  However,
+if control dependencies guaranteed transitivity (which they do not),
+then adding the following two CPUs would guarantee a related assertion:
+
+	CPU 2                     CPU 3
+	=====================     =====================
+	ACCESS_ONCE(x) = 2;       ACCESS_ONCE(y) = 2;
+
+	assert(!(r1 == 2 && r2 == 2 && x == 1 && y == 1)); /* FAILS!!! */
+
+But because control dependencies do -not- provide transitivity, the
+above assertion can fail after the combined four-CPU example completes.
+If you need the four-CPU example to provide ordering, you will need
+smp_mb() between the loads and stores in the CPU 0 and CPU 1 code fragments.
+
+In summary:
+
+  (*) Control dependencies can order prior loads against later stores.
+      However, they do -not- guarantee any other sort of ordering:
+      Not prior loads against later loads, nor prior stores against
+      later anything.  If you need these other forms of ordering,
+      use smb_rmb(), smp_wmb(), or, in the case of prior stores and
+      later loads, smp_mb().
+
+  (*) Control dependencies require at least one run-time conditional
+      between the prior load and the subsequent store.  If the compiler
+      is able to optimize the conditional away, it will have also
+      optimized away the ordering.  Careful use of ACCESS_ONCE() can
+      help to preserve the needed conditional.
+
+  (*) Control dependencies require that the compiler avoid reordering the
+      dependency into nonexistence.  Careful use of ACCESS_ONCE() or
+      barrier() can help to preserve your control dependency.  Please
+      see the Compiler Barrier section for more information.
+
+  (*) Control dependencies do -not- provide transitivity.  If you
+      need transitivity, use smp_mb().
 
 
 SMP BARRIER PAIRING
@@ -561,23 +744,23 @@ barrier, though a general barrier would also be viable.  Similarly a read
 barrier or a data dependency barrier should always be paired with at least an
 write barrier, though, again, a general barrier is viable:
 
-	CPU 1		CPU 2
-	===============	===============
-	a = 1;
+	CPU 1		      CPU 2
+	===============	      ===============
+	ACCESS_ONCE(a) = 1;
 	<write barrier>
-	b = 2;		x = b;
-			<read barrier>
-			y = a;
+	ACCESS_ONCE(b) = 2;   x = ACCESS_ONCE(b);
+			      <read barrier>
+			      y = ACCESS_ONCE(a);
 
 Or:
 
-	CPU 1		CPU 2
-	===============	===============================
+	CPU 1		      CPU 2
+	===============	      ===============================
 	a = 1;
 	<write barrier>
-	b = &a;		x = b;
-			<data dependency barrier>
-			y = *x;
+	ACCESS_ONCE(b) = &a;  x = ACCESS_ONCE(b);
+			      <data dependency barrier>
+			      y = *x;
 
 Basically, the read barrier always has to be there, even though it can be of
 the "weaker" type.
@@ -586,13 +769,13 @@ the "weaker" type.
 match the loads after the read barrier or the data dependency barrier, and vice
 versa:
 
-	CPU 1                           CPU 2
-	===============                 ===============
-	a = 1;           }----   --->{  v = c
-	b = 2;           }    \ /    {  w = d
-	<write barrier>        \        <read barrier>
-	c = 3;           }    / \    {  x = a;
-	d = 4;           }----   --->{  y = b;
+	CPU 1                               CPU 2
+	===================                 ===================
+	ACCESS_ONCE(a) = 1;  }----   --->{  v = ACCESS_ONCE(c);
+	ACCESS_ONCE(b) = 2;  }    \ /    {  w = ACCESS_ONCE(d);
+	<write barrier>            \        <read barrier>
+	ACCESS_ONCE(c) = 3;  }    / \    {  x = ACCESS_ONCE(a);
+	ACCESS_ONCE(d) = 4;  }----   --->{  y = ACCESS_ONCE(b);
 
 
 EXAMPLES OF MEMORY BARRIER SEQUENCES
@@ -882,12 +1065,12 @@ cache it for later use.
 
 Consider:
 
-	CPU 1	   		CPU 2
+	CPU 1			CPU 2
 	=======================	=======================
-	 	   		LOAD B
-	 	   		DIVIDE		} Divide instructions generally
-	 	   		DIVIDE		} take a long time to perform
-	 	   		LOAD A
+				LOAD B
+				DIVIDE		} Divide instructions generally
+				DIVIDE		} take a long time to perform
+				LOAD A
 
 Which might appear as this:
 
@@ -910,13 +1093,13 @@ Which might appear as this:
 Placing a read barrier or a data dependency barrier just before the second
 load:
 
-	CPU 1	   		CPU 2
+	CPU 1			CPU 2
 	=======================	=======================
-	 	   		LOAD B
-	 	   		DIVIDE
-	 	   		DIVIDE
+				LOAD B
+				DIVIDE
+				DIVIDE
 				<read barrier>
-	 	   		LOAD A
+				LOAD A
 
 will force any value speculatively obtained to be reconsidered to an extent
 dependent on the type of barrier used.  If there was no change made to the
@@ -1042,10 +1225,277 @@ compiler from moving the memory accesses either side of it to the other side:
 
 	barrier();
 
-This is a general barrier - lesser varieties of compiler barrier do not exist.
+This is a general barrier -- there are no read-read or write-write variants
+of barrier().  However, ACCESS_ONCE() can be thought of as a weak form
+for barrier() that affects only the specific accesses flagged by the
+ACCESS_ONCE().
+
+The barrier() function has the following effects:
+
+ (*) Prevents the compiler from reordering accesses following the
+     barrier() to precede any accesses preceding the barrier().
+     One example use for this property is to ease communication between
+     interrupt-handler code and the code that was interrupted.
+
+ (*) Within a loop, forces the compiler to load the variables used
+     in that loop's conditional on each pass through that loop.
+
+The ACCESS_ONCE() function can prevent any number of optimizations that,
+while perfectly safe in single-threaded code, can be fatal in concurrent
+code.  Here are some examples of these sorts of optimizations:
+
+ (*) The compiler is within its rights to merge successive loads from
+     the same variable.  Such merging can cause the compiler to "optimize"
+     the following code:
+
+	while (tmp = a)
+		do_something_with(tmp);
+
+     into the following code, which, although in some sense legitimate
+     for single-threaded code, is almost certainly not what the developer
+     intended:
+
+	if (tmp = a)
+		for (;;)
+			do_something_with(tmp);
+
+     Use ACCESS_ONCE() to prevent the compiler from doing this to you:
+
+	while (tmp = ACCESS_ONCE(a))
+		do_something_with(tmp);
+
+ (*) The compiler is within its rights to reload a variable, for example,
+     in cases where high register pressure prevents the compiler from
+     keeping all data of interest in registers.  The compiler might
+     therefore optimize the variable 'tmp' out of our previous example:
+
+	while (tmp = a)
+		do_something_with(tmp);
+
+     This could result in the following code, which is perfectly safe in
+     single-threaded code, but can be fatal in concurrent code:
+
+	while (a)
+		do_something_with(a);
+
+     For example, the optimized version of this code could result in
+     passing a zero to do_something_with() in the case where the variable
+     a was modified by some other CPU between the "while" statement and
+     the call to do_something_with().
+
+     Again, use ACCESS_ONCE() to prevent the compiler from doing this:
+
+	while (tmp = ACCESS_ONCE(a))
+		do_something_with(tmp);
 
-The compiler barrier has no direct effect on the CPU, which may then reorder
-things however it wishes.
+     Note that if the compiler runs short of registers, it might save
+     tmp onto the stack.  The overhead of this saving and later restoring
+     is why compilers reload variables.  Doing so is perfectly safe for
+     single-threaded code, so you need to tell the compiler about cases
+     where it is not safe.
+
+ (*) The compiler is within its rights to omit a load entirely if it knows
+     what the value will be.  For example, if the compiler can prove that
+     the value of variable 'a' is always zero, it can optimize this code:
+
+	while (tmp = a)
+		do_something_with(tmp);
+
+     Into this:
+
+	do { } while (0);
+
+     This transformation is a win for single-threaded code because it gets
+     rid of a load and a branch.  The problem is that the compiler will
+     carry out its proof assuming that the current CPU is the only one
+     updating variable 'a'.  If variable 'a' is shared, then the compiler's
+     proof will be erroneous.  Use ACCESS_ONCE() to tell the compiler
+     that it doesn't know as much as it thinks it does:
+
+	while (tmp = ACCESS_ONCE(a))
+		do_something_with(tmp);
+
+     But please note that the compiler is also closely watching what you
+     do with the value after the ACCESS_ONCE().  For example, suppose you
+     do the following and MAX is a preprocessor macro with the value 1:
+
+	while ((tmp = ACCESS_ONCE(a)) % MAX)
+		do_something_with(tmp);
+
+     Then the compiler knows that the result of the "%" operator applied
+     to MAX will always be zero, again allowing the compiler to optimize
+     the code into near-nonexistence.  (It will still load from the
+     variable 'a'.)
+
+ (*) Similarly, the compiler is within its rights to omit a store entirely
+     if it knows that the variable already has the value being stored.
+     Again, the compiler assumes that the current CPU is the only one
+     storing into the variable, which can cause the compiler to do the
+     wrong thing for shared variables.  For example, suppose you have
+     the following:
+
+	a = 0;
+	/* Code that does not store to variable a. */
+	a = 0;
+
+     The compiler sees that the value of variable 'a' is already zero, so
+     it might well omit the second store.  This would come as a fatal
+     surprise if some other CPU might have stored to variable 'a' in the
+     meantime.
+
+     Use ACCESS_ONCE() to prevent the compiler from making this sort of
+     wrong guess:
+
+	ACCESS_ONCE(a) = 0;
+	/* Code that does not store to variable a. */
+	ACCESS_ONCE(a) = 0;
+
+ (*) The compiler is within its rights to reorder memory accesses unless
+     you tell it not to.  For example, consider the following interaction
+     between process-level code and an interrupt handler:
+
+	void process_level(void)
+	{
+		msg = get_message();
+		flag = true;
+	}
+
+	void interrupt_handler(void)
+	{
+		if (flag)
+			process_message(msg);
+	}
+
+     There is nothing to prevent the the compiler from transforming
+     process_level() to the following, in fact, this might well be a
+     win for single-threaded code:
+
+	void process_level(void)
+	{
+		flag = true;
+		msg = get_message();
+	}
+
+     If the interrupt occurs between these two statement, then
+     interrupt_handler() might be passed a garbled msg.  Use ACCESS_ONCE()
+     to prevent this as follows:
+
+	void process_level(void)
+	{
+		ACCESS_ONCE(msg) = get_message();
+		ACCESS_ONCE(flag) = true;
+	}
+
+	void interrupt_handler(void)
+	{
+		if (ACCESS_ONCE(flag))
+			process_message(ACCESS_ONCE(msg));
+	}
+
+     Note that the ACCESS_ONCE() wrappers in interrupt_handler()
+     are needed if this interrupt handler can itself be interrupted
+     by something that also accesses 'flag' and 'msg', for example,
+     a nested interrupt or an NMI.  Otherwise, ACCESS_ONCE() is not
+     needed in interrupt_handler() other than for documentation purposes.
+     (Note also that nested interrupts do not typically occur in modern
+     Linux kernels, in fact, if an interrupt handler returns with
+     interrupts enabled, you will get a WARN_ONCE() splat.)
+
+     You should assume that the compiler can move ACCESS_ONCE() past
+     code not containing ACCESS_ONCE(), barrier(), or similar primitives.
+
+     This effect could also be achieved using barrier(), but ACCESS_ONCE()
+     is more selective:  With ACCESS_ONCE(), the compiler need only forget
+     the contents of the indicated memory locations, while with barrier()
+     the compiler must discard the value of all memory locations that
+     it has currented cached in any machine registers.  Of course,
+     the compiler must also respect the order in which the ACCESS_ONCE()s
+     occur, though the CPU of course need not do so.
+
+ (*) The compiler is within its rights to invent stores to a variable,
+     as in the following example:
+
+	if (a)
+		b = a;
+	else
+		b = 42;
+
+     The compiler might save a branch by optimizing this as follows:
+
+	b = 42;
+	if (a)
+		b = a;
+
+     In single-threaded code, this is not only safe, but also saves
+     a branch.  Unfortunately, in concurrent code, this optimization
+     could cause some other CPU to see a spurious value of 42 -- even
+     if variable 'a' was never zero -- when loading variable 'b'.
+     Use ACCESS_ONCE() to prevent this as follows:
+
+	if (a)
+		ACCESS_ONCE(b) = a;
+	else
+		ACCESS_ONCE(b) = 42;
+
+     The compiler can also invent loads.  These are usually less
+     damaging, but they can result in cache-line bouncing and thus in
+     poor performance and scalability.  Use ACCESS_ONCE() to prevent
+     invented loads.
+
+ (*) For aligned memory locations whose size allows them to be accessed
+     with a single memory-reference instruction, prevents "load tearing"
+     and "store tearing," in which a single large access is replaced by
+     multiple smaller accesses.  For example, given an architecture having
+     16-bit store instructions with 7-bit immediate fields, the compiler
+     might be tempted to use two 16-bit store-immediate instructions to
+     implement the following 32-bit store:
+
+	p = 0x00010002;
+
+     Please note that GCC really does use this sort of optimization,
+     which is not surprising given that it would likely take more
+     than two instructions to build the constant and then store it.
+     This optimization can therefore be a win in single-threaded code.
+     In fact, a recent bug (since fixed) caused GCC to incorrectly use
+     this optimization in a volatile store.  In the absence of such bugs,
+     use of ACCESS_ONCE() prevents store tearing in the following example:
+
+	ACCESS_ONCE(p) = 0x00010002;
+
+     Use of packed structures can also result in load and store tearing,
+     as in this example:
+
+	struct __attribute__((__packed__)) foo {
+		short a;
+		int b;
+		short c;
+	};
+	struct foo foo1, foo2;
+	...
+
+	foo2.a = foo1.a;
+	foo2.b = foo1.b;
+	foo2.c = foo1.c;
+
+     Because there are no ACCESS_ONCE() wrappers and no volatile markings,
+     the compiler would be well within its rights to implement these three
+     assignment statements as a pair of 32-bit loads followed by a pair
+     of 32-bit stores.  This would result in load tearing on 'foo1.b'
+     and store tearing on 'foo2.b'.  ACCESS_ONCE() again prevents tearing
+     in this example:
+
+	foo2.a = foo1.a;
+	ACCESS_ONCE(foo2.b) = ACCESS_ONCE(foo1.b);
+	foo2.c = foo1.c;
+
+All that aside, it is never necessary to use ACCESS_ONCE() on a variable
+that has been marked volatile.  For example, because 'jiffies' is marked
+volatile, it is never necessary to say ACCESS_ONCE(jiffies).  The reason
+for this is that ACCESS_ONCE() is implemented as a volatile cast, which
+has no effect when its argument is already marked volatile.
+
+Please note that these compiler barriers have no direct effect on the CPU,
+which may then reorder things however it wishes.
 
 
 CPU MEMORY BARRIERS
@@ -1189,8 +1639,12 @@ for each construct.  These operations all imply certain barriers:
      Memory operations issued after the LOCK will be completed after the LOCK
      operation has completed.
 
-     Memory operations issued before the LOCK may be completed after the LOCK
-     operation has completed.
+     Memory operations issued before the LOCK may be completed after the
+     LOCK operation has completed.  An smp_mb__before_spinlock(), combined
+     with a following LOCK, orders prior loads against subsequent stores
+     and stores and prior stores against subsequent stores.  Note that
+     this is weaker than smp_mb()!  The smp_mb__before_spinlock()
+     primitive is free on many architectures.
 
  (2) UNLOCK operation implication:
 
@@ -1210,9 +1664,6 @@ for each construct.  These operations all imply certain barriers:
      All LOCK operations issued before an UNLOCK operation will be completed
      before the UNLOCK operation.
 
-     All UNLOCK operations issued before a LOCK operation will be completed
-     before the LOCK operation.
-
  (5) Failed conditional LOCK implication:
 
      Certain variants of the LOCK operation may fail, either due to being
@@ -1220,9 +1671,6 @@ for each construct.  These operations all imply certain barriers:
      signal whilst asleep waiting for the lock to become available.  Failed
      locks do not imply any sort of barrier.
 
-Therefore, from (1), (2) and (4) an UNLOCK followed by an unconditional LOCK is
-equivalent to a full barrier, but a LOCK followed by an UNLOCK is not.
-
 [!] Note: one of the consequences of LOCKs and UNLOCKs being only one-way
     barriers is that the effects of instructions outside of a critical section
     may seep into the inside of the critical section.
@@ -1233,13 +1681,57 @@ LOCK, and an access following the UNLOCK to happen before the UNLOCK, and the
 two accesses can themselves then cross:
 
 	*A = a;
-	LOCK
-	UNLOCK
+	LOCK M
+	UNLOCK M
 	*B = b;
 
 may occur as:
 
-	LOCK, STORE *B, STORE *A, UNLOCK
+	LOCK M, STORE *B, STORE *A, UNLOCK M
+
+This same reordering can of course occur if the LOCK and UNLOCK are
+to the same lock variable, but only from the perspective of another
+CPU not holding that lock.
+
+In short, an UNLOCK followed by a LOCK may -not- be assumed to be a full
+memory barrier because it is possible for a preceding UNLOCK to pass a
+later LOCK from the viewpoint of the CPU, but not from the viewpoint
+of the compiler.  Note that deadlocks cannot be introduced by this
+interchange because if such a deadlock threatened, the UNLOCK would
+simply complete.
+
+If it is necessary for an UNLOCK-LOCK pair to produce a full barrier,
+the LOCK can be followed by an smp_mb__after_unlock_lock() invocation.
+This will produce a full barrier if either (a) the UNLOCK and the LOCK
+are executed by the same CPU or task, or (b) the UNLOCK and LOCK act
+on the same lock variable.  The smp_mb__after_unlock_lock() primitive
+is free on many architectures.  Without smp_mb__after_unlock_lock(),
+the critical sections corresponding to the UNLOCK and the LOCK can cross:
+
+	*A = a;
+	UNLOCK M
+	LOCK N
+	*B = b;
+
+could occur as:
+
+	LOCK N, STORE *B, STORE *A, UNLOCK M
+
+With smp_mb__after_unlock_lock(), they cannot, so that:
+
+	*A = a;
+	UNLOCK M
+	LOCK N
+	smp_mb__after_unlock_lock();
+	*B = b;
+
+will always occur as either of the following:
+
+	STORE *A, UNLOCK, LOCK, STORE *B
+	STORE *A, LOCK, UNLOCK, STORE *B
+
+If the UNLOCK and LOCK were instead both operating on the same lock
+variable, only the first of these two alternatives can occur.
 
 Locks and semaphores may not provide any guarantee of ordering on UP compiled
 systems, and so cannot be counted on in such a situation to actually achieve
@@ -1435,12 +1927,12 @@ three CPUs; then should the following sequence of events occur:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	*A = a;				*E = e;
+	ACCESS_ONCE(*A) = a;		ACCESS_ONCE(*E) = e;
 	LOCK M				LOCK Q
-	*B = b;				*F = f;
-	*C = c;				*G = g;
+	ACCESS_ONCE(*B) = b;		ACCESS_ONCE(*F) = f;
+	ACCESS_ONCE(*C) = c;		ACCESS_ONCE(*G) = g;
 	UNLOCK M			UNLOCK Q
-	*D = d;				*H = h;
+	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*H) = h;
 
 Then there is no guarantee as to what order CPU 3 will see the accesses to *A
 through *H occur in, other than the constraints imposed by the separate locks
@@ -1460,17 +1952,18 @@ However, if the following occurs:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	*A = a;
-	LOCK M		[1]
-	*B = b;
-	*C = c;
-	UNLOCK M	[1]
-	*D = d;				*E = e;
-					LOCK M		[2]
-					*F = f;
-					*G = g;
-					UNLOCK M	[2]
-					*H = h;
+	ACCESS_ONCE(*A) = a;
+	LOCK M		     [1]
+	ACCESS_ONCE(*B) = b;
+	ACCESS_ONCE(*C) = c;
+	UNLOCK M	     [1]
+	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*E) = e;
+					LOCK M		     [2]
+					smp_mb__after_unlock_lock();
+					ACCESS_ONCE(*F) = f;
+					ACCESS_ONCE(*G) = g;
+					UNLOCK M	     [2]
+					ACCESS_ONCE(*H) = h;
 
 CPU 3 might see:
 
@@ -1484,6 +1977,11 @@ But assuming CPU 1 gets the lock first, CPU 3 won't see any of:
 	*F, *G or *H preceding LOCK M [2]
 	*A, *B, *C, *E, *F or *G following UNLOCK M [2]
 
+Note that the smp_mb__after_unlock_lock() is critically important
+here: Without it CPU 3 might see some of the above orderings.
+Without smp_mb__after_unlock_lock(), the accesses are not guaranteed
+to be seen in order unless CPU 3 holds lock M.
+
 
 LOCKS VS I/O ACCESSES
 ---------------------
@@ -1687,21 +2185,23 @@ explicit lock operations, described later).  These include:
 
 	xchg();
 	cmpxchg();
-	atomic_xchg();
-	atomic_cmpxchg();
-	atomic_inc_return();
-	atomic_dec_return();
-	atomic_add_return();
-	atomic_sub_return();
-	atomic_inc_and_test();
-	atomic_dec_and_test();
-	atomic_sub_and_test();
-	atomic_add_negative();
-	atomic_add_unless();	/* when succeeds (returns 1) */
+	atomic_xchg();			atomic_long_xchg();
+	atomic_cmpxchg();		atomic_long_cmpxchg();
+	atomic_inc_return();		atomic_long_inc_return();
+	atomic_dec_return();		atomic_long_dec_return();
+	atomic_add_return();		atomic_long_add_return();
+	atomic_sub_return();		atomic_long_sub_return();
+	atomic_inc_and_test();		atomic_long_inc_and_test();
+	atomic_dec_and_test();		atomic_long_dec_and_test();
+	atomic_sub_and_test();		atomic_long_sub_and_test();
+	atomic_add_negative();		atomic_long_add_negative();
 	test_and_set_bit();
 	test_and_clear_bit();
 	test_and_change_bit();
 
+	/* when succeeds (returns 1) */
+	atomic_add_unless();		atomic_long_add_unless();
+
 These are used for such things as implementing LOCK-class and UNLOCK-class
 operations and adjusting reference counters towards object destruction, and as
 such the implicit memory barrier effects are necessary.
@@ -1887,8 +2387,8 @@ functions:
      space should suffice for PCI.
 
      [*] 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.
+	 cause a malfunction - consider the 16550 Rx/Tx serial registers for
+	 example.
 
      Used with prefetchable I/O memory, an mmiowb() barrier may be required to
      force stores to be ordered.
@@ -1955,19 +2455,19 @@ barriers for the most part act at the interface between the CPU and its cache
 	                          :
 	+--------+    +--------+  :   +--------+    +-----------+
 	|        |    |        |  :   |        |    |           |    +--------+
-	|  CPU   |    | Memory |  :   | CPU    |    |           |    |	      |
-	|  Core  |--->| Access |----->| Cache  |<-->|           |    |	      |
+	|  CPU   |    | Memory |  :   | CPU    |    |           |    |        |
+	|  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
 	|        |    | Queue  |  :   |        |    |           |--->| Memory |
-	|        |    |        |  :   |        |    |           |    |	      |
-	+--------+    +--------+  :   +--------+    |           |    | 	      |
+	|        |    |        |  :   |        |    |           |    |        |
+	+--------+    +--------+  :   +--------+    |           |    |        |
 	                          :                 | Cache     |    +--------+
 	                          :                 | Coherency |
 	                          :                 | Mechanism |    +--------+
 	+--------+    +--------+  :   +--------+    |           |    |	      |
 	|        |    |        |  :   |        |    |           |    |        |
 	|  CPU   |    | Memory |  :   | CPU    |    |           |--->| Device |
-	|  Core  |--->| Access |----->| Cache  |<-->|           |    | 	      |
-	|        |    | Queue  |  :   |        |    |           |    | 	      |
+	|  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
+	|        |    | Queue  |  :   |        |    |           |    |        |
 	|        |    |        |  :   |        |    |           |    +--------+
 	+--------+    +--------+  :   +--------+    +-----------+
 	                          :
@@ -2090,7 +2590,7 @@ CPU's caches by some other cache event:
 	p = &v;		q = p;
 			<D:request p>
 	<B:modify p=&v>	<D:commit p=&v>
-		  	<D:read p>
+			<D:read p>
 			x = *q;
 			<C:read *q>	Reads from v before v updated in cache
 			<C:unbusy>
@@ -2115,7 +2615,7 @@ queue before processing any further requests:
 	p = &v;		q = p;
 			<D:request p>
 	<B:modify p=&v>	<D:commit p=&v>
-		  	<D:read p>
+			<D:read p>
 			smp_read_barrier_depends()
 			<C:unbusy>
 			<C:commit v=2>
@@ -2177,11 +2677,11 @@ A programmer might take it for granted that the CPU will perform memory
 operations in exactly the order specified, so that if the CPU is, for example,
 given the following piece of code to execute:
 
-	a = *A;
-	*B = b;
-	c = *C;
-	d = *D;
-	*E = e;
+	a = ACCESS_ONCE(*A);
+	ACCESS_ONCE(*B) = b;
+	c = ACCESS_ONCE(*C);
+	d = ACCESS_ONCE(*D);
+	ACCESS_ONCE(*E) = e;
 
 they would then expect that the CPU will complete the memory operation for each
 instruction before moving on to the next one, leading to a definite sequence of
@@ -2228,12 +2728,12 @@ However, it is guaranteed that a CPU will be self-consistent: it will see its
 _own_ accesses appear to be correctly ordered, without the need for a memory
 barrier.  For instance with the following code:
 
-	U = *A;
-	*A = V;
-	*A = W;
-	X = *A;
-	*A = Y;
-	Z = *A;
+	U = ACCESS_ONCE(*A);
+	ACCESS_ONCE(*A) = V;
+	ACCESS_ONCE(*A) = W;
+	X = ACCESS_ONCE(*A);
+	ACCESS_ONCE(*A) = Y;
+	Z = ACCESS_ONCE(*A);
 
 and assuming no intervention by an external influence, it can be assumed that
 the final result will appear to be:
@@ -2250,7 +2750,12 @@ accesses:
 
 in that order, but, without intervention, the sequence may have almost any
 combination of elements combined or discarded, provided the program's view of
-the world remains consistent.
+the world remains consistent.  Note that ACCESS_ONCE() is -not- optional
+in the above example, as there are architectures where a given CPU might
+interchange successive loads to the same location.  On such architectures,
+ACCESS_ONCE() does whatever is necessary to prevent this, for example, on
+Itanium the volatile casts used by ACCESS_ONCE() cause GCC to emit the
+special ld.acq and st.rel instructions that prevent such reordering.
 
 The compiler may also combine, discard or defer elements of the sequence before
 the CPU even sees them.
@@ -2264,13 +2769,13 @@ may be reduced to:
 
 	*A = W;
 
-since, without a write barrier, it can be assumed that the effect of the
-storage of V to *A is lost.  Similarly:
+since, without either a write barrier or an ACCESS_ONCE(), it can be
+assumed that the effect of the storage of V to *A is lost.  Similarly:
 
 	*A = Y;
 	Z = *A;
 
-may, without a memory barrier, be reduced to:
+may, without a memory barrier or an ACCESS_ONCE(), be reduced to:
 
 	*A = Y;
 	Z = Y;
diff --git a/Documentation/robust-futex-ABI.txt b/Documentation/robust-futex-ABI.txt
index fd1cd8aae4eb..16eb314f56cc 100644
--- a/Documentation/robust-futex-ABI.txt
+++ b/Documentation/robust-futex-ABI.txt
@@ -146,8 +146,8 @@ On removal:
  1) set the 'list_op_pending' word to the address of the 'lock entry'
     to be removed,
  2) remove the lock entry for this lock from the 'head' list,
- 2) release the futex lock, and
- 2) clear the 'lock_op_pending' word.
+ 3) release the futex lock, and
+ 4) clear the 'lock_op_pending' word.
 
 On exit, the kernel will consider the address stored in
 'list_op_pending' and the address of each 'lock word' found by walking
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 26b7ee491df8..6d486404200e 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -428,11 +428,6 @@ rate for each task.
 numa_balancing_scan_size_mb is how many megabytes worth of pages are
 scanned for a given scan.
 
-numa_balancing_settle_count is how many scan periods must complete before
-the schedule balancer stops pushing the task towards a preferred node. This
-gives the scheduler a chance to place the task on an alternative node if the
-preferred node is overloaded.
-
 numa_balancing_migrate_deferred is how many page migrations get skipped
 unconditionally, after a page migration is skipped because a page is shared
 with other tasks. This reduces page migration overhead, and determines
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index f4f268c2b826..cb81741d3b0b 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -608,6 +608,9 @@ Protocol:       2.12+
 	- If 1, the kernel supports the 64-bit EFI handoff entry point
           given at handover_offset + 0x200.
 
+  Bit 4 (read): XLF_EFI_KEXEC
+	- If 1, the kernel supports kexec EFI boot with EFI runtime support.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f75c9c..c584a51add15 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -28,4 +28,11 @@ reference.
 Current X86-64 implementations only support 40 bits of address space,
 but we support up to 46 bits. This expands into MBZ space in the page tables.
 
+->trampoline_pgd:
+
+We map EFI runtime services in the aforementioned PGD in the virtual
+range of 64Gb (arbitrarily set, can be raised if needed)
+
+0xffffffef00000000 - 0xffffffff00000000
+
 -Andi Kleen, Jul 2004
diff --git a/MAINTAINERS b/MAINTAINERS
index 1d63ab3a8da9..57afee5a1114 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5158,6 +5158,11 @@ F:	drivers/lguest/
 F:	include/linux/lguest*.h
 F:	tools/lguest/
 
+LIBLOCKDEP
+M:	Sasha Levin <sasha.levin@oracle.com>
+S:	Maintained
+F:	tools/lib/lockdep/
+
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
 W:	http://www.ibm.com/linux/ltc/projects/ppc
@@ -7151,6 +7156,12 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/rcu/torture.c
 
+RCUTORTURE TEST FRAMEWORK
+M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+F:	tools/testing/selftests/rcutorture
+
 RDC R-321X SoC
 M:	Florian Fainelli <florian@openwrt.org>
 S:	Maintained
diff --git a/Makefile b/Makefile
index 034c30442a43..b300e89eddd0 100644
--- a/Makefile
+++ b/Makefile
@@ -601,10 +601,24 @@ ifneq ($(CONFIG_FRAME_WARN),0)
 KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
-# Force gcc to behave correct even for buggy distributions
-ifndef CONFIG_CC_STACKPROTECTOR
-KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector)
+# Handle stack protector mode.
+ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
+  stackp-flag := -fstack-protector
+  ifeq ($(call cc-option, $(stackp-flag)),)
+    $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \
+	      -fstack-protector not supported by compiler))
+  endif
+else ifdef CONFIG_CC_STACKPROTECTOR_STRONG
+  stackp-flag := -fstack-protector-strong
+  ifeq ($(call cc-option, $(stackp-flag)),)
+    $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \
+	      -fstack-protector-strong not supported by compiler)
+  endif
+else
+  # Force off for distro compilers that enable stack protector by default.
+  stackp-flag := $(call cc-option, -fno-stack-protector)
 endif
+KBUILD_CFLAGS += $(stackp-flag)
 
 # This warning generated too much noise in a regular build.
 # Use make W=1 to enable this warning (see scripts/Makefile.build)
diff --git a/arch/Kconfig b/arch/Kconfig
index f1cf895c040f..80bbb8ccd0d1 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -336,6 +336,73 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
+config HAVE_CC_STACKPROTECTOR
+	bool
+	help
+	  An arch should select this symbol if:
+	  - its compiler supports the -fstack-protector option
+	  - it has implemented a stack canary (e.g. __stack_chk_guard)
+
+config CC_STACKPROTECTOR
+	def_bool n
+	help
+	  Set when a stack-protector mode is enabled, so that the build
+	  can enable kernel-side support for the GCC feature.
+
+choice
+	prompt "Stack Protector buffer overflow detection"
+	depends on HAVE_CC_STACKPROTECTOR
+	default CC_STACKPROTECTOR_NONE
+	help
+	  This option turns on the "stack-protector" GCC feature. This
+	  feature puts, at the beginning of functions, a canary value on
+	  the stack just before the return address, and validates
+	  the value just before actually returning.  Stack based buffer
+	  overflows (that need to overwrite this return address) now also
+	  overwrite the canary, which gets detected and the attack is then
+	  neutralized via a kernel panic.
+
+config CC_STACKPROTECTOR_NONE
+	bool "None"
+	help
+	  Disable "stack-protector" GCC feature.
+
+config CC_STACKPROTECTOR_REGULAR
+	bool "Regular"
+	select CC_STACKPROTECTOR
+	help
+	  Functions will have the stack-protector canary logic added if they
+	  have an 8-byte or larger character array on the stack.
+
+	  This feature requires gcc version 4.2 or above, or a distribution
+	  gcc with the feature backported ("-fstack-protector").
+
+	  On an x86 "defconfig" build, this feature adds canary checks to
+	  about 3% of all kernel functions, which increases kernel code size
+	  by about 0.3%.
+
+config CC_STACKPROTECTOR_STRONG
+	bool "Strong"
+	select CC_STACKPROTECTOR
+	help
+	  Functions will have the stack-protector canary logic added in any
+	  of the following conditions:
+
+	  - local variable's address used as part of the right hand side of an
+	    assignment or function argument
+	  - local variable is an array (or union containing an array),
+	    regardless of array type or length
+	  - uses register local variables
+
+	  This feature requires gcc version 4.9 or above, or a distribution
+	  gcc with the feature backported ("-fstack-protector-strong").
+
+	  On an x86 "defconfig" build, this feature adds canary checks to
+	  about 20% of all kernel functions, which increases the kernel code
+	  size by about 2%.
+
+endchoice
+
 config HAVE_CONTEXT_TRACKING
 	bool
 	help
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f9d07d330530..6aaf21020d80 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -31,6 +31,7 @@ config ARM
 	select HAVE_BPF_JIT
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
@@ -1888,18 +1889,6 @@ config SECCOMP
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	help
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-	  This feature requires gcc version 4.2 or above.
-
 config SWIOTLB
 	def_bool y
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index b321ce609442..23d5e3946589 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -40,10 +40,6 @@ ifeq ($(CONFIG_FRAME_POINTER),y)
 KBUILD_CFLAGS	+=-fno-omit-frame-pointer -mapcs -mno-sched-prolog
 endif
 
-ifeq ($(CONFIG_CC_STACKPROTECTOR),y)
-KBUILD_CFLAGS	+=-fstack-protector
-endif
-
 ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 AS		+= -EB
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 31bd43b82095..d4f891f56996 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -127,6 +127,18 @@ asmlinkage void __div0(void)
 	error("Attempting division by 0!");
 }
 
+unsigned long __stack_chk_guard;
+
+void __stack_chk_guard_setup(void)
+{
+	__stack_chk_guard = 0x000a0dff;
+}
+
+void __stack_chk_fail(void)
+{
+	error("stack-protector: Kernel stack is corrupted\n");
+}
+
 extern int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x));
 
 
@@ -137,6 +149,8 @@ decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
 {
 	int ret;
 
+	__stack_chk_guard_setup();
+
 	output_data		= (unsigned char *)output_start;
 	free_mem_ptr		= free_mem_ptr_p;
 	free_mem_end_ptr	= free_mem_ptr_end_p;
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index bc3f2efa0d86..789d846a9184 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -99,10 +99,6 @@ int armpmu_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0;
 
-	/* The period may have been changed by PERF_EVENT_IOC_PERIOD */
-	if (unlikely(period != hwc->last_period))
-		left = period - (hwc->last_period - left);
-
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 99db162fdc40..d053ba3a8564 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -48,6 +48,7 @@ config MIPS
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select CLONE_BACKWARDS
 	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_CC_STACKPROTECTOR
 
 menu "Machine selection"
 
@@ -2323,19 +2324,6 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	help
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-
-	  This feature requires gcc version 4.2 or above.
-
 config USE_OF
 	bool
 	select OF
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index de300b993607..efe50787cd89 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -232,10 +232,6 @@ bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y) \
 
 LDFLAGS			+= -m $(ld-emul)
 
-ifdef CONFIG_CC_STACKPROTECTOR
-  KBUILD_CFLAGS += -fstack-protector
-endif
-
 ifdef CONFIG_MIPS
 CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
 	egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
diff --git a/arch/mips/ar7/setup.c b/arch/mips/ar7/setup.c
index 9a357fffcfbe..820b7a313d9b 100644
--- a/arch/mips/ar7/setup.c
+++ b/arch/mips/ar7/setup.c
@@ -92,7 +92,6 @@ void __init plat_mem_setup(void)
 	_machine_restart = ar7_machine_restart;
 	_machine_halt = ar7_machine_halt;
 	pm_power_off = ar7_machine_power_off;
-	panic_timeout = 3;
 
 	io_base = (unsigned long)ioremap(AR7_REGS_BASE, 0x10000);
 	if (!io_base)
diff --git a/arch/mips/emma/markeins/setup.c b/arch/mips/emma/markeins/setup.c
index d71005835c00..9100122e5cef 100644
--- a/arch/mips/emma/markeins/setup.c
+++ b/arch/mips/emma/markeins/setup.c
@@ -111,9 +111,6 @@ void __init plat_mem_setup(void)
 	iomem_resource.start = EMMA2RH_IO_BASE;
 	iomem_resource.end = EMMA2RH_ROM_BASE - 1;
 
-	/* Reboot on panic */
-	panic_timeout = 180;
-
 	markeins_sio_setup();
 }
 
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 6d981bb337ec..54e75c77184b 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -92,7 +92,6 @@ static void __init xlp_init_mem_from_bars(void)
 
 void __init plat_mem_setup(void)
 {
-	panic_timeout	= 5;
 	_machine_restart = (void (*)(char *))nlm_linux_exit;
 	_machine_halt	= nlm_linux_exit;
 	pm_power_off	= nlm_linux_exit;
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
index 214d123b79fa..921be5f77797 100644
--- a/arch/mips/netlogic/xlr/setup.c
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -92,7 +92,6 @@ static void nlm_linux_exit(void)
 
 void __init plat_mem_setup(void)
 {
-	panic_timeout	= 5;
 	_machine_restart = (void (*)(char *))nlm_linux_exit;
 	_machine_halt	= nlm_linux_exit;
 	pm_power_off	= nlm_linux_exit;
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index 41707a245dea..3462c831d0ea 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -134,8 +134,6 @@ void __init plat_mem_setup(void)
 #error invalid SiByte board configuration
 #endif
 
-	panic_timeout = 5;  /* For debug.  */
-
 	board_be_handler = swarm_be_handler;
 
 	if (xicor_probe())
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4d03f1aeebd4..3429f1bbfa2d 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -148,6 +148,10 @@ config EARLY_PRINTK
 	bool
 	default y
 
+config PANIC_TIMEOUT
+	int
+	default 180
+
 config COMPAT
 	bool
 	default y if PPC64
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 703a8412dac2..11ba86e17631 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -26,6 +26,7 @@ extern void reloc_got2(unsigned long);
 void check_for_initrd(void);
 void do_init_bootmem(void);
 void setup_panic(void);
+#define ARCH_PANIC_TIMEOUT 180
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 5f54a744dcc5..f6e78d63fb6a 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -28,6 +28,8 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+
 #define arch_spin_is_locked(x)		((x)->slock != 0)
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index 75c6ecdb8f37..7422a999a39a 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -36,9 +36,8 @@ typedef ppc_opcode_t uprobe_opcode_t;
 
 struct arch_uprobe {
 	union {
-		u8	insn[MAX_UINSN_BYTES];
-		u8	ixol[MAX_UINSN_BYTES];
-		u32	ainsn;
+		u32	insn;
+		u32	ixol;
 	};
 };
 
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index b903dc5cf944..2b0da27eaee4 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -296,9 +296,6 @@ void __init setup_arch(char **cmdline_p)
 	if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE))
 		ucache_bsize = icache_bsize = dcache_bsize;
 
-	/* reboot on panic */
-	panic_timeout = 180;
-
 	if (ppc_md.panic)
 		setup_panic();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2232aff66059..02929896bb66 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -592,9 +592,6 @@ void __init setup_arch(char **cmdline_p)
 	dcache_bsize = ppc64_caches.dline_size;
 	icache_bsize = ppc64_caches.iline_size;
 
-	/* reboot on panic */
-	panic_timeout = 180;
-
 	if (ppc_md.panic)
 		setup_panic();
 
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
index 59f419b935f2..003b20964ea0 100644
--- a/arch/powerpc/kernel/uprobes.c
+++ b/arch/powerpc/kernel/uprobes.c
@@ -186,7 +186,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	 * emulate_step() returns 1 if the insn was successfully emulated.
 	 * For all other cases, we need to single-step in hardware.
 	 */
-	ret = emulate_step(regs, auprobe->ainsn);
+	ret = emulate_step(regs, auprobe->insn);
 	if (ret > 0)
 		return true;
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 49cd16e6b450..8e639d7cbda7 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -470,7 +470,7 @@ static long pseries_little_endian_exceptions(void)
 
 static void __init pSeries_setup_arch(void)
 {
-	panic_timeout = 10;
+	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
 	/* Discover PIC type and setup ppc_md accordingly */
 	pseries_discover_pic();
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 9b0979f4df7a..ce298317a73e 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -66,6 +66,7 @@ config SUPERH32
 	select PERF_EVENTS
 	select ARCH_HIBERNATION_POSSIBLE if MMU
 	select SPARSE_IRQ
+	select HAVE_CC_STACKPROTECTOR
 
 config SUPERH64
 	def_bool ARCH = "sh64"
@@ -695,20 +696,6 @@ config SECCOMP
 
 	  If unsure, say N.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	depends on SUPERH32
-	help
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-
-	  This feature requires gcc version 4.2 or above.
-
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on SYS_SUPPORTS_SMP
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index aed701c7b11b..d4d16e4be07c 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -199,10 +199,6 @@ ifeq ($(CONFIG_DWARF_UNWINDER),y)
   KBUILD_CFLAGS += -fasynchronous-unwind-tables
 endif
 
-ifeq ($(CONFIG_CC_STACKPROTECTOR),y)
-  KBUILD_CFLAGS += -fstack-protector
-endif
-
 libs-$(CONFIG_SUPERH32)		:= arch/sh/lib/	$(libs-y)
 libs-$(CONFIG_SUPERH64)		:= arch/sh/lib64/ $(libs-y)
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ef02cdfeb5da..e8371863208a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -126,6 +126,7 @@ config X86
 	select RTC_LIB
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
+	select HAVE_CC_STACKPROTECTOR
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -1618,22 +1619,6 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection"
-	---help---
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-
-	  This feature requires gcc version 4.2 or above, or a distribution
-	  gcc with the feature backported. Older versions are automatically
-	  detected and for those versions, this configuration option is
-	  ignored. (and a warning is printed during bootup)
-
 source kernel/Kconfig.hz
 
 config KEXEC
@@ -1729,16 +1714,60 @@ config RELOCATABLE
 
 	  Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
 	  it has been loaded at and the compile time physical address
-	  (CONFIG_PHYSICAL_START) is ignored.
+	  (CONFIG_PHYSICAL_START) is used as the minimum location.
 
-# Relocation on x86-32 needs some additional build support
+config RANDOMIZE_BASE
+	bool "Randomize the address of the kernel image"
+	depends on RELOCATABLE
+	depends on !HIBERNATION
+	default n
+	---help---
+	   Randomizes the physical and virtual address at which the
+	   kernel image is decompressed, as a security feature that
+	   deters exploit attempts relying on knowledge of the location
+	   of kernel internals.
+
+	   Entropy is generated using the RDRAND instruction if it is
+	   supported. If RDTSC is supported, it is used as well. If
+	   neither RDRAND nor RDTSC are supported, then randomness is
+	   read from the i8254 timer.
+
+	   The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
+	   and aligned according to PHYSICAL_ALIGN. Since the kernel is
+	   built using 2GiB addressing, and PHYSICAL_ALGIN must be at a
+	   minimum of 2MiB, only 10 bits of entropy is theoretically
+	   possible. At best, due to page table layouts, 64-bit can use
+	   9 bits of entropy and 32-bit uses 8 bits.
+
+config RANDOMIZE_BASE_MAX_OFFSET
+	hex "Maximum ASLR offset allowed"
+	depends on RANDOMIZE_BASE
+	range 0x0 0x20000000 if X86_32
+	default "0x20000000" if X86_32
+	range 0x0 0x40000000 if X86_64
+	default "0x40000000" if X86_64
+	---help---
+	 Determines the maximal offset in bytes that will be applied to the
+	 kernel when Address Space Layout Randomization (ASLR) is active.
+	 Must be less than or equal to the actual physical memory on the
+	 system. This must be a multiple of CONFIG_PHYSICAL_ALIGN.
+
+	 On 32-bit this is limited to 512MiB.
+
+	 On 64-bit this is limited by how the kernel fixmap page table is
+	 positioned, so this cannot be larger that 1GiB currently. Normally
+	 there is a 512MiB to 1.5GiB split between kernel and modules. When
+	 this is raised above the 512MiB default, the modules area will
+	 shrink to compensate, up to the current maximum 1GiB to 1GiB split.
+
+# Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
 	def_bool y
-	depends on X86_32 && RELOCATABLE
+	depends on RANDOMIZE_BASE || (X86_32 && RELOCATABLE)
 
 config PHYSICAL_ALIGN
 	hex "Alignment value to which kernel should be aligned"
-	default "0x1000000"
+	default "0x200000"
 	range 0x2000 0x1000000 if X86_32
 	range 0x200000 0x1000000 if X86_64
 	---help---
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 57d021507120..13b22e0f681d 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -89,13 +89,11 @@ else
         KBUILD_CFLAGS += -maccumulate-outgoing-args
 endif
 
+# Make sure compiler does not have buggy stack-protector support.
 ifdef CONFIG_CC_STACKPROTECTOR
 	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
-        ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
-                stackp-y := -fstack-protector
-                KBUILD_CFLAGS += $(stackp-y)
-        else
-                $(warning stack protector enabled but no compiler support)
+        ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
+                $(warning stack-protector enabled but compiler support broken)
         endif
 endif
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index d9c11956fce0..de7066918005 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -20,7 +20,7 @@ targets		:= vmlinux.bin setup.bin setup.elf bzImage
 targets		+= fdimage fdimage144 fdimage288 image.iso mtools.conf
 subdir-		:= compressed
 
-setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o
+setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o
 setup-y		+= early_serial_console.o edd.o header.o main.o mca.o memory.o
 setup-y		+= pm.o pmjump.o printf.o regs.o string.o tty.o video.o
 setup-y		+= video-mode.o version.o
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index 1dfbf64e52a2..d401b4a262b0 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -1,6 +1,6 @@
 /* -----------------------------------------------------------------------
  *
- *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *   Copyright 2009-2014 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2 or (at your
@@ -13,8 +13,8 @@
  * touching registers they shouldn't be.
  */
 
-	.code16gcc
-	.text
+	.code16
+	.section ".inittext","ax"
 	.globl	intcall
 	.type	intcall, @function
 intcall:
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index ef72baeff484..50f8c5e0f37e 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -26,9 +26,8 @@
 #include <asm/boot.h>
 #include <asm/setup.h>
 #include "bitops.h"
-#include <asm/cpufeature.h>
-#include <asm/processor-flags.h>
 #include "ctype.h"
+#include "cpuflags.h"
 
 /* Useful macros */
 #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@@ -307,14 +306,7 @@ static inline int cmdline_find_option_bool(const char *option)
 	return __cmdline_find_option_bool(cmd_line_ptr, option);
 }
 
-
 /* cpu.c, cpucheck.c */
-struct cpu_features {
-	int level;		/* Family, or 64 for x86-64 */
-	int model;
-	u32 flags[NCAPINTS];
-};
-extern struct cpu_features cpu;
 int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
 int validate_cpu(void);
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index c8a6792e7842..0fcd9133790c 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -28,7 +28,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
 VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
-	$(obj)/piggy.o
+	$(obj)/piggy.o $(obj)/cpuflags.o $(obj)/aslr.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
new file mode 100644
index 000000000000..84be1752dcd8
--- /dev/null
+++ b/arch/x86/boot/compressed/aslr.c
@@ -0,0 +1,317 @@
+#include "misc.h"
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+#include <asm/e820.h>
+
+#include <generated/compile.h>
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <generated/utsrelease.h>
+#include <linux/version.h>
+
+/* Simplified build-specific string for starting entropy. */
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
+#define I8254_PORT_CONTROL	0x43
+#define I8254_PORT_COUNTER0	0x40
+#define I8254_CMD_READBACK	0xC0
+#define I8254_SELECT_COUNTER0	0x02
+#define I8254_STATUS_NOTREADY	0x40
+static inline u16 i8254(void)
+{
+	u16 status, timer;
+
+	do {
+		outb(I8254_PORT_CONTROL,
+		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		status = inb(I8254_PORT_COUNTER0);
+		timer  = inb(I8254_PORT_COUNTER0);
+		timer |= inb(I8254_PORT_COUNTER0) << 8;
+	} while (status & I8254_STATUS_NOTREADY);
+
+	return timer;
+}
+
+static unsigned long rotate_xor(unsigned long hash, const void *area,
+				size_t size)
+{
+	size_t i;
+	unsigned long *ptr = (unsigned long *)area;
+
+	for (i = 0; i < size / sizeof(hash); i++) {
+		/* Rotate by odd number of bits and XOR. */
+		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+		hash ^= ptr[i];
+	}
+
+	return hash;
+}
+
+/* Attempt to create a simple but unpredictable starting entropy. */
+static unsigned long get_random_boot(void)
+{
+	unsigned long hash = 0;
+
+	hash = rotate_xor(hash, build_str, sizeof(build_str));
+	hash = rotate_xor(hash, real_mode, sizeof(*real_mode));
+
+	return hash;
+}
+
+static unsigned long get_random_long(void)
+{
+#ifdef CONFIG_X86_64
+	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+	const unsigned long mix_const = 0x3f39e593UL;
+#endif
+	unsigned long raw, random = get_random_boot();
+	bool use_i8254 = true;
+
+	debug_putstr("KASLR using");
+
+	if (has_cpuflag(X86_FEATURE_RDRAND)) {
+		debug_putstr(" RDRAND");
+		if (rdrand_long(&raw)) {
+			random ^= raw;
+			use_i8254 = false;
+		}
+	}
+
+	if (has_cpuflag(X86_FEATURE_TSC)) {
+		debug_putstr(" RDTSC");
+		rdtscll(raw);
+
+		random ^= raw;
+		use_i8254 = false;
+	}
+
+	if (use_i8254) {
+		debug_putstr(" i8254");
+		random ^= i8254();
+	}
+
+	/* Circular multiply for better bit diffusion */
+	asm("mul %3"
+	    : "=a" (random), "=d" (raw)
+	    : "a" (random), "rm" (mix_const));
+	random += raw;
+
+	debug_putstr("...\n");
+
+	return random;
+}
+
+struct mem_vector {
+	unsigned long start;
+	unsigned long size;
+};
+
+#define MEM_AVOID_MAX 5
+struct mem_vector mem_avoid[MEM_AVOID_MAX];
+
+static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
+{
+	/* Item at least partially before region. */
+	if (item->start < region->start)
+		return false;
+	/* Item at least partially after region. */
+	if (item->start + item->size > region->start + region->size)
+		return false;
+	return true;
+}
+
+static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
+{
+	/* Item one is entirely before item two. */
+	if (one->start + one->size <= two->start)
+		return false;
+	/* Item one is entirely after item two. */
+	if (one->start >= two->start + two->size)
+		return false;
+	return true;
+}
+
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+			   unsigned long output, unsigned long output_size)
+{
+	u64 initrd_start, initrd_size;
+	u64 cmd_line, cmd_line_size;
+	unsigned long unsafe, unsafe_len;
+	char *ptr;
+
+	/*
+	 * Avoid the region that is unsafe to overlap during
+	 * decompression (see calculations at top of misc.c).
+	 */
+	unsafe_len = (output_size >> 12) + 32768 + 18;
+	unsafe = (unsigned long)input + input_size - unsafe_len;
+	mem_avoid[0].start = unsafe;
+	mem_avoid[0].size = unsafe_len;
+
+	/* Avoid initrd. */
+	initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;
+	initrd_start |= real_mode->hdr.ramdisk_image;
+	initrd_size  = (u64)real_mode->ext_ramdisk_size << 32;
+	initrd_size |= real_mode->hdr.ramdisk_size;
+	mem_avoid[1].start = initrd_start;
+	mem_avoid[1].size = initrd_size;
+
+	/* Avoid kernel command line. */
+	cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;
+	cmd_line |= real_mode->hdr.cmd_line_ptr;
+	/* Calculate size of cmd_line. */
+	ptr = (char *)(unsigned long)cmd_line;
+	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+		;
+	mem_avoid[2].start = cmd_line;
+	mem_avoid[2].size = cmd_line_size;
+
+	/* Avoid heap memory. */
+	mem_avoid[3].start = (unsigned long)free_mem_ptr;
+	mem_avoid[3].size = BOOT_HEAP_SIZE;
+
+	/* Avoid stack memory. */
+	mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
+	mem_avoid[4].size = BOOT_STACK_SIZE;
+}
+
+/* Does this memory vector overlap a known avoided area? */
+bool mem_avoid_overlap(struct mem_vector *img)
+{
+	int i;
+
+	for (i = 0; i < MEM_AVOID_MAX; i++) {
+		if (mem_overlaps(img, &mem_avoid[i]))
+			return true;
+	}
+
+	return false;
+}
+
+unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
+unsigned long slot_max = 0;
+
+static void slots_append(unsigned long addr)
+{
+	/* Overflowing the slots list should be impossible. */
+	if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			CONFIG_PHYSICAL_ALIGN)
+		return;
+
+	slots[slot_max++] = addr;
+}
+
+static unsigned long slots_fetch_random(void)
+{
+	/* Handle case of no slots stored. */
+	if (slot_max == 0)
+		return 0;
+
+	return slots[get_random_long() % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	struct mem_vector region, img;
+
+	/* Skip non-RAM entries. */
+	if (entry->type != E820_RAM)
+		return;
+
+	/* Ignore entries entirely above our maximum. */
+	if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		return;
+
+	/* Ignore entries entirely below our minimum. */
+	if (entry->addr + entry->size < minimum)
+		return;
+
+	region.start = entry->addr;
+	region.size = entry->size;
+
+	/* Potentially raise address to minimum location. */
+	if (region.start < minimum)
+		region.start = minimum;
+
+	/* Potentially raise address to meet alignment requirements. */
+	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+
+	/* Did we raise the address above the bounds of this e820 region? */
+	if (region.start > entry->addr + entry->size)
+		return;
+
+	/* Reduce size by any delta from the original address. */
+	region.size -= region.start - entry->addr;
+
+	/* Reduce maximum size to fit end of image within maximum limit. */
+	if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start;
+
+	/* Walk each aligned slot and check for avoided areas. */
+	for (img.start = region.start, img.size = image_size ;
+	     mem_contains(&region, &img) ;
+	     img.start += CONFIG_PHYSICAL_ALIGN) {
+		if (mem_avoid_overlap(&img))
+			continue;
+		slots_append(img.start);
+	}
+}
+
+static unsigned long find_random_addr(unsigned long minimum,
+				      unsigned long size)
+{
+	int i;
+	unsigned long addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < real_mode->e820_entries; i++) {
+		process_e820_entry(&real_mode->e820_map[i], minimum, size);
+	}
+
+	return slots_fetch_random();
+}
+
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	unsigned long choice = (unsigned long)output;
+	unsigned long random;
+
+	if (cmdline_find_option_bool("nokaslr")) {
+		debug_putstr("KASLR disabled...\n");
+		goto out;
+	}
+
+	/* Record the various known unsafe memory ranges. */
+	mem_avoid_init((unsigned long)input, input_size,
+		       (unsigned long)output, output_size);
+
+	/* Walk e820 and find a random address. */
+	random = find_random_addr(choice, output_size);
+	if (!random) {
+		debug_putstr("KASLR could not find suitable E820 region...\n");
+		goto out;
+	}
+
+	/* Always enforce the minimum. */
+	if (random < choice)
+		goto out;
+
+	choice = random;
+out:
+	return (unsigned char *)choice;
+}
+
+#endif /* CONFIG_RANDOMIZE_BASE */
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index bffd73b45b1f..b68e3033e6b9 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,6 +1,6 @@
 #include "misc.h"
 
-#ifdef CONFIG_EARLY_PRINTK
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
 
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)
diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
new file mode 100644
index 000000000000..aa313466118b
--- /dev/null
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -0,0 +1,12 @@
+#ifdef CONFIG_RANDOMIZE_BASE
+
+#include "../cpuflags.c"
+
+bool has_cpuflag(int flag)
+{
+	get_cpuflags();
+
+	return test_bit(flag, cpu.flags);
+}
+
+#endif
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 5d6f6891b188..9116aac232c7 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -117,9 +117,11 @@ preferred_addr:
 	addl    %eax, %ebx
 	notl	%eax
 	andl    %eax, %ebx
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
 #endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
 
 	/* Target address to relocate to for decompression */
 	addl	$z_extract_offset, %ebx
@@ -191,14 +193,14 @@ relocated:
 	leal	boot_heap(%ebx), %eax
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
-	call	decompress_kernel
+	call	decompress_kernel /* returns kernel location in %eax */
 	addl	$24, %esp
 
 /*
  * Jump to the decompressed kernel.
  */
 	xorl	%ebx, %ebx
-	jmp	*%ebp
+	jmp	*%eax
 
 /*
  * Stack and heap for uncompression
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c337422b575d..c5c1ae0997e7 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -94,9 +94,11 @@ ENTRY(startup_32)
 	addl	%eax, %ebx
 	notl	%eax
 	andl	%eax, %ebx
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
 #endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
 
 	/* Target address to relocate to for decompression */
 	addl	$z_extract_offset, %ebx
@@ -269,9 +271,11 @@ preferred_addr:
 	addq	%rax, %rbp
 	notq	%rax
 	andq	%rax, %rbp
-#else
-	movq	$LOAD_PHYSICAL_ADDR, %rbp
+	cmpq	$LOAD_PHYSICAL_ADDR, %rbp
+	jge	1f
 #endif
+	movq	$LOAD_PHYSICAL_ADDR, %rbp
+1:
 
 	/* Target address to relocate to for decompression */
 	leaq	z_extract_offset(%rbp), %rbx
@@ -339,13 +343,13 @@ relocated:
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
 	movq	$z_output_len, %r9	/* decompressed length */
-	call	decompress_kernel
+	call	decompress_kernel	/* returns kernel location in %rax */
 	popq	%rsi
 
 /*
  * Jump to the decompressed kernel.
  */
-	jmp	*%rbp
+	jmp	*%rax
 
 	.code32
 no_longmode:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 434f077d2c4d..196eaf373a06 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -112,14 +112,8 @@ struct boot_params *real_mode;		/* Pointer to real-mode data */
 void *memset(void *s, int c, size_t n);
 void *memcpy(void *dest, const void *src, size_t n);
 
-#ifdef CONFIG_X86_64
-#define memptr long
-#else
-#define memptr unsigned
-#endif
-
-static memptr free_mem_ptr;
-static memptr free_mem_end_ptr;
+memptr free_mem_ptr;
+memptr free_mem_end_ptr;
 
 static char *vidmem;
 static int vidport;
@@ -395,7 +389,7 @@ static void parse_elf(void *output)
 	free(phdrs);
 }
 
-asmlinkage void decompress_kernel(void *rmode, memptr heap,
+asmlinkage void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
@@ -422,6 +416,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	output = choose_kernel_location(input_data, input_len,
+					output, output_len);
+
+	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
 		error("Destination address inappropriately aligned");
 #ifdef CONFIG_X86_64
@@ -441,5 +439,5 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	parse_elf(output);
 	handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
-	return;
+	return output;
 }
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 674019d8e235..24e3e569a13c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,7 +23,15 @@
 #define BOOT_BOOT_H
 #include "../ctype.h"
 
+#ifdef CONFIG_X86_64
+#define memptr long
+#else
+#define memptr unsigned
+#endif
+
 /* misc.c */
+extern memptr free_mem_ptr;
+extern memptr free_mem_end_ptr;
 extern struct boot_params *real_mode;		/* Pointer to real-mode data */
 void __putstr(const char *s);
 #define error_putstr(__x)  __putstr(__x)
@@ -39,23 +47,40 @@ static inline void debug_putstr(const char *s)
 
 #endif
 
-#ifdef CONFIG_EARLY_PRINTK
-
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
 /* cmdline.c */
 int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
+#endif
 
-/* early_serial_console.c */
-extern int early_serial_base;
-void console_init(void);
 
+#if CONFIG_RANDOMIZE_BASE
+/* aslr.c */
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size);
+/* cpuflags.c */
+bool has_cpuflag(int flag);
 #else
+static inline
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	return output;
+}
+#endif
 
+#ifdef CONFIG_EARLY_PRINTK
 /* early_serial_console.c */
+extern int early_serial_base;
+void console_init(void);
+#else
 static const int early_serial_base;
 static inline void console_init(void)
 { }
-
 #endif
 
 #endif
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index 11f272c6f5e9..1eb7d298b47d 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -14,7 +14,7 @@
  * Memory copy routines
  */
 
-	.code16gcc
+	.code16
 	.text
 
 GLOBAL(memcpy)
@@ -30,7 +30,7 @@ GLOBAL(memcpy)
 	rep; movsb
 	popw	%di
 	popw	%si
-	ret
+	retl
 ENDPROC(memcpy)
 
 GLOBAL(memset)
@@ -45,25 +45,25 @@ GLOBAL(memset)
 	andw	$3, %cx
 	rep; stosb
 	popw	%di
-	ret
+	retl
 ENDPROC(memset)
 
 GLOBAL(copy_from_fs)
 	pushw	%ds
 	pushw	%fs
 	popw	%ds
-	call	memcpy
+	calll	memcpy
 	popw	%ds
-	ret
+	retl
 ENDPROC(copy_from_fs)
 
 GLOBAL(copy_to_fs)
 	pushw	%es
 	pushw	%fs
 	popw	%es
-	call	memcpy
+	calll	memcpy
 	popw	%es
-	ret
+	retl
 ENDPROC(copy_to_fs)
 
 #if 0 /* Not currently used, but can be enabled as needed */
@@ -71,17 +71,17 @@ GLOBAL(copy_from_gs)
 	pushw	%ds
 	pushw	%gs
 	popw	%ds
-	call	memcpy
+	calll	memcpy
 	popw	%ds
-	ret
+	retl
 ENDPROC(copy_from_gs)
 
 GLOBAL(copy_to_gs)
 	pushw	%es
 	pushw	%gs
 	popw	%es
-	call	memcpy
+	calll	memcpy
 	popw	%es
-	ret
+	retl
 ENDPROC(copy_to_gs)
 #endif
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 4d3ff037201f..100a9a10076a 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -28,8 +28,6 @@
 #include <asm/required-features.h>
 #include <asm/msr-index.h>
 
-struct cpu_features cpu;
-static u32 cpu_vendor[3];
 static u32 err_flags[NCAPINTS];
 
 static const int req_level = CONFIG_X86_MINIMUM_CPU_FAMILY;
@@ -69,92 +67,8 @@ static int is_transmeta(void)
 	       cpu_vendor[2] == A32('M', 'x', '8', '6');
 }
 
-static int has_fpu(void)
-{
-	u16 fcw = -1, fsw = -1;
-	u32 cr0;
-
-	asm("movl %%cr0,%0" : "=r" (cr0));
-	if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
-		cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
-		asm volatile("movl %0,%%cr0" : : "r" (cr0));
-	}
-
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
-
-	return fsw == 0 && (fcw & 0x103f) == 0x003f;
-}
-
-static int has_eflag(u32 mask)
-{
-	u32 f0, f1;
-
-	asm("pushfl ; "
-	    "pushfl ; "
-	    "popl %0 ; "
-	    "movl %0,%1 ; "
-	    "xorl %2,%1 ; "
-	    "pushl %1 ; "
-	    "popfl ; "
-	    "pushfl ; "
-	    "popl %1 ; "
-	    "popfl"
-	    : "=&r" (f0), "=&r" (f1)
-	    : "ri" (mask));
-
-	return !!((f0^f1) & mask);
-}
-
-static void get_flags(void)
-{
-	u32 max_intel_level, max_amd_level;
-	u32 tfms;
-
-	if (has_fpu())
-		set_bit(X86_FEATURE_FPU, cpu.flags);
-
-	if (has_eflag(X86_EFLAGS_ID)) {
-		asm("cpuid"
-		    : "=a" (max_intel_level),
-		      "=b" (cpu_vendor[0]),
-		      "=d" (cpu_vendor[1]),
-		      "=c" (cpu_vendor[2])
-		    : "a" (0));
-
-		if (max_intel_level >= 0x00000001 &&
-		    max_intel_level <= 0x0000ffff) {
-			asm("cpuid"
-			    : "=a" (tfms),
-			      "=c" (cpu.flags[4]),
-			      "=d" (cpu.flags[0])
-			    : "a" (0x00000001)
-			    : "ebx");
-			cpu.level = (tfms >> 8) & 15;
-			cpu.model = (tfms >> 4) & 15;
-			if (cpu.level >= 6)
-				cpu.model += ((tfms >> 16) & 0xf) << 4;
-		}
-
-		asm("cpuid"
-		    : "=a" (max_amd_level)
-		    : "a" (0x80000000)
-		    : "ebx", "ecx", "edx");
-
-		if (max_amd_level >= 0x80000001 &&
-		    max_amd_level <= 0x8000ffff) {
-			u32 eax = 0x80000001;
-			asm("cpuid"
-			    : "+a" (eax),
-			      "=c" (cpu.flags[6]),
-			      "=d" (cpu.flags[1])
-			    : : "ebx");
-		}
-	}
-}
-
 /* Returns a bitmask of which words we have error bits in */
-static int check_flags(void)
+static int check_cpuflags(void)
 {
 	u32 err;
 	int i;
@@ -187,8 +101,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 	if (has_eflag(X86_EFLAGS_AC))
 		cpu.level = 4;
 
-	get_flags();
-	err = check_flags();
+	get_cpuflags();
+	err = check_cpuflags();
 
 	if (test_bit(X86_FEATURE_LM, cpu.flags))
 		cpu.level = 64;
@@ -207,8 +121,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 		eax &= ~(1 << 15);
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
-		get_flags();	/* Make sure it really did something */
-		err = check_flags();
+		get_cpuflags();	/* Make sure it really did something */
+		err = check_cpuflags();
 	} else if (err == 0x01 &&
 		   !(err_flags[0] & ~(1 << X86_FEATURE_CX8)) &&
 		   is_centaur() && cpu.model >= 6) {
@@ -223,7 +137,7 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
 		set_bit(X86_FEATURE_CX8, cpu.flags);
-		err = check_flags();
+		err = check_cpuflags();
 	} else if (err == 0x01 && is_transmeta()) {
 		/* Transmeta might have masked feature bits in word 0 */
 
@@ -238,7 +152,7 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 		    : : "ecx", "ebx");
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
-		err = check_flags();
+		err = check_cpuflags();
 	}
 
 	if (err_flags_ptr)
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
new file mode 100644
index 000000000000..a9fcb7cfb241
--- /dev/null
+++ b/arch/x86/boot/cpuflags.c
@@ -0,0 +1,104 @@
+#include <linux/types.h>
+#include "bitops.h"
+
+#include <asm/processor-flags.h>
+#include <asm/required-features.h>
+#include <asm/msr-index.h>
+#include "cpuflags.h"
+
+struct cpu_features cpu;
+u32 cpu_vendor[3];
+
+static bool loaded_flags;
+
+static int has_fpu(void)
+{
+	u16 fcw = -1, fsw = -1;
+	unsigned long cr0;
+
+	asm volatile("mov %%cr0,%0" : "=r" (cr0));
+	if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
+		cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
+		asm volatile("mov %0,%%cr0" : : "r" (cr0));
+	}
+
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+		     : "+m" (fsw), "+m" (fcw));
+
+	return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+int has_eflag(unsigned long mask)
+{
+	unsigned long f0, f1;
+
+	asm volatile("pushf	\n\t"
+		     "pushf	\n\t"
+		     "pop %0	\n\t"
+		     "mov %0,%1	\n\t"
+		     "xor %2,%1	\n\t"
+		     "push %1	\n\t"
+		     "popf	\n\t"
+		     "pushf	\n\t"
+		     "pop %1	\n\t"
+		     "popf"
+		     : "=&r" (f0), "=&r" (f1)
+		     : "ri" (mask));
+
+	return !!((f0^f1) & mask);
+}
+
+/* Handle x86_32 PIC using ebx. */
+#if defined(__i386__) && defined(__PIC__)
+# define EBX_REG "=r"
+#else
+# define EBX_REG "=b"
+#endif
+
+static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
+{
+	asm volatile(".ifnc %%ebx,%3 ; movl  %%ebx,%3 ; .endif	\n\t"
+		     "cpuid					\n\t"
+		     ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif	\n\t"
+		    : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b)
+		    : "a" (id)
+	);
+}
+
+void get_cpuflags(void)
+{
+	u32 max_intel_level, max_amd_level;
+	u32 tfms;
+	u32 ignored;
+
+	if (loaded_flags)
+		return;
+	loaded_flags = true;
+
+	if (has_fpu())
+		set_bit(X86_FEATURE_FPU, cpu.flags);
+
+	if (has_eflag(X86_EFLAGS_ID)) {
+		cpuid(0x0, &max_intel_level, &cpu_vendor[0], &cpu_vendor[2],
+		      &cpu_vendor[1]);
+
+		if (max_intel_level >= 0x00000001 &&
+		    max_intel_level <= 0x0000ffff) {
+			cpuid(0x1, &tfms, &ignored, &cpu.flags[4],
+			      &cpu.flags[0]);
+			cpu.level = (tfms >> 8) & 15;
+			cpu.model = (tfms >> 4) & 15;
+			if (cpu.level >= 6)
+				cpu.model += ((tfms >> 16) & 0xf) << 4;
+		}
+
+		cpuid(0x80000000, &max_amd_level, &ignored, &ignored,
+		      &ignored);
+
+		if (max_amd_level >= 0x80000001 &&
+		    max_amd_level <= 0x8000ffff) {
+			cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6],
+			      &cpu.flags[1]);
+		}
+	}
+}
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
new file mode 100644
index 000000000000..ea97697e51e4
--- /dev/null
+++ b/arch/x86/boot/cpuflags.h
@@ -0,0 +1,19 @@
+#ifndef BOOT_CPUFLAGS_H
+#define BOOT_CPUFLAGS_H
+
+#include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
+
+struct cpu_features {
+	int level;		/* Family, or 64 for x86-64 */
+	int model;
+	u32 flags[NCAPINTS];
+};
+
+extern struct cpu_features cpu;
+extern u32 cpu_vendor[3];
+
+int has_eflag(unsigned long mask);
+void get_cpuflags(void);
+
+#endif
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 9ec06a1f6d61..ec3b8ba68096 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -391,7 +391,14 @@ xloadflags:
 #else
 # define XLF23 0
 #endif
-			.word XLF0 | XLF1 | XLF23
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC)
+# define XLF4 XLF_EFI_KEXEC
+#else
+# define XLF4 0
+#endif
+
+			.word XLF0 | XLF1 | XLF23 | XLF4
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
                                                 #added with boot protocol
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 0d9ec770f2f8..e6a92455740e 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -39,6 +39,20 @@
 
 #ifdef CONFIG_ARCH_RANDOM
 
+/* Instead of arch_get_random_long() when alternatives haven't run. */
+static inline int rdrand_long(unsigned long *v)
+{
+	int ok;
+	asm volatile("1: " RDRAND_LONG "\n\t"
+		     "jc 2f\n\t"
+		     "decl %0\n\t"
+		     "jnz 1b\n\t"
+		     "2:"
+		     : "=r" (ok), "=a" (*v)
+		     : "0" (RDRAND_RETRY_LOOPS));
+	return ok;
+}
+
 #define GET_RANDOM(name, type, rdrand, nop)			\
 static inline int name(type *v)					\
 {								\
@@ -68,6 +82,13 @@ GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
 
 #endif /* CONFIG_X86_64 */
 
+#else
+
+static inline int rdrand_long(unsigned long *v)
+{
+	return 0;
+}
+
 #endif  /* CONFIG_ARCH_RANDOM */
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 89270b4318db..e099f9502ace 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -216,6 +216,7 @@
 #define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 #define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_MPX		(9*32+14) /* Memory Protection Extension */
 #define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	(9*32+20) /* Supervisor Mode Access Prevention */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 65c6e6e3a552..3b978c472d08 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,6 +1,24 @@
 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
+/*
+ * We map the EFI regions needed for runtime services non-contiguously,
+ * with preserved alignment on virtual addresses starting from -4G down
+ * for a total max space of 64G. This way, we provide for stable runtime
+ * services addresses across kernels so that a kexec'd kernel can still
+ * use them.
+ *
+ * This is the main reason why we're doing stable VA mappings for RT
+ * services.
+ *
+ * This flag is used in conjuction with a chicken bit called
+ * "efi=old_map" which can be used as a fallback to the old runtime
+ * services mapping method in case there's some b0rkage with a
+ * particular EFI implementation (haha, it is hard to hold up the
+ * sarcasm here...).
+ */
+#define EFI_OLD_MEMMAP		EFI_ARCH_1
+
 #ifdef CONFIG_X86_32
 
 #define EFI_LOADER_SIGNATURE	"EL32"
@@ -69,24 +87,31 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3),		\
 		  (u64)(a4), (u64)(a5), (u64)(a6))
 
+#define _efi_call_virtX(x, f, ...)					\
+({									\
+	efi_status_t __s;						\
+									\
+	efi_sync_low_kernel_mappings();					\
+	preempt_disable();						\
+	__s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+	preempt_enable();						\
+	__s;								\
+})
+
 #define efi_call_virt0(f)				\
-	efi_call0((efi.systab->runtime->f))
-#define efi_call_virt1(f, a1)					\
-	efi_call1((efi.systab->runtime->f), (u64)(a1))
-#define efi_call_virt2(f, a1, a2)					\
-	efi_call2((efi.systab->runtime->f), (u64)(a1), (u64)(a2))
-#define efi_call_virt3(f, a1, a2, a3)					\
-	efi_call3((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3))
-#define efi_call_virt4(f, a1, a2, a3, a4)				\
-	efi_call4((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4))
-#define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
-	efi_call5((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5))
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_call6((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+	_efi_call_virtX(0, f)
+#define efi_call_virt1(f, a1)				\
+	_efi_call_virtX(1, f, (u64)(a1))
+#define efi_call_virt2(f, a1, a2)			\
+	_efi_call_virtX(2, f, (u64)(a1), (u64)(a2))
+#define efi_call_virt3(f, a1, a2, a3)			\
+	_efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3))
+#define efi_call_virt4(f, a1, a2, a3, a4)		\
+	_efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4))
+#define efi_call_virt5(f, a1, a2, a3, a4, a5)		\
+	_efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5))
+#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
+	_efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
 extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 				 u32 type, u64 attribute);
@@ -95,12 +120,28 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 
 extern int add_efi_memmap;
 extern unsigned long x86_efi_facility;
+extern struct efi_scratch efi_scratch;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
+extern void __init efi_map_region(efi_memory_desc_t *md);
+extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
+extern void efi_sync_low_kernel_mappings(void);
+extern void efi_setup_page_tables(void);
+extern void __init old_map_region(efi_memory_desc_t *md);
+
+struct efi_setup_data {
+	u64 fw_vendor;
+	u64 runtime;
+	u64 tables;
+	u64 smbios;
+	u64 reserved[8];
+};
+
+extern u64 efi_setup;
 
 #ifdef CONFIG_EFI
 
@@ -110,7 +151,7 @@ static inline bool efi_is_native(void)
 }
 
 extern struct console early_efi_console;
-
+extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
@@ -122,6 +163,7 @@ extern struct console early_efi_console;
 #define efi_call4(_f, _a1, _a2, _a3, _a4)		(-ENOSYS)
 #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
 #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
+static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
 #endif /* CONFIG_EFI */
 
 #endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index be27ba1e947a..b4c1f5453436 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -110,26 +110,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 						u32 oldval, u32 newval)
 {
-	int ret = 0;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
-	asm volatile("\t" ASM_STAC "\n"
-		     "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
-		     "2:\t" ASM_CLAC "\n"
-		     "\t.section .fixup, \"ax\"\n"
-		     "3:\tmov     %3, %0\n"
-		     "\tjmp     2b\n"
-		     "\t.previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : "+r" (ret), "=a" (oldval), "+m" (*uaddr)
-		     : "i" (-EFAULT), "r" (newval), "1" (oldval)
-		     : "memory"
-	);
-
-	*uval = oldval;
-	return ret;
+	return user_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval);
 }
 
 #endif
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 0ea10f27d613..cb6cfcd034cf 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -25,6 +25,7 @@ extern void irq_ctx_init(int cpu);
 
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
+extern int check_irq_vectors_for_cpu_disable(void);
 extern void fixup_irqs(void);
 extern void irq_force_complete_move(int);
 #endif
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 2f366d0ac6b4..19b71c439256 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_MWAIT_H
 #define _ASM_X86_MWAIT_H
 
+#include <linux/sched.h>
+
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
 #define MWAIT_SUBSTATE_SIZE		4
@@ -13,4 +15,45 @@
 
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
 
+static inline void __monitor(const void *eax, unsigned long ecx,
+			     unsigned long edx)
+{
+	/* "monitor %eax, %ecx, %edx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xc8;"
+		     :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+	/* "mwait %eax, %ecx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xc9;"
+		     :: "a" (eax), "c" (ecx));
+}
+
+/*
+ * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
+ * which can obviate IPI to trigger checking of need_resched.
+ * We execute MONITOR against need_resched and enter optimized wait state
+ * through MWAIT. Whenever someone changes need_resched, we would be woken
+ * up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
+ */
+static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+{
+	if (!current_set_polling_and_test()) {
+		if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) {
+			mb();
+			clflush((void *)&current_thread_info()->flags);
+			mb();
+		}
+
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		if (!need_resched())
+			__mwait(eax, ecx);
+	}
+	__current_clr_polling();
+}
+
 #endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index c87892442e53..775873d3be55 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -71,6 +71,7 @@ extern bool __virt_addr_valid(unsigned long kaddr);
 #include <asm-generic/getorder.h>
 
 #define __HAVE_ARCH_GATE_AREA 1
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 
 #endif	/* __KERNEL__ */
 #endif /* _ASM_X86_PAGE_H */
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index 4d550d04b609..904f528cc8e8 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -5,10 +5,6 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_HUGETLB_PAGE
-#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-#endif
-
 #define __phys_addr_nodebug(x)	((x) - PAGE_OFFSET)
 #ifdef CONFIG_DEBUG_VIRTUAL
 extern unsigned long __phys_addr(unsigned long);
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 43dcd804ebd5..8de6d9cf3b95 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -39,9 +39,18 @@
 #define __VIRTUAL_MASK_SHIFT	47
 
 /*
- * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
- * arch/x86/kernel/head_64.S), and it is mapped here:
+ * Kernel image size is limited to 1GiB due to the fixmap living in the
+ * next 1GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). Use
+ * 512MiB by default, leaving 1.5GiB for modules once the page tables
+ * are fully set up. If kernel ASLR is configured, it can extend the
+ * kernel page table mapping, reducing the size of the modules area.
  */
-#define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
+#define KERNEL_IMAGE_SIZE_DEFAULT      (512 * 1024 * 1024)
+#if defined(CONFIG_RANDOMIZE_BASE) && \
+	CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE_DEFAULT
+#define KERNEL_IMAGE_SIZE   CONFIG_RANDOMIZE_BASE_MAX_OFFSET
+#else
+#define KERNEL_IMAGE_SIZE      KERNEL_IMAGE_SIZE_DEFAULT
+#endif
 
 #endif /* _ASM_X86_PAGE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 3bf2dd0cf61f..0d193e234647 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -55,6 +55,13 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+/* Bit manipulation helper on pte/pgoff entry */
+static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshift,
+				      unsigned long mask, unsigned int leftshift)
+{
+	return ((value >> rightshift) & mask) << leftshift;
+}
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
 
 /*
@@ -71,31 +78,34 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 #define PTE_FILE_BITS3		(PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
 
-#define pte_to_pgoff(pte)						\
-	((((pte).pte_low >> (PTE_FILE_SHIFT1))				\
-	  & ((1U << PTE_FILE_BITS1) - 1)))				\
-	+ ((((pte).pte_low >> (PTE_FILE_SHIFT2))			\
-	    & ((1U << PTE_FILE_BITS2) - 1))				\
-	   << (PTE_FILE_BITS1))						\
-	+ ((((pte).pte_low >> (PTE_FILE_SHIFT3))			\
-	    & ((1U << PTE_FILE_BITS3) - 1))				\
-	   << (PTE_FILE_BITS1 + PTE_FILE_BITS2))			\
-	+ ((((pte).pte_low >> (PTE_FILE_SHIFT4)))			\
-	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
-
-#define pgoff_to_pte(off)						\
-	((pte_t) { .pte_low =						\
-	 ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
-	 + ((((off) >> PTE_FILE_BITS1)					\
-	     & ((1U << PTE_FILE_BITS2) - 1))				\
-	    << PTE_FILE_SHIFT2)						\
-	 + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
-	     & ((1U << PTE_FILE_BITS3) - 1))				\
-	    << PTE_FILE_SHIFT3)						\
-	 + ((((off) >>							\
-	      (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)))	\
-	    << PTE_FILE_SHIFT4)						\
-	 + _PAGE_FILE })
+#define PTE_FILE_MASK1		((1U << PTE_FILE_BITS1) - 1)
+#define PTE_FILE_MASK2		((1U << PTE_FILE_BITS2) - 1)
+#define PTE_FILE_MASK3		((1U << PTE_FILE_BITS3) - 1)
+
+#define PTE_FILE_LSHIFT2	(PTE_FILE_BITS1)
+#define PTE_FILE_LSHIFT3	(PTE_FILE_BITS1 + PTE_FILE_BITS2)
+#define PTE_FILE_LSHIFT4	(PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)
+
+static __always_inline pgoff_t pte_to_pgoff(pte_t pte)
+{
+	return (pgoff_t)
+		(pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1,  0)		    +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2,  PTE_FILE_LSHIFT2) +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3,  PTE_FILE_LSHIFT3) +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT4,           -1UL,  PTE_FILE_LSHIFT4));
+}
+
+static __always_inline pte_t pgoff_to_pte(pgoff_t off)
+{
+	return (pte_t){
+		.pte_low =
+			pte_bitop(off,                0, PTE_FILE_MASK1,  PTE_FILE_SHIFT1) +
+			pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2,  PTE_FILE_SHIFT2) +
+			pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3,  PTE_FILE_SHIFT3) +
+			pte_bitop(off, PTE_FILE_LSHIFT4,           -1UL,  PTE_FILE_SHIFT4) +
+			_PAGE_FILE,
+	};
+}
 
 #else /* CONFIG_MEM_SOFT_DIRTY */
 
@@ -115,22 +125,30 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
 #define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 
-#define pte_to_pgoff(pte)						\
-	((((pte).pte_low >> PTE_FILE_SHIFT1)				\
-	  & ((1U << PTE_FILE_BITS1) - 1))				\
-	 + ((((pte).pte_low >> PTE_FILE_SHIFT2)				\
-	     & ((1U << PTE_FILE_BITS2) - 1)) << PTE_FILE_BITS1)		\
-	 + (((pte).pte_low >> PTE_FILE_SHIFT3)				\
-	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2)))
-
-#define pgoff_to_pte(off)						\
-	((pte_t) { .pte_low =						\
-	 (((off) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
-	 + ((((off) >> PTE_FILE_BITS1) & ((1U << PTE_FILE_BITS2) - 1))	\
-	    << PTE_FILE_SHIFT2)						\
-	 + (((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
-	    << PTE_FILE_SHIFT3)						\
-	 + _PAGE_FILE })
+#define PTE_FILE_MASK1		((1U << PTE_FILE_BITS1) - 1)
+#define PTE_FILE_MASK2		((1U << PTE_FILE_BITS2) - 1)
+
+#define PTE_FILE_LSHIFT2	(PTE_FILE_BITS1)
+#define PTE_FILE_LSHIFT3	(PTE_FILE_BITS1 + PTE_FILE_BITS2)
+
+static __always_inline pgoff_t pte_to_pgoff(pte_t pte)
+{
+	return (pgoff_t)
+		(pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1,  0)		    +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2,  PTE_FILE_LSHIFT2) +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT3,           -1UL,  PTE_FILE_LSHIFT3));
+}
+
+static __always_inline pte_t pgoff_to_pte(pgoff_t off)
+{
+	return (pte_t){
+		.pte_low =
+			pte_bitop(off,                0, PTE_FILE_MASK1,  PTE_FILE_SHIFT1) +
+			pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2,  PTE_FILE_SHIFT2) +
+			pte_bitop(off, PTE_FILE_LSHIFT3,           -1UL,  PTE_FILE_SHIFT3) +
+			_PAGE_FILE,
+	};
+}
 
 #endif /* CONFIG_MEM_SOFT_DIRTY */
 
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d883440cb9a..c883bf726398 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -58,7 +58,7 @@ typedef struct { pteval_t pte; } pte_t;
 #define VMALLOC_START    _AC(0xffffc90000000000, UL)
 #define VMALLOC_END      _AC(0xffffe8ffffffffff, UL)
 #define VMEMMAP_START	 _AC(0xffffea0000000000, UL)
-#define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
+#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 0ecac257fb26..a83aa44bb1fb 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -382,7 +382,8 @@ static inline void update_page_count(int level, unsigned long pages) { }
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
-
+extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+				   unsigned numpages, unsigned long page_flags);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7b034a4057f9..a9e1108c0691 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -72,6 +72,7 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO];
 extern u16 __read_mostly tlb_lld_4k[NR_INFO];
 extern u16 __read_mostly tlb_lld_2m[NR_INFO];
 extern u16 __read_mostly tlb_lld_4m[NR_INFO];
+extern u16 __read_mostly tlb_lld_1g[NR_INFO];
 extern s8  __read_mostly tlb_flushall_shift;
 
 /*
@@ -370,6 +371,26 @@ struct ymmh_struct {
 	u32 ymmh_space[64];
 };
 
+struct lwp_struct {
+	u64 lwpcb_addr;
+	u32 flags;
+	u32 buf_head_offset;
+	u64 buf_base;
+	u32 buf_size;
+	u32 filters;
+	u64 saved_event_record[4];
+	u32 event_counter[16];
+};
+
+struct bndregs_struct {
+	u64 bndregs[8];
+} __packed;
+
+struct bndcsr_struct {
+	u64 cfg_reg_u;
+	u64 status_reg;
+} __packed;
+
 struct xsave_hdr_struct {
 	u64 xstate_bv;
 	u64 reserved1[2];
@@ -380,6 +401,9 @@ struct xsave_struct {
 	struct i387_fxsave_struct i387;
 	struct xsave_hdr_struct xsave_hdr;
 	struct ymmh_struct ymmh;
+	struct lwp_struct lwp;
+	struct bndregs_struct bndregs;
+	struct bndcsr_struct bndcsr;
 	/* new processor state extensions will go here */
 } __attribute__ ((packed, aligned (64)));
 
@@ -700,29 +724,6 @@ static inline void sync_core(void)
 #endif
 }
 
-static inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
-{
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
-}
-
-static inline void __mwait(unsigned long eax, unsigned long ecx)
-{
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
-}
-
-static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
-{
-	trace_hardirqs_on();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
-}
-
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 extern void init_amd_e400_c1e_mask(void);
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8ec57c07b125..0d592e0a5b84 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -40,22 +40,30 @@
 /*
  * Test whether a block of memory is a valid user space address.
  * Returns 0 if the range is valid, nonzero otherwise.
- *
- * This is equivalent to the following test:
- * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
- *
- * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
+static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit)
+{
+	/*
+	 * If we have used "sizeof()" for the size,
+	 * we know it won't overflow the limit (but
+	 * it might overflow the 'addr', so it's
+	 * important to subtract the size from the
+	 * limit, not add it to the address).
+	 */
+	if (__builtin_constant_p(size))
+		return addr > limit - size;
+
+	/* Arbitrary sizes? Be careful about overflow */
+	addr += size;
+	if (addr < size)
+		return true;
+	return addr > limit;
+}
 
 #define __range_not_ok(addr, size, limit)				\
 ({									\
-	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
-	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
-	    : "=&r" (flag), "=r" (roksum)				\
-	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (limit));						\
-	flag;								\
+	__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
 })
 
 /**
@@ -78,7 +86,7 @@
  * this function, memory access functions may still return -EFAULT.
  */
 #define access_ok(type, addr, size) \
-	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
+	likely(!__range_not_ok(addr, size, user_addr_max()))
 
 /*
  * The exception table consists of pairs of addresses relative to the
@@ -525,6 +533,98 @@ extern __must_check long strnlen_user(const char __user *str, long n);
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 
+extern void __cmpxchg_wrong_size(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+#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);				\
+	switch (size) {							\
+	case 1:								\
+	{								\
+		asm volatile("\t" ASM_STAC "\n"				\
+			"1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n"		\
+			"2:\t" ASM_CLAC "\n"				\
+			"\t.section .fixup, \"ax\"\n"			\
+			"3:\tmov     %3, %0\n"				\
+			"\tjmp     2b\n"				\
+			"\t.previous\n"					\
+			_ASM_EXTABLE(1b, 3b)				\
+			: "+r" (__ret), "=a" (__old), "+m" (*(ptr))	\
+			: "i" (-EFAULT), "q" (__new), "1" (__old)	\
+			: "memory"					\
+		);							\
+		break;							\
+	}								\
+	case 2:								\
+	{								\
+		asm volatile("\t" ASM_STAC "\n"				\
+			"1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n"		\
+			"2:\t" ASM_CLAC "\n"				\
+			"\t.section .fixup, \"ax\"\n"			\
+			"3:\tmov     %3, %0\n"				\
+			"\tjmp     2b\n"				\
+			"\t.previous\n"					\
+			_ASM_EXTABLE(1b, 3b)				\
+			: "+r" (__ret), "=a" (__old), "+m" (*(ptr))	\
+			: "i" (-EFAULT), "r" (__new), "1" (__old)	\
+			: "memory"					\
+		);							\
+		break;							\
+	}								\
+	case 4:								\
+	{								\
+		asm volatile("\t" ASM_STAC "\n"				\
+			"1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"		\
+			"2:\t" ASM_CLAC "\n"				\
+			"\t.section .fixup, \"ax\"\n"			\
+			"3:\tmov     %3, %0\n"				\
+			"\tjmp     2b\n"				\
+			"\t.previous\n"					\
+			_ASM_EXTABLE(1b, 3b)				\
+			: "+r" (__ret), "=a" (__old), "+m" (*(ptr))	\
+			: "i" (-EFAULT), "r" (__new), "1" (__old)	\
+			: "memory"					\
+		);							\
+		break;							\
+	}								\
+	case 8:								\
+	{								\
+		if (!IS_ENABLED(CONFIG_X86_64))				\
+			__cmpxchg_wrong_size();				\
+									\
+		asm volatile("\t" ASM_STAC "\n"				\
+			"1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n"		\
+			"2:\t" ASM_CLAC "\n"				\
+			"\t.section .fixup, \"ax\"\n"			\
+			"3:\tmov     %3, %0\n"				\
+			"\tjmp     2b\n"				\
+			"\t.previous\n"					\
+			_ASM_EXTABLE(1b, 3b)				\
+			: "+r" (__ret), "=a" (__old), "+m" (*(ptr))	\
+			: "i" (-EFAULT), "r" (__new), "1" (__old)	\
+			: "memory"					\
+		);							\
+		break;							\
+	}								\
+	default:							\
+		__cmpxchg_wrong_size();					\
+	}								\
+	*__uval = __old;						\
+	__ret;								\
+})
+
+#define user_atomic_cmpxchg_inatomic(uval, ptr, old, new)		\
+({									\
+	access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr))) ?		\
+		__user_atomic_cmpxchg_inatomic((uval), (ptr),		\
+				(old), (new), sizeof(*(ptr))) :		\
+		-EFAULT;						\
+})
+
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 190413d0de57..12a26b979bf1 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -204,13 +204,13 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 static __must_check __always_inline int
 __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
 {
-	return __copy_from_user_nocheck(dst, (__force const void *)src, size);
+	return __copy_from_user_nocheck(dst, src, size);
 }
 
 static __must_check __always_inline int
 __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
 {
-	return __copy_to_user_nocheck((__force void *)dst, src, size);
+	return __copy_to_user_nocheck(dst, src, size);
 }
 
 extern long __copy_user_nocache(void *dst, const void __user *src,
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 0415cdabb5a6..554738963b28 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -9,6 +9,8 @@
 #define XSTATE_FP	0x1
 #define XSTATE_SSE	0x2
 #define XSTATE_YMM	0x4
+#define XSTATE_BNDREGS	0x8
+#define XSTATE_BNDCSR	0x10
 
 #define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
 
@@ -20,10 +22,14 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
-/*
- * These are the features that the OS can handle currently.
- */
-#define XCNTXT_MASK	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+/* Supported features which support lazy state saving */
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+
+/* Supported features which require eager state saving */
+#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
+
+/* All currently supported features */
+#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
 
 #ifdef CONFIG_X86_64
 #define REX_PREFIX	"0x48, "
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9c3733c5f8f7..225b0988043a 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
+#define SETUP_EFI			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
@@ -23,6 +24,7 @@
 #define XLF_CAN_BE_LOADED_ABOVE_4G	(1<<1)
 #define XLF_EFI_HANDOVER_32		(1<<2)
 #define XLF_EFI_HANDOVER_64		(1<<3)
+#define XLF_EFI_KEXEC			(1<<4)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/uapi/asm/stat.h b/arch/x86/include/uapi/asm/stat.h
index 7b3ddc348585..bc03eb5d6360 100644
--- a/arch/x86/include/uapi/asm/stat.h
+++ b/arch/x86/include/uapi/asm/stat.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_STAT_H
 #define _ASM_X86_STAT_H
 
+#include <asm/posix_types.h>
+
 #define STAT_HAVE_NSEC 1
 
 #ifdef __i386__
@@ -78,26 +80,26 @@ struct stat64 {
 #else /* __i386__ */
 
 struct stat {
-	unsigned long	st_dev;
-	unsigned long	st_ino;
-	unsigned long	st_nlink;
-
-	unsigned int	st_mode;
-	unsigned int	st_uid;
-	unsigned int	st_gid;
-	unsigned int	__pad0;
-	unsigned long	st_rdev;
-	long		st_size;
-	long		st_blksize;
-	long		st_blocks;	/* Number 512-byte blocks allocated. */
-
-	unsigned long	st_atime;
-	unsigned long	st_atime_nsec;
-	unsigned long	st_mtime;
-	unsigned long	st_mtime_nsec;
-	unsigned long	st_ctime;
-	unsigned long   st_ctime_nsec;
-	long		__unused[3];
+	__kernel_ulong_t	st_dev;
+	__kernel_ulong_t	st_ino;
+	__kernel_ulong_t	st_nlink;
+
+	unsigned int		st_mode;
+	unsigned int		st_uid;
+	unsigned int		st_gid;
+	unsigned int		__pad0;
+	__kernel_ulong_t	st_rdev;
+	__kernel_long_t		st_size;
+	__kernel_long_t		st_blksize;
+	__kernel_long_t		st_blocks;	/* Number 512-byte blocks allocated. */
+
+	__kernel_ulong_t	st_atime;
+	__kernel_ulong_t	st_atime_nsec;
+	__kernel_ulong_t	st_mtime;
+	__kernel_ulong_t	st_mtime_nsec;
+	__kernel_ulong_t	st_ctime;
+	__kernel_ulong_t	st_ctime_nsec;
+	__kernel_long_t		__unused[3];
 };
 
 /* We don't need to memset the whole thing just to initialize the padding */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e2cd79..510cca5c5390 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index d2b7f27781bc..e69182fd01cf 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -150,29 +150,6 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
-			clflush((void *)&current_thread_info()->flags);
-
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(ax, cx);
-	}
-}
-
 void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 47b56a7e99cb..6359506a19ee 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
 endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_rapl.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6abc172b8258..24b6fd10625a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -472,6 +472,7 @@ u16 __read_mostly tlb_lli_4m[NR_INFO];
 u16 __read_mostly tlb_lld_4k[NR_INFO];
 u16 __read_mostly tlb_lld_2m[NR_INFO];
 u16 __read_mostly tlb_lld_4m[NR_INFO];
+u16 __read_mostly tlb_lld_1g[NR_INFO];
 
 /*
  * tlb_flushall_shift shows the balance point in replacing cr3 write
@@ -486,13 +487,13 @@ void cpu_detect_tlb(struct cpuinfo_x86 *c)
 	if (this_cpu->c_detect_tlb)
 		this_cpu->c_detect_tlb(c);
 
-	printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
-		"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n"	     \
+	printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n"
+		"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n"
 		"tlb_flushall_shift: %d\n",
 		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
 		tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
 		tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
-		tlb_flushall_shift);
+		tlb_lld_1g[ENTRIES], tlb_flushall_shift);
 }
 
 void detect_ht(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index ea04b342c026..5eb7ea5fae15 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -506,6 +506,7 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 #define TLB_DATA0_2M_4M	0x23
 
 #define STLB_4K		0x41
+#define STLB_4K_2M	0x42
 
 static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
@@ -526,13 +527,20 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
+	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
+	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
 	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
 	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
 	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
 	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
 	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
+	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
+	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
 	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
 	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
+	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
+	{ 0xc2, TLB_DATA_2M_4M,		16,	" DTLB 2 MByte/4MByte pages, 4-way associative" },
 	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
 	{ 0x00, 0, 0 }
 };
@@ -558,6 +566,20 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case STLB_4K_2M:
+		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
 	case TLB_INST_ALL:
 		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
@@ -603,6 +625,10 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case TLB_DATA_1G:
+		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
+		break;
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b3218cdee95f..a389c1d859ec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2272,8 +2272,10 @@ static int mce_device_create(unsigned int cpu)
 	dev->release = &mce_device_release;
 
 	err = device_register(dev);
-	if (err)
+	if (err) {
+		put_device(dev);
 		return err;
+	}
 
 	for (i = 0; mce_device_attrs[i]; i++) {
 		err = device_create_file(dev, mce_device_attrs[i]);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
new file mode 100644
index 000000000000..0e3754e450d9
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -0,0 +1,662 @@
+/*
+ * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Copyright (C) 2013 Google, Inc., Stephane Eranian
+ *
+ * Intel RAPL interface is specified in the IA-32 Manual Vol3b
+ * section 14.7.1 (September 2013)
+ *
+ * RAPL provides more controls than just reporting energy consumption
+ * however here we only expose the 3 energy consumption free running
+ * counters (pp0, pkg, dram).
+ *
+ * Each of those counters increments in a power unit defined by the
+ * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules
+ * but it can vary.
+ *
+ * Counter to rapl events mappings:
+ *
+ *  pp0 counter: consumption of all physical cores (power plane 0)
+ * 	  event: rapl_energy_cores
+ *    perf code: 0x1
+ *
+ *  pkg counter: consumption of the whole processor package
+ *	  event: rapl_energy_pkg
+ *    perf code: 0x2
+ *
+ * dram counter: consumption of the dram domain (servers only)
+ *	  event: rapl_energy_dram
+ *    perf code: 0x3
+ *
+ * We manage those counters as free running (read-only). They may be
+ * use simultaneously by other tools, such as turbostat.
+ *
+ * The events only support system-wide mode counting. There is no
+ * sampling support because it does not make sense and is not
+ * supported by the RAPL hardware.
+ *
+ * Because we want to avoid floating-point operations in the kernel,
+ * the events are all reported in fixed point arithmetic (32.32).
+ * Tools must adjust the counts to convert them to Watts using
+ * the duration of the measurement. Tools may use a function such as
+ * ldexp(raw_count, -32);
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+#include <asm/cpu_device_id.h>
+#include "perf_event.h"
+
+/*
+ * RAPL energy status counters
+ */
+#define RAPL_IDX_PP0_NRG_STAT	0	/* all cores */
+#define INTEL_RAPL_PP0		0x1	/* pseudo-encoding */
+#define RAPL_IDX_PKG_NRG_STAT	1	/* entire package */
+#define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
+#define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
+#define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
+
+/* Clients have PP0, PKG */
+#define RAPL_IDX_CLN	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT)
+
+/* Servers have PP0, PKG, RAM */
+#define RAPL_IDX_SRV	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT)
+
+/*
+ * event code: LSB 8 bits, passed in attr->config
+ * any other bit is reserved
+ */
+#define RAPL_EVENT_MASK	0xFFULL
+
+#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format)		\
+static ssize_t __rapl_##_var##_show(struct kobject *kobj,	\
+				struct kobj_attribute *attr,	\
+				char *page)			\
+{								\
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);		\
+	return sprintf(page, _format "\n");			\
+}								\
+static struct kobj_attribute format_attr_##_var =		\
+	__ATTR(_name, 0444, __rapl_##_var##_show, NULL)
+
+#define RAPL_EVENT_DESC(_name, _config)				\
+{								\
+	.attr	= __ATTR(_name, 0444, rapl_event_show, NULL),	\
+	.config	= _config,					\
+}
+
+#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
+
+struct rapl_pmu {
+	spinlock_t	 lock;
+	int		 hw_unit;  /* 1/2^hw_unit Joule */
+	int		 n_active; /* number of active events */
+	struct list_head active_list;
+	struct pmu	 *pmu; /* pointer to rapl_pmu_class */
+	ktime_t		 timer_interval; /* in ktime_t unit */
+	struct hrtimer   hrtimer;
+};
+
+static struct pmu rapl_pmu_class;
+static cpumask_t rapl_cpu_mask;
+static int rapl_cntr_mask;
+
+static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu);
+static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free);
+
+static inline u64 rapl_read_counter(struct perf_event *event)
+{
+	u64 raw;
+	rdmsrl(event->hw.event_base, raw);
+	return raw;
+}
+
+static inline u64 rapl_scale(u64 v)
+{
+	/*
+	 * scale delta to smallest unit (1/2^32)
+	 * users must then scale back: count * 1/(1e9*2^32) to get Joules
+	 * or use ldexp(count, -32).
+	 * Watts = Joules/Time delta
+	 */
+	return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+}
+
+static u64 rapl_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev_raw_count, new_raw_count;
+	s64 delta, sdelta;
+	int shift = RAPL_CNTR_WIDTH;
+
+again:
+	prev_raw_count = local64_read(&hwc->prev_count);
+	rdmsrl(event->hw.event_base, new_raw_count);
+
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+			    new_raw_count) != prev_raw_count) {
+		cpu_relax();
+		goto again;
+	}
+
+	/*
+	 * Now we have the new raw value and have updated the prev
+	 * timestamp already. We can now calculate the elapsed delta
+	 * (event-)time and add that to the generic event.
+	 *
+	 * Careful, not all hw sign-extends above the physical width
+	 * of the count.
+	 */
+	delta = (new_raw_count << shift) - (prev_raw_count << shift);
+	delta >>= shift;
+
+	sdelta = rapl_scale(delta);
+
+	local64_add(sdelta, &event->count);
+
+	return new_raw_count;
+}
+
+static void rapl_start_hrtimer(struct rapl_pmu *pmu)
+{
+	__hrtimer_start_range_ns(&pmu->hrtimer,
+			pmu->timer_interval, 0,
+			HRTIMER_MODE_REL_PINNED, 0);
+}
+
+static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
+{
+	hrtimer_cancel(&pmu->hrtimer);
+}
+
+static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct perf_event *event;
+	unsigned long flags;
+
+	if (!pmu->n_active)
+		return HRTIMER_NORESTART;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	list_for_each_entry(event, &pmu->active_list, active_entry) {
+		rapl_event_update(event);
+	}
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+
+	hrtimer_forward_now(hrtimer, pmu->timer_interval);
+
+	return HRTIMER_RESTART;
+}
+
+static void rapl_hrtimer_init(struct rapl_pmu *pmu)
+{
+	struct hrtimer *hr = &pmu->hrtimer;
+
+	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hr->function = rapl_hrtimer_handle;
+}
+
+static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
+				   struct perf_event *event)
+{
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	event->hw.state = 0;
+
+	list_add_tail(&event->active_entry, &pmu->active_list);
+
+	local64_set(&event->hw.prev_count, rapl_read_counter(event));
+
+	pmu->n_active++;
+	if (pmu->n_active == 1)
+		rapl_start_hrtimer(pmu);
+}
+
+static void rapl_pmu_event_start(struct perf_event *event, int mode)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+	__rapl_pmu_event_start(pmu, event);
+	spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static void rapl_pmu_event_stop(struct perf_event *event, int mode)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	/* mark event as deactivated and stopped */
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		WARN_ON_ONCE(pmu->n_active <= 0);
+		pmu->n_active--;
+		if (pmu->n_active == 0)
+			rapl_stop_hrtimer(pmu);
+
+		list_del(&event->active_entry);
+
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	/* check if update of sw counter is necessary */
+	if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		rapl_event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static int rapl_pmu_event_add(struct perf_event *event, int mode)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (mode & PERF_EF_START)
+		__rapl_pmu_event_start(pmu, event);
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+
+	return 0;
+}
+
+static void rapl_pmu_event_del(struct perf_event *event, int flags)
+{
+	rapl_pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int rapl_pmu_event_init(struct perf_event *event)
+{
+	u64 cfg = event->attr.config & RAPL_EVENT_MASK;
+	int bit, msr, ret = 0;
+
+	/* only look at RAPL events */
+	if (event->attr.type != rapl_pmu_class.type)
+		return -ENOENT;
+
+	/* check only supported bits are set */
+	if (event->attr.config & ~RAPL_EVENT_MASK)
+		return -EINVAL;
+
+	/*
+	 * check event is known (determines counter)
+	 */
+	switch (cfg) {
+	case INTEL_RAPL_PP0:
+		bit = RAPL_IDX_PP0_NRG_STAT;
+		msr = MSR_PP0_ENERGY_STATUS;
+		break;
+	case INTEL_RAPL_PKG:
+		bit = RAPL_IDX_PKG_NRG_STAT;
+		msr = MSR_PKG_ENERGY_STATUS;
+		break;
+	case INTEL_RAPL_RAM:
+		bit = RAPL_IDX_RAM_NRG_STAT;
+		msr = MSR_DRAM_ENERGY_STATUS;
+		break;
+	default:
+		return -EINVAL;
+	}
+	/* check event supported */
+	if (!(rapl_cntr_mask & (1 << bit)))
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	/* must be done before validate_group */
+	event->hw.event_base = msr;
+	event->hw.config = cfg;
+	event->hw.idx = bit;
+
+	return ret;
+}
+
+static void rapl_pmu_event_read(struct perf_event *event)
+{
+	rapl_event_update(event);
+}
+
+static ssize_t rapl_get_attr_cpumask(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask);
+
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
+
+static struct attribute *rapl_pmu_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group rapl_pmu_attr_group = {
+	.attrs = rapl_pmu_attrs,
+};
+
+EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+EVENT_ATTR_STR(energy-pkg  , rapl_pkg, "event=0x02");
+EVENT_ATTR_STR(energy-ram  , rapl_ram, "event=0x03");
+
+EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+EVENT_ATTR_STR(energy-pkg.unit  , rapl_pkg_unit, "Joules");
+EVENT_ATTR_STR(energy-ram.unit  , rapl_ram_unit, "Joules");
+
+/*
+ * we compute in 0.23 nJ increments regardless of MSR
+ */
+EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+
+static struct attribute *rapl_events_srv_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
+static struct attribute *rapl_events_cln_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	NULL,
+};
+
+static struct attribute_group rapl_pmu_events_group = {
+	.name = "events",
+	.attrs = NULL, /* patched at runtime */
+};
+
+DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+static struct attribute *rapl_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group rapl_pmu_format_group = {
+	.name = "format",
+	.attrs = rapl_formats_attr,
+};
+
+const struct attribute_group *rapl_attr_groups[] = {
+	&rapl_pmu_attr_group,
+	&rapl_pmu_format_group,
+	&rapl_pmu_events_group,
+	NULL,
+};
+
+static struct pmu rapl_pmu_class = {
+	.attr_groups	= rapl_attr_groups,
+	.task_ctx_nr	= perf_invalid_context, /* system-wide only */
+	.event_init	= rapl_pmu_event_init,
+	.add		= rapl_pmu_event_add, /* must have */
+	.del		= rapl_pmu_event_del, /* must have */
+	.start		= rapl_pmu_event_start,
+	.stop		= rapl_pmu_event_stop,
+	.read		= rapl_pmu_event_read,
+};
+
+static void rapl_cpu_exit(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+	int i, phys_id = topology_physical_package_id(cpu);
+	int target = -1;
+
+	/* find a new cpu on same package */
+	for_each_online_cpu(i) {
+		if (i == cpu)
+			continue;
+		if (phys_id == topology_physical_package_id(i)) {
+			target = i;
+			break;
+		}
+	}
+	/*
+	 * clear cpu from cpumask
+	 * if was set in cpumask and still some cpu on package,
+	 * then move to new cpu
+	 */
+	if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0)
+		cpumask_set_cpu(target, &rapl_cpu_mask);
+
+	WARN_ON(cpumask_empty(&rapl_cpu_mask));
+	/*
+	 * migrate events and context to new cpu
+	 */
+	if (target >= 0)
+		perf_pmu_migrate_context(pmu->pmu, cpu, target);
+
+	/* cancel overflow polling timer for CPU */
+	rapl_stop_hrtimer(pmu);
+}
+
+static void rapl_cpu_init(int cpu)
+{
+	int i, phys_id = topology_physical_package_id(cpu);
+
+	/* check if phys_is is already covered */
+	for_each_cpu(i, &rapl_cpu_mask) {
+		if (phys_id == topology_physical_package_id(i))
+			return;
+	}
+	/* was not found, so add it */
+	cpumask_set_cpu(cpu, &rapl_cpu_mask);
+}
+
+static int rapl_cpu_prepare(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+	int phys_id = topology_physical_package_id(cpu);
+	u64 ms;
+
+	if (pmu)
+		return 0;
+
+	if (phys_id < 0)
+		return -1;
+
+	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+	if (!pmu)
+		return -1;
+
+	spin_lock_init(&pmu->lock);
+
+	INIT_LIST_HEAD(&pmu->active_list);
+
+	/*
+	 * grab power unit as: 1/2^unit Joules
+	 *
+	 * we cache in local PMU instance
+	 */
+	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
+	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->pmu = &rapl_pmu_class;
+
+	/*
+	 * use reference of 200W for scaling the timeout
+	 * to avoid missing counter overflows.
+	 * 200W = 200 Joules/sec
+	 * divide interval by 2 to avoid lockstep (2 * 100)
+	 * if hw unit is 32, then we use 2 ms 1/200/2
+	 */
+	if (pmu->hw_unit < 32)
+		ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1));
+	else
+		ms = 2;
+
+	pmu->timer_interval = ms_to_ktime(ms);
+
+	rapl_hrtimer_init(pmu);
+
+	/* set RAPL pmu for this cpu for now */
+	per_cpu(rapl_pmu, cpu) = pmu;
+	per_cpu(rapl_pmu_to_free, cpu) = NULL;
+
+	return 0;
+}
+
+static void rapl_cpu_kfree(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu);
+
+	kfree(pmu);
+
+	per_cpu(rapl_pmu_to_free, cpu) = NULL;
+}
+
+static int rapl_cpu_dying(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+
+	if (!pmu)
+		return 0;
+
+	per_cpu(rapl_pmu, cpu) = NULL;
+
+	per_cpu(rapl_pmu_to_free, cpu) = pmu;
+
+	return 0;
+}
+
+static int rapl_cpu_notifier(struct notifier_block *self,
+			     unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		rapl_cpu_prepare(cpu);
+		break;
+	case CPU_STARTING:
+		rapl_cpu_init(cpu);
+		break;
+	case CPU_UP_CANCELED:
+	case CPU_DYING:
+		rapl_cpu_dying(cpu);
+		break;
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		rapl_cpu_kfree(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		rapl_cpu_exit(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static const struct x86_cpu_id rapl_cpu_match[] = {
+	[0] = { .vendor = X86_VENDOR_INTEL, .family = 6 },
+	[1] = {},
+};
+
+static int __init rapl_pmu_init(void)
+{
+	struct rapl_pmu *pmu;
+	int cpu, ret;
+
+	/*
+	 * check for Intel processor family 6
+	 */
+	if (!x86_match_cpu(rapl_cpu_match))
+		return 0;
+
+	/* check supported CPU */
+	switch (boot_cpu_data.x86_model) {
+	case 42: /* Sandy Bridge */
+	case 58: /* Ivy Bridge */
+	case 60: /* Haswell */
+	case 69: /* Haswell-Celeron */
+		rapl_cntr_mask = RAPL_IDX_CLN;
+		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
+		break;
+	case 45: /* Sandy Bridge-EP */
+	case 62: /* IvyTown */
+		rapl_cntr_mask = RAPL_IDX_SRV;
+		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
+		break;
+
+	default:
+		/* unsupported */
+		return 0;
+	}
+	get_online_cpus();
+
+	for_each_online_cpu(cpu) {
+		rapl_cpu_prepare(cpu);
+		rapl_cpu_init(cpu);
+	}
+
+	perf_cpu_notifier(rapl_cpu_notifier);
+
+	ret = perf_pmu_register(&rapl_pmu_class, "power", -1);
+	if (WARN_ON(ret)) {
+		pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret);
+		put_online_cpus();
+		return -1;
+	}
+
+	pmu = __get_cpu_var(rapl_pmu);
+
+	pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
+		" API unit is 2^-32 Joules,"
+		" %d fixed counters"
+		" %llu ms ovfl timer\n",
+		pmu->hw_unit,
+		hweight32(rapl_cntr_mask),
+		ktime_to_ms(pmu->timer_interval));
+
+	put_online_cpus();
+
+	return 0;
+}
+device_initcall(rapl_pmu_init);
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 88db010845cb..384df5105fbc 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -31,20 +31,6 @@ static int __init x86_rdrand_setup(char *s)
 }
 __setup("nordrand", x86_rdrand_setup);
 
-/* We can't use arch_get_random_long() here since alternatives haven't run */
-static inline int rdrand_long(unsigned long *v)
-{
-	int ok;
-	asm volatile("1: " RDRAND_LONG "\n\t"
-		     "jc 2f\n\t"
-		     "decl %0\n\t"
-		     "jnz 1b\n\t"
-		     "2:"
-		     : "=r" (ok), "=a" (*v)
-		     : "0" (RDRAND_RETRY_LOOPS));
-	return ok;
-}
-
 /*
  * Force a reseed cycle; we are architecturally guaranteed a reseed
  * after no more than 512 128-bit chunks of random data.  This also
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 22d0687e7fda..7d4069864472 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -262,6 +262,50 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+/*
+ * This cpu is going to be removed and its vectors migrated to the remaining
+ * online cpus.  Check to see if there are enough vectors in the remaining cpus.
+ */
+int check_irq_vectors_for_cpu_disable(void)
+{
+	int irq, cpu;
+	unsigned int vector, this_count, count;
+	struct irq_desc *desc;
+	struct irq_data *data;
+	struct cpumask *affinity;
+
+	this_count = 0;
+	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+		irq = __this_cpu_read(vector_irq[vector]);
+		if (irq >= 0) {
+			desc = irq_to_desc(irq);
+			data = irq_desc_get_irq_data(desc);
+			affinity = data->affinity;
+			if (irq_has_action(irq) || !irqd_is_per_cpu(data) ||
+			    !cpumask_subset(affinity, cpu_online_mask))
+				this_count++;
+		}
+	}
+
+	count = 0;
+	for_each_online_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+		     vector++) {
+			if (per_cpu(vector_irq, cpu)[vector] < 0)
+				count++;
+		}
+	}
+
+	if (count < this_count) {
+		pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n",
+			smp_processor_id(), this_count, count);
+		return -ERANGE;
+	}
+	return 0;
+}
+
 /* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
 void fixup_irqs(void)
 {
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
new file mode 100644
index 000000000000..c2bedaea11f7
--- /dev/null
+++ b/arch/x86/kernel/ksysfs.c
@@ -0,0 +1,340 @@
+/*
+ * Architecture specific sysfs attributes in /sys/kernel
+ *
+ * Copyright (C) 2007, Intel Corp.
+ *      Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2013, 2013 Red Hat, Inc.
+ *      Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/io.h>
+#include <asm/setup.h>
+
+static ssize_t version_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x%04x\n", boot_params.hdr.version);
+}
+
+static struct kobj_attribute boot_params_version_attr = __ATTR_RO(version);
+
+static ssize_t boot_params_data_read(struct file *fp, struct kobject *kobj,
+				     struct bin_attribute *bin_attr,
+				     char *buf, loff_t off, size_t count)
+{
+	memcpy(buf, (void *)&boot_params + off, count);
+	return count;
+}
+
+static struct bin_attribute boot_params_data_attr = {
+	.attr = {
+		.name = "data",
+		.mode = S_IRUGO,
+	},
+	.read = boot_params_data_read,
+	.size = sizeof(boot_params),
+};
+
+static struct attribute *boot_params_version_attrs[] = {
+	&boot_params_version_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *boot_params_data_attrs[] = {
+	&boot_params_data_attr,
+	NULL,
+};
+
+static struct attribute_group boot_params_attr_group = {
+	.attrs = boot_params_version_attrs,
+	.bin_attrs = boot_params_data_attrs,
+};
+
+static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr)
+{
+	const char *name;
+
+	name = kobject_name(kobj);
+	return kstrtoint(name, 10, nr);
+}
+
+static int get_setup_data_paddr(int nr, u64 *paddr)
+{
+	int i = 0;
+	struct setup_data *data;
+	u64 pa_data = boot_params.hdr.setup_data;
+
+	while (pa_data) {
+		if (nr == i) {
+			*paddr = pa_data;
+			return 0;
+		}
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data)
+			return -ENOMEM;
+
+		pa_data = data->next;
+		iounmap(data);
+		i++;
+	}
+	return -EINVAL;
+}
+
+static int __init get_setup_data_size(int nr, size_t *size)
+{
+	int i = 0;
+	struct setup_data *data;
+	u64 pa_data = boot_params.hdr.setup_data;
+
+	while (pa_data) {
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data)
+			return -ENOMEM;
+		if (nr == i) {
+			*size = data->len;
+			iounmap(data);
+			return 0;
+		}
+
+		pa_data = data->next;
+		iounmap(data);
+		i++;
+	}
+	return -EINVAL;
+}
+
+static ssize_t type_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	int nr, ret;
+	u64 paddr;
+	struct setup_data *data;
+
+	ret = kobj_to_setup_data_nr(kobj, &nr);
+	if (ret)
+		return ret;
+
+	ret = get_setup_data_paddr(nr, &paddr);
+	if (ret)
+		return ret;
+	data = ioremap_cache(paddr, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	ret = sprintf(buf, "0x%x\n", data->type);
+	iounmap(data);
+	return ret;
+}
+
+static ssize_t setup_data_data_read(struct file *fp,
+				    struct kobject *kobj,
+				    struct bin_attribute *bin_attr,
+				    char *buf,
+				    loff_t off, size_t count)
+{
+	int nr, ret = 0;
+	u64 paddr;
+	struct setup_data *data;
+	void *p;
+
+	ret = kobj_to_setup_data_nr(kobj, &nr);
+	if (ret)
+		return ret;
+
+	ret = get_setup_data_paddr(nr, &paddr);
+	if (ret)
+		return ret;
+	data = ioremap_cache(paddr, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	if (off > data->len) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (count > data->len - off)
+		count = data->len - off;
+
+	if (!count)
+		goto out;
+
+	ret = count;
+	p = ioremap_cache(paddr + sizeof(*data), data->len);
+	if (!p) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	memcpy(buf, p + off, count);
+	iounmap(p);
+out:
+	iounmap(data);
+	return ret;
+}
+
+static struct kobj_attribute type_attr = __ATTR_RO(type);
+
+static struct bin_attribute data_attr = {
+	.attr = {
+		.name = "data",
+		.mode = S_IRUGO,
+	},
+	.read = setup_data_data_read,
+};
+
+static struct attribute *setup_data_type_attrs[] = {
+	&type_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *setup_data_data_attrs[] = {
+	&data_attr,
+	NULL,
+};
+
+static struct attribute_group setup_data_attr_group = {
+	.attrs = setup_data_type_attrs,
+	.bin_attrs = setup_data_data_attrs,
+};
+
+static int __init create_setup_data_node(struct kobject *parent,
+					 struct kobject **kobjp, int nr)
+{
+	int ret = 0;
+	size_t size;
+	struct kobject *kobj;
+	char name[16]; /* should be enough for setup_data nodes numbers */
+	snprintf(name, 16, "%d", nr);
+
+	kobj = kobject_create_and_add(name, parent);
+	if (!kobj)
+		return -ENOMEM;
+
+	ret = get_setup_data_size(nr, &size);
+	if (ret)
+		goto out_kobj;
+
+	data_attr.size = size;
+	ret = sysfs_create_group(kobj, &setup_data_attr_group);
+	if (ret)
+		goto out_kobj;
+	*kobjp = kobj;
+
+	return 0;
+out_kobj:
+	kobject_put(kobj);
+	return ret;
+}
+
+static void __init cleanup_setup_data_node(struct kobject *kobj)
+{
+	sysfs_remove_group(kobj, &setup_data_attr_group);
+	kobject_put(kobj);
+}
+
+static int __init get_setup_data_total_num(u64 pa_data, int *nr)
+{
+	int ret = 0;
+	struct setup_data *data;
+
+	*nr = 0;
+	while (pa_data) {
+		*nr += 1;
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pa_data = data->next;
+		iounmap(data);
+	}
+
+out:
+	return ret;
+}
+
+static int __init create_setup_data_nodes(struct kobject *parent)
+{
+	struct kobject *setup_data_kobj, **kobjp;
+	u64 pa_data;
+	int i, j, nr, ret = 0;
+
+	pa_data = boot_params.hdr.setup_data;
+	if (!pa_data)
+		return 0;
+
+	setup_data_kobj = kobject_create_and_add("setup_data", parent);
+	if (!setup_data_kobj) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = get_setup_data_total_num(pa_data, &nr);
+	if (ret)
+		goto out_setup_data_kobj;
+
+	kobjp = kmalloc(sizeof(*kobjp) * nr, GFP_KERNEL);
+	if (!kobjp) {
+		ret = -ENOMEM;
+		goto out_setup_data_kobj;
+	}
+
+	for (i = 0; i < nr; i++) {
+		ret = create_setup_data_node(setup_data_kobj, kobjp + i, i);
+		if (ret)
+			goto out_clean_nodes;
+	}
+
+	kfree(kobjp);
+	return 0;
+
+out_clean_nodes:
+	for (j = i - 1; j > 0; j--)
+		cleanup_setup_data_node(*(kobjp + j));
+	kfree(kobjp);
+out_setup_data_kobj:
+	kobject_put(setup_data_kobj);
+out:
+	return ret;
+}
+
+static int __init boot_params_ksysfs_init(void)
+{
+	int ret;
+	struct kobject *boot_params_kobj;
+
+	boot_params_kobj = kobject_create_and_add("boot_params",
+						  kernel_kobj);
+	if (!boot_params_kobj) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sysfs_create_group(boot_params_kobj, &boot_params_attr_group);
+	if (ret)
+		goto out_boot_params_kobj;
+
+	ret = create_setup_data_nodes(boot_params_kobj);
+	if (ret)
+		goto out_create_group;
+
+	return 0;
+out_create_group:
+	sysfs_remove_group(boot_params_kobj, &boot_params_attr_group);
+out_boot_params_kobj:
+	kobject_put(boot_params_kobj);
+out:
+	return ret;
+}
+
+arch_initcall(boot_params_ksysfs_init);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb233bc9dee3..5a7b2a070fb3 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -447,6 +447,9 @@ static void __init parse_setup_data(void)
 		case SETUP_DTB:
 			add_dtb(pa_data);
 			break;
+		case SETUP_EFI:
+			parse_efi_setup(pa_data, data_len);
+			break;
 		default:
 			break;
 		}
@@ -824,6 +827,20 @@ static void __init trim_low_memory_range(void)
 }
 	
 /*
+ * Dump out kernel offset information on panic.
+ */
+static int
+dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
+{
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
+		 "(relocation range: 0x%lx-0x%lx)\n",
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
+
+	return 0;
+}
+
+/*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
  * for initialization.  Note, the efi init code path is determined by the
@@ -924,8 +941,6 @@ void __init setup_arch(char **cmdline_p)
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();
-	/* update the e820_saved too */
-	e820_reserve_setup_data();
 
 	copy_edd();
 
@@ -987,6 +1002,8 @@ void __init setup_arch(char **cmdline_p)
 		early_dump_pci_devices();
 #endif
 
+	/* update the e820_saved too */
+	e820_reserve_setup_data();
 	finish_e820_parsing();
 
 	if (efi_enabled(EFI_BOOT))
@@ -1248,3 +1265,15 @@ void __init i386_reserve_resources(void)
 }
 
 #endif /* CONFIG_X86_32 */
+
+static struct notifier_block kernel_offset_notifier = {
+	.notifier_call = dump_kernel_offset
+};
+
+static int __init register_kernel_offset_dumper(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list,
+					&kernel_offset_notifier);
+	return 0;
+}
+__initcall(register_kernel_offset_dumper);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85dc05a3aa02..a32da804252e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1312,6 +1312,12 @@ void cpu_disable_common(void)
 
 int native_cpu_disable(void)
 {
+	int ret;
+
+	ret = check_irq_vectors_for_cpu_disable();
+	if (ret)
+		return ret;
+
 	clear_local_APIC();
 
 	cpu_disable_common();
@@ -1417,7 +1423,9 @@ static inline void mwait_play_dead(void)
 		 * The WBINVD is insufficient due to the spurious-wakeup
 		 * case where we return around the loop.
 		 */
+		mb();
 		clflush(mwait_ptr);
+		mb();
 		__monitor(mwait_ptr, 0, 0);
 		mb();
 		__mwait(eax, 0);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b857ed890b4c..57409f6b8c62 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -211,21 +211,17 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 	exception_exit(prev_state);					\
 }
 
-DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
-		regs->ip)
-DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
-DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN,
-		regs->ip)
-DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
-		coprocessor_segment_overrun)
-DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(X86_TRAP_DE,     SIGFPE,  "divide error",			divide_error,		     FPE_INTDIV, regs->ip )
+DO_ERROR     (X86_TRAP_OF,     SIGSEGV, "overflow",			overflow					  )
+DO_ERROR     (X86_TRAP_BR,     SIGSEGV, "bounds",			bounds						  )
+DO_ERROR_INFO(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op,		     ILL_ILLOPN, regs->ip )
+DO_ERROR     (X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",	coprocessor_segment_overrun			  )
+DO_ERROR     (X86_TRAP_TS,     SIGSEGV, "invalid TSS",			invalid_TSS					  )
+DO_ERROR     (X86_TRAP_NP,     SIGBUS,  "segment not present",		segment_not_present				  )
 #ifdef CONFIG_X86_32
-DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
+DO_ERROR     (X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment					  )
 #endif
-DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
-		BUS_ADRALN, 0)
+DO_ERROR_INFO(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check,	     BUS_ADRALN, 0	  )
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 422fd8223470..a4b451c6addf 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -562,6 +562,16 @@ static void __init xstate_enable_boot_cpu(void)
 	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
 		eagerfpu = ENABLE;
 
+	if (pcntxt_mask & XSTATE_EAGER) {
+		if (eagerfpu == DISABLE) {
+			pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
+					pcntxt_mask & XSTATE_EAGER);
+			pcntxt_mask &= ~XSTATE_EAGER;
+		} else {
+			eagerfpu = ENABLE;
+		}
+	}
+
 	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
 		pcntxt_mask, xstate_size);
 }
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index a30ca15be21c..dee945d55594 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -186,7 +186,7 @@ ENTRY(copy_user_generic_unrolled)
 30:	shll $6,%ecx
 	addl %ecx,%edx
 	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
+40:	leal (%rdx,%rcx,8),%edx
 	jmp 60f
 50:	movl %ecx,%edx
 60:	jmp copy_user_handle_tail /* ecx is zerorest also */
@@ -236,8 +236,6 @@ ENDPROC(copy_user_generic_unrolled)
 ENTRY(copy_user_generic_string)
 	CFI_STARTPROC
 	ASM_STAC
-	andl %edx,%edx
-	jz 4f
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
 	ALIGN_DESTINATION
@@ -249,12 +247,12 @@ ENTRY(copy_user_generic_string)
 2:	movl %edx,%ecx
 3:	rep
 	movsb
-4:	xorl %eax,%eax
+	xorl %eax,%eax
 	ASM_CLAC
 	ret
 
 	.section .fixup,"ax"
-11:	lea (%rdx,%rcx,8),%rcx
+11:	leal (%rdx,%rcx,8),%ecx
 12:	movl %ecx,%edx		/* ecx is zerorest also */
 	jmp copy_user_handle_tail
 	.previous
@@ -279,12 +277,10 @@ ENDPROC(copy_user_generic_string)
 ENTRY(copy_user_enhanced_fast_string)
 	CFI_STARTPROC
 	ASM_STAC
-	andl %edx,%edx
-	jz 2f
 	movl %edx,%ecx
 1:	rep
 	movsb
-2:	xorl %eax,%eax
+	xorl %eax,%eax
 	ASM_CLAC
 	ret
 
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 9d980d88b747..8c9f647ff9e1 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -87,9 +87,7 @@ int pmd_huge_support(void)
 }
 #endif
 
-/* x86_64 also uses this file */
-
-#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#ifdef CONFIG_HUGETLB_PAGE
 static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
@@ -99,7 +97,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
+	info.low_limit = current->mm->mmap_legacy_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
@@ -172,8 +170,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		return hugetlb_get_unmapped_area_topdown(file, addr, len,
 				pgoff, flags);
 }
-
-#endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
+#endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef CONFIG_X86_64
 static __init int setup_hugepagesz(char *opt)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4287f1ffba7e..5bdc5430597c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -806,6 +806,9 @@ void __init mem_init(void)
 	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
 #undef high_memory
 #undef __FIXADDR_TOP
+#ifdef CONFIG_RANDOMIZE_BASE
+	BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE);
+#endif
 
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 24aec58d6afd..c85da7bb6b60 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -211,9 +211,13 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	 */
 	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
 	if (!nd_pa) {
-		pr_err("Cannot find %zu bytes in node %d\n",
-		       nd_size, nid);
-		return;
+		nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
+					      MEMBLOCK_ALLOC_ACCESSIBLE);
+		if (!nd_pa) {
+			pr_err("Cannot find %zu bytes in node %d\n",
+			       nd_size, nid);
+			return;
+		}
 	}
 	nd = __va(nd_pa);
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480c2d71..b3b19f46c016 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -30,6 +30,7 @@
  */
 struct cpa_data {
 	unsigned long	*vaddr;
+	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
 	int		numpages;
@@ -322,17 +323,9 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	return prot;
 }
 
-/*
- * Lookup the page table entry for a virtual address. Return a pointer
- * to the entry and the level of the mapping.
- *
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
- */
-pte_t *lookup_address(unsigned long address, unsigned int *level)
+static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+				      unsigned int *level)
 {
-	pgd_t *pgd = pgd_offset_k(address);
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -361,8 +354,31 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 
 	return pte_offset_kernel(pmd, address);
 }
+
+/*
+ * Lookup the page table entry for a virtual address. Return a pointer
+ * to the entry and the level of the mapping.
+ *
+ * Note: We return pud and pmd either when the entry is marked large
+ * or when the present bit is not set. Otherwise we would return a
+ * pointer to a nonexisting mapping.
+ */
+pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+}
 EXPORT_SYMBOL_GPL(lookup_address);
 
+static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
+				  unsigned int *level)
+{
+        if (cpa->pgd)
+		return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+					       address, level);
+
+        return lookup_address(address, level);
+}
+
 /*
  * This is necessary because __pa() does not work on some
  * kinds of memory, like vmalloc() or the alloc_remap()
@@ -437,7 +453,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * Check for races, another CPU might have split this page
 	 * up already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte)
 		goto out_unlock;
 
@@ -543,7 +559,8 @@ out_unlock:
 }
 
 static int
-__split_large_page(pte_t *kpte, unsigned long address, struct page *base)
+__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
+		   struct page *base)
 {
 	pte_t *pbase = (pte_t *)page_address(base);
 	unsigned long pfn, pfninc = 1;
@@ -556,7 +573,7 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte) {
 		spin_unlock(&pgd_lock);
 		return 1;
@@ -632,7 +649,8 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	return 0;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
+			    unsigned long address)
 {
 	struct page *base;
 
@@ -644,15 +662,390 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	if (!base)
 		return -ENOMEM;
 
-	if (__split_large_page(kpte, address, base))
+	if (__split_large_page(cpa, kpte, address, base))
 		__free_page(base);
 
 	return 0;
 }
 
+static bool try_to_free_pte_page(pte_t *pte)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		if (!pte_none(pte[i]))
+			return false;
+
+	free_page((unsigned long)pte);
+	return true;
+}
+
+static bool try_to_free_pmd_page(pmd_t *pmd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		if (!pmd_none(pmd[i]))
+			return false;
+
+	free_page((unsigned long)pmd);
+	return true;
+}
+
+static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+{
+	pte_t *pte = pte_offset_kernel(pmd, start);
+
+	while (start < end) {
+		set_pte(pte, __pte(0));
+
+		start += PAGE_SIZE;
+		pte++;
+	}
+
+	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+		pmd_clear(pmd);
+		return true;
+	}
+	return false;
+}
+
+static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+			      unsigned long start, unsigned long end)
+{
+	if (unmap_pte_range(pmd, start, end))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud, start);
+
+	/*
+	 * Not on a 2MB page boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+		unsigned long pre_end = min_t(unsigned long, end, next_page);
+
+		__unmap_pmd_range(pud, pmd, start, pre_end);
+
+		start = pre_end;
+		pmd++;
+	}
+
+	/*
+	 * Try to unmap in 2M chunks.
+	 */
+	while (end - start >= PMD_SIZE) {
+		if (pmd_large(*pmd))
+			pmd_clear(pmd);
+		else
+			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+
+		start += PMD_SIZE;
+		pmd++;
+	}
+
+	/*
+	 * 4K leftovers?
+	 */
+	if (start < end)
+		return __unmap_pmd_range(pud, pmd, start, end);
+
+	/*
+	 * Try again to free the PMD page if haven't succeeded above.
+	 */
+	if (!pud_none(*pud))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+	pud_t *pud = pud_offset(pgd, start);
+
+	/*
+	 * Not on a GB page boundary?
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+		unsigned long pre_end	= min_t(unsigned long, end, next_page);
+
+		unmap_pmd_range(pud, start, pre_end);
+
+		start = pre_end;
+		pud++;
+	}
+
+	/*
+	 * Try to unmap in 1G chunks?
+	 */
+	while (end - start >= PUD_SIZE) {
+
+		if (pud_large(*pud))
+			pud_clear(pud);
+		else
+			unmap_pmd_range(pud, start, start + PUD_SIZE);
+
+		start += PUD_SIZE;
+		pud++;
+	}
+
+	/*
+	 * 2M leftovers?
+	 */
+	if (start < end)
+		unmap_pmd_range(pud, start, end);
+
+	/*
+	 * No need to try to free the PUD page because we'll free it in
+	 * populate_pgd's error path
+	 */
+}
+
+static int alloc_pte_page(pmd_t *pmd)
+{
+	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+	if (!pte)
+		return -1;
+
+	set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+	return 0;
+}
+
+static int alloc_pmd_page(pud_t *pud)
+{
+	pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+	if (!pmd)
+		return -1;
+
+	set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	return 0;
+}
+
+static void populate_pte(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pmd_t *pmd, pgprot_t pgprot)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, start);
+
+	while (num_pages-- && start < end) {
+
+		/* deal with the NX bit */
+		if (!(pgprot_val(pgprot) & _PAGE_NX))
+			cpa->pfn &= ~_PAGE_NX;
+
+		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
+
+		start	 += PAGE_SIZE;
+		cpa->pfn += PAGE_SIZE;
+		pte++;
+	}
+}
+
+static int populate_pmd(struct cpa_data *cpa,
+			unsigned long start, unsigned long end,
+			unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+{
+	unsigned int cur_pages = 0;
+	pmd_t *pmd;
+
+	/*
+	 * Not on a 2M boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long pre_end = start + (num_pages << PAGE_SHIFT);
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+
+		pre_end   = min_t(unsigned long, pre_end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(unsigned int, num_pages, cur_pages);
+
+		/*
+		 * Need a PTE page?
+		 */
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot);
+
+		start = pre_end;
+	}
+
+	/*
+	 * We mapped them all?
+	 */
+	if (num_pages == cur_pages)
+		return cur_pages;
+
+	while (end - start >= PMD_SIZE) {
+
+		/*
+		 * We cannot use a 1G page so allocate a PMD page if needed.
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		pmd = pmd_offset(pud, start);
+
+		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+
+		start	  += PMD_SIZE;
+		cpa->pfn  += PMD_SIZE;
+		cur_pages += PMD_SIZE >> PAGE_SHIFT;
+	}
+
+	/*
+	 * Map trailing 4K pages.
+	 */
+	if (start < end) {
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, end, num_pages - cur_pages,
+			     pmd, pgprot);
+	}
+	return num_pages;
+}
+
+static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+			pgprot_t pgprot)
+{
+	pud_t *pud;
+	unsigned long end;
+	int cur_pages = 0;
+
+	end = start + (cpa->numpages << PAGE_SHIFT);
+
+	/*
+	 * Not on a Gb page boundary? => map everything up to it with
+	 * smaller pages.
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long pre_end;
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+
+		pre_end   = min_t(unsigned long, end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(int, (int)cpa->numpages, cur_pages);
+
+		pud = pud_offset(pgd, start);
+
+		/*
+		 * Need a PMD page?
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		cur_pages = populate_pmd(cpa, start, pre_end, cur_pages,
+					 pud, pgprot);
+		if (cur_pages < 0)
+			return cur_pages;
+
+		start = pre_end;
+	}
+
+	/* We mapped them all? */
+	if (cpa->numpages == cur_pages)
+		return cur_pages;
+
+	pud = pud_offset(pgd, start);
+
+	/*
+	 * Map everything starting from the Gb boundary, possibly with 1G pages
+	 */
+	while (end - start >= PUD_SIZE) {
+		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+
+		start	  += PUD_SIZE;
+		cpa->pfn  += PUD_SIZE;
+		cur_pages += PUD_SIZE >> PAGE_SHIFT;
+		pud++;
+	}
+
+	/* Map trailing leftover */
+	if (start < end) {
+		int tmp;
+
+		pud = pud_offset(pgd, start);
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages,
+				   pud, pgprot);
+		if (tmp < 0)
+			return cur_pages;
+
+		cur_pages += tmp;
+	}
+	return cur_pages;
+}
+
+/*
+ * Restrictions for kernel page table do not necessarily apply when mapping in
+ * an alternate PGD.
+ */
+static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
+{
+	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
+	bool allocd_pgd = false;
+	pgd_t *pgd_entry;
+	pud_t *pud = NULL;	/* shut up gcc */
+	int ret;
+
+	pgd_entry = cpa->pgd + pgd_index(addr);
+
+	/*
+	 * Allocate a PUD page and hand it down for mapping.
+	 */
+	if (pgd_none(*pgd_entry)) {
+		pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+		if (!pud)
+			return -1;
+
+		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
+		allocd_pgd = true;
+	}
+
+	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);
+
+	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
+	if (ret < 0) {
+		unmap_pud_range(pgd_entry, addr,
+				addr + (cpa->numpages << PAGE_SHIFT));
+
+		if (allocd_pgd) {
+			/*
+			 * If I allocated this PUD page, I can just as well
+			 * free it in this error path.
+			 */
+			pgd_clear(pgd_entry);
+			free_page((unsigned long)pud);
+		}
+		return ret;
+	}
+	cpa->numpages = ret;
+	return 0;
+}
+
 static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 			       int primary)
 {
+	if (cpa->pgd)
+		return populate_pgd(cpa, vaddr);
+
 	/*
 	 * Ignore all non primary paths.
 	 */
@@ -697,7 +1090,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	else
 		address = *cpa->vaddr;
 repeat:
-	kpte = lookup_address(address, &level);
+	kpte = _lookup_address_cpa(cpa, address, &level);
 	if (!kpte)
 		return __cpa_process_fault(cpa, address, primary);
 
@@ -761,7 +1154,7 @@ repeat:
 	/*
 	 * We have to split the large page:
 	 */
-	err = split_large_page(kpte, address);
+	err = split_large_page(cpa, kpte, address);
 	if (!err) {
 		/*
 	 	 * Do a global flush tlb after splitting the large page
@@ -910,6 +1303,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	int ret, cache, checkalias;
 	unsigned long baddr = 0;
 
+	memset(&cpa, 0, sizeof(cpa));
+
 	/*
 	 * Check, if we are requested to change a not supported
 	 * feature:
@@ -1356,6 +1751,7 @@ static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
 	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
 				.mask_clr = __pgprot(0),
@@ -1374,6 +1770,7 @@ static int __set_pages_np(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
 	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
 				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
@@ -1434,6 +1831,36 @@ bool kernel_page_present(struct page *page)
 
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
+int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+			    unsigned numpages, unsigned long page_flags)
+{
+	int retval = -EINVAL;
+
+	struct cpa_data cpa = {
+		.vaddr = &address,
+		.pfn = pfn,
+		.pgd = pgd,
+		.numpages = numpages,
+		.mask_set = __pgprot(0),
+		.mask_clr = __pgprot(0),
+		.flags = 0,
+	};
+
+	if (!(__supported_pte_mask & _PAGE_NX))
+		goto out;
+
+	if (!(page_flags & _PAGE_NX))
+		cpa.mask_clr = __pgprot(_PAGE_NX);
+
+	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);
+
+	retval = __change_page_attr_set_clr(&cpa, 0);
+	__flush_tlb_all();
+
+out:
+	return retval;
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cceb813044ef..d62ec87a2b26 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -12,6 +12,8 @@
  *	Bibo Mao <bibo.mao@intel.com>
  *	Chandramouli Narayanan <mouli@linux.intel.com>
  *	Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2013 SuSE Labs
+ *	Borislav Petkov <bp@suse.de> - runtime services VA mapping
  *
  * Copied from efi_32.c to eliminate the duplicated code between EFI
  * 32/64 support code. --ying 2007-10-26
@@ -51,7 +53,7 @@
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
 
-#define EFI_DEBUG	1
+#define EFI_DEBUG
 
 #define EFI_MIN_RESERVE 5120
 
@@ -74,6 +76,8 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 	{NULL_GUID, NULL, NULL},
 };
 
+u64 efi_setup;		/* efi setup_data physical address */
+
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
  */
@@ -110,7 +114,6 @@ static int __init setup_storage_paranoia(char *arg)
 }
 early_param("efi_no_storage_paranoia", setup_storage_paranoia);
 
-
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	unsigned long flags;
@@ -398,9 +401,9 @@ int __init efi_memblock_x86_reserve_range(void)
 	return 0;
 }
 
-#if EFI_DEBUG
 static void __init print_efi_memmap(void)
 {
+#ifdef EFI_DEBUG
 	efi_memory_desc_t *md;
 	void *p;
 	int i;
@@ -415,8 +418,8 @@ static void __init print_efi_memmap(void)
 			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
 			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
 	}
-}
 #endif  /*  EFI_DEBUG  */
+}
 
 void __init efi_reserve_boot_services(void)
 {
@@ -436,7 +439,7 @@ void __init efi_reserve_boot_services(void)
 		 * - Not within any part of the kernel
 		 * - Not the bios reserved area
 		*/
-		if ((start+size >= __pa_symbol(_text)
+		if ((start + size > __pa_symbol(_text)
 				&& start <= __pa_symbol(_end)) ||
 			!e820_all_mapped(start, start+size, E820_RAM) ||
 			memblock_is_region_reserved(start, size)) {
@@ -489,18 +492,27 @@ static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
+		struct efi_setup_data *data = NULL;
 		u64 tmp = 0;
 
+		if (efi_setup) {
+			data = early_memremap(efi_setup, sizeof(*data));
+			if (!data)
+				return -ENOMEM;
+		}
 		systab64 = early_ioremap((unsigned long)phys,
 					 sizeof(*systab64));
 		if (systab64 == NULL) {
 			pr_err("Couldn't map the system table!\n");
+			if (data)
+				early_iounmap(data, sizeof(*data));
 			return -ENOMEM;
 		}
 
 		efi_systab.hdr = systab64->hdr;
-		efi_systab.fw_vendor = systab64->fw_vendor;
-		tmp |= systab64->fw_vendor;
+		efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor :
+					      systab64->fw_vendor;
+		tmp |= data ? data->fw_vendor : systab64->fw_vendor;
 		efi_systab.fw_revision = systab64->fw_revision;
 		efi_systab.con_in_handle = systab64->con_in_handle;
 		tmp |= systab64->con_in_handle;
@@ -514,15 +526,20 @@ static int __init efi_systab_init(void *phys)
 		tmp |= systab64->stderr_handle;
 		efi_systab.stderr = systab64->stderr;
 		tmp |= systab64->stderr;
-		efi_systab.runtime = (void *)(unsigned long)systab64->runtime;
-		tmp |= systab64->runtime;
+		efi_systab.runtime = data ?
+				     (void *)(unsigned long)data->runtime :
+				     (void *)(unsigned long)systab64->runtime;
+		tmp |= data ? data->runtime : systab64->runtime;
 		efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
 		tmp |= systab64->boottime;
 		efi_systab.nr_tables = systab64->nr_tables;
-		efi_systab.tables = systab64->tables;
-		tmp |= systab64->tables;
+		efi_systab.tables = data ? (unsigned long)data->tables :
+					   systab64->tables;
+		tmp |= data ? data->tables : systab64->tables;
 
 		early_iounmap(systab64, sizeof(*systab64));
+		if (data)
+			early_iounmap(data, sizeof(*data));
 #ifdef CONFIG_X86_32
 		if (tmp >> 32) {
 			pr_err("EFI data located above 4GB, disabling EFI.\n");
@@ -626,6 +643,62 @@ static int __init efi_memmap_init(void)
 	return 0;
 }
 
+/*
+ * A number of config table entries get remapped to virtual addresses
+ * after entering EFI virtual mode. However, the kexec kernel requires
+ * their physical addresses therefore we pass them via setup_data and
+ * correct those entries to their respective physical addresses here.
+ *
+ * Currently only handles smbios which is necessary for some firmware
+ * implementation.
+ */
+static int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+	int i, sz, ret = 0;
+	void *p, *tablep;
+	struct efi_setup_data *data;
+
+	if (!efi_setup)
+		return 0;
+
+	if (!efi_enabled(EFI_64BIT))
+		return 0;
+
+	data = early_memremap(efi_setup, sizeof(*data));
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (!data->smbios)
+		goto out_memremap;
+
+	sz = sizeof(efi_config_table_64_t);
+
+	p = tablep = early_memremap(tables, nr_tables * sz);
+	if (!p) {
+		pr_err("Could not map Configuration table!\n");
+		ret = -ENOMEM;
+		goto out_memremap;
+	}
+
+	for (i = 0; i < efi.systab->nr_tables; i++) {
+		efi_guid_t guid;
+
+		guid = ((efi_config_table_64_t *)p)->guid;
+
+		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
+			((efi_config_table_64_t *)p)->table = data->smbios;
+		p += sz;
+	}
+	early_iounmap(tablep, nr_tables * sz);
+
+out_memremap:
+	early_iounmap(data, sizeof(*data));
+out:
+	return ret;
+}
+
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -651,6 +724,10 @@ void __init efi_init(void)
 
 	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
+	efi.config_table = (unsigned long)efi.systab->tables;
+	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
+	efi.runtime	 = (unsigned long)efi.systab->runtime;
+
 	/*
 	 * Show what we know for posterity
 	 */
@@ -667,6 +744,9 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
+	if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables))
+		return;
+
 	if (efi_config_init(arch_tables))
 		return;
 
@@ -684,15 +764,12 @@ void __init efi_init(void)
 			return;
 		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
-
 	if (efi_memmap_init())
 		return;
 
 	set_bit(EFI_MEMMAP, &x86_efi_facility);
 
-#if EFI_DEBUG
 	print_efi_memmap();
-#endif
 }
 
 void __init efi_late_init(void)
@@ -741,36 +818,38 @@ void efi_memory_uc(u64 addr, unsigned long size)
 	set_memory_uc(addr, npages);
 }
 
-/*
- * This function will switch the EFI runtime services to virtual mode.
- * Essentially, look through the EFI memmap and map every region that
- * has the runtime attribute bit set in its memory descriptor and update
- * that memory descriptor with the virtual address obtained from ioremap().
- * This enables the runtime services to be called without having to
- * thunk back into physical mode for every invocation.
- */
-void __init efi_enter_virtual_mode(void)
+void __init old_map_region(efi_memory_desc_t *md)
 {
-	efi_memory_desc_t *md, *prev_md = NULL;
-	efi_status_t status;
+	u64 start_pfn, end_pfn, end;
 	unsigned long size;
-	u64 end, systab, start_pfn, end_pfn;
-	void *p, *va, *new_memmap = NULL;
-	int count = 0;
+	void *va;
 
-	efi.systab = NULL;
+	start_pfn = PFN_DOWN(md->phys_addr);
+	size	  = md->num_pages << PAGE_SHIFT;
+	end	  = md->phys_addr + size;
+	end_pfn   = PFN_UP(end);
 
-	/*
-	 * We don't do virtual mode, since we don't do runtime services, on
-	 * non-native EFI
-	 */
+	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
+		va = __va(md->phys_addr);
 
-	if (!efi_is_native()) {
-		efi_unmap_memmap();
-		return;
-	}
+		if (!(md->attribute & EFI_MEMORY_WB))
+			efi_memory_uc((u64)(unsigned long)va, size);
+	} else
+		va = efi_ioremap(md->phys_addr, size,
+				 md->type, md->attribute);
+
+	md->virt_addr = (u64) (unsigned long) va;
+	if (!va)
+		pr_err("ioremap of 0x%llX failed!\n",
+		       (unsigned long long)md->phys_addr);
+}
+
+/* Merge contiguous regions of the same type and attribute */
+static void __init efi_merge_regions(void)
+{
+	void *p;
+	efi_memory_desc_t *md, *prev_md = NULL;
 
-	/* Merge contiguous regions of the same type and attribute */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		u64 prev_size;
 		md = p;
@@ -796,6 +875,77 @@ void __init efi_enter_virtual_mode(void)
 		}
 		prev_md = md;
 	}
+}
+
+static void __init get_systab_virt_addr(efi_memory_desc_t *md)
+{
+	unsigned long size;
+	u64 end, systab;
+
+	size = md->num_pages << EFI_PAGE_SHIFT;
+	end = md->phys_addr + size;
+	systab = (u64)(unsigned long)efi_phys.systab;
+	if (md->phys_addr <= systab && systab < end) {
+		systab += md->virt_addr - md->phys_addr;
+		efi.systab = (efi_system_table_t *)(unsigned long)systab;
+	}
+}
+
+static int __init save_runtime_map(void)
+{
+	efi_memory_desc_t *md;
+	void *tmp, *p, *q = NULL;
+	int count = 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
+		    (md->type == EFI_BOOT_SERVICES_CODE) ||
+		    (md->type == EFI_BOOT_SERVICES_DATA))
+			continue;
+		tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL);
+		if (!tmp)
+			goto out;
+		q = tmp;
+
+		memcpy(q + count * memmap.desc_size, md, memmap.desc_size);
+		count++;
+	}
+
+	efi_runtime_map_setup(q, count, memmap.desc_size);
+
+	return 0;
+out:
+	kfree(q);
+	return -ENOMEM;
+}
+
+/*
+ * Map efi regions which were passed via setup_data. The virt_addr is a fixed
+ * addr which was used in first kernel of a kexec boot.
+ */
+static void __init efi_map_regions_fixed(void)
+{
+	void *p;
+	efi_memory_desc_t *md;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		efi_map_region_fixed(md); /* FIXME: add error handling */
+		get_systab_virt_addr(md);
+	}
+
+}
+
+/*
+ * Map efi memory ranges for runtime serivce and update new_memmap with virtual
+ * addresses.
+ */
+static void * __init efi_map_regions(int *count)
+{
+	efi_memory_desc_t *md;
+	void *p, *tmp, *new_memmap = NULL;
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
@@ -807,53 +957,95 @@ void __init efi_enter_virtual_mode(void)
 				continue;
 		}
 
-		size = md->num_pages << EFI_PAGE_SHIFT;
-		end = md->phys_addr + size;
+		efi_map_region(md);
+		get_systab_virt_addr(md);
 
-		start_pfn = PFN_DOWN(md->phys_addr);
-		end_pfn = PFN_UP(end);
-		if (pfn_range_is_mapped(start_pfn, end_pfn)) {
-			va = __va(md->phys_addr);
+		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
+			       GFP_KERNEL);
+		if (!tmp)
+			goto out;
+		new_memmap = tmp;
+		memcpy(new_memmap + (*count * memmap.desc_size), md,
+		       memmap.desc_size);
+		(*count)++;
+	}
 
-			if (!(md->attribute & EFI_MEMORY_WB))
-				efi_memory_uc((u64)(unsigned long)va, size);
-		} else
-			va = efi_ioremap(md->phys_addr, size,
-					 md->type, md->attribute);
+	return new_memmap;
+out:
+	kfree(new_memmap);
+	return NULL;
+}
+
+/*
+ * This function will switch the EFI runtime services to virtual mode.
+ * Essentially, we look through the EFI memmap and map every region that
+ * has the runtime attribute bit set in its memory descriptor into the
+ * ->trampoline_pgd page table using a top-down VA allocation scheme.
+ *
+ * The old method which used to update that memory descriptor with the
+ * virtual address obtained from ioremap() is still supported when the
+ * kernel is booted with efi=old_map on its command line. Same old
+ * method enabled the runtime services to be called without having to
+ * thunk back into physical mode for every invocation.
+ *
+ * The new method does a pagetable switch in a preemption-safe manner
+ * so that we're in a different address space when calling a runtime
+ * function. For function arguments passing we do copy the PGDs of the
+ * kernel page table into ->trampoline_pgd prior to each call.
+ *
+ * Specially for kexec boot, efi runtime maps in previous kernel should
+ * be passed in via setup_data. In that case runtime ranges will be mapped
+ * to the same virtual addresses as the first kernel.
+ */
+void __init efi_enter_virtual_mode(void)
+{
+	efi_status_t status;
+	void *new_memmap = NULL;
+	int err, count = 0;
 
-		md->virt_addr = (u64) (unsigned long) va;
+	efi.systab = NULL;
 
-		if (!va) {
-			pr_err("ioremap of 0x%llX failed!\n",
-			       (unsigned long long)md->phys_addr);
-			continue;
-		}
+	/*
+	 * We don't do virtual mode, since we don't do runtime services, on
+	 * non-native EFI
+	 */
+	if (!efi_is_native()) {
+		efi_unmap_memmap();
+		return;
+	}
 
-		systab = (u64) (unsigned long) efi_phys.systab;
-		if (md->phys_addr <= systab && systab < end) {
-			systab += md->virt_addr - md->phys_addr;
-			efi.systab = (efi_system_table_t *) (unsigned long) systab;
+	if (efi_setup) {
+		efi_map_regions_fixed();
+	} else {
+		efi_merge_regions();
+		new_memmap = efi_map_regions(&count);
+		if (!new_memmap) {
+			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+			return;
 		}
-		new_memmap = krealloc(new_memmap,
-				      (count + 1) * memmap.desc_size,
-				      GFP_KERNEL);
-		memcpy(new_memmap + (count * memmap.desc_size), md,
-		       memmap.desc_size);
-		count++;
 	}
 
+	err = save_runtime_map();
+	if (err)
+		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+
 	BUG_ON(!efi.systab);
 
-	status = phys_efi_set_virtual_address_map(
-		memmap.desc_size * count,
-		memmap.desc_size,
-		memmap.desc_version,
-		(efi_memory_desc_t *)__pa(new_memmap));
+	efi_setup_page_tables();
+	efi_sync_low_kernel_mappings();
 
-	if (status != EFI_SUCCESS) {
-		pr_alert("Unable to switch EFI into virtual mode "
-			 "(status=%lx)!\n", status);
-		panic("EFI call to SetVirtualAddressMap() failed!");
+	if (!efi_setup) {
+		status = phys_efi_set_virtual_address_map(
+			memmap.desc_size * count,
+			memmap.desc_size,
+			memmap.desc_version,
+			(efi_memory_desc_t *)__pa(new_memmap));
+
+		if (status != EFI_SUCCESS) {
+			pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+				 status);
+			panic("EFI call to SetVirtualAddressMap() failed!");
+		}
 	}
 
 	/*
@@ -876,7 +1068,8 @@ void __init efi_enter_virtual_mode(void)
 	efi.query_variable_info = virt_efi_query_variable_info;
 	efi.update_capsule = virt_efi_update_capsule;
 	efi.query_capsule_caps = virt_efi_query_capsule_caps;
-	if (__supported_pte_mask & _PAGE_NX)
+
+	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
 		runtime_code_page_mkexec();
 
 	kfree(new_memmap);
@@ -1006,3 +1199,15 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 	return EFI_SUCCESS;
 }
 EXPORT_SYMBOL_GPL(efi_query_variable_store);
+
+static int __init parse_efi_cmdline(char *str)
+{
+	if (*str == '=')
+		str++;
+
+	if (!strncmp(str, "old_map", 7))
+		set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+
+	return 0;
+}
+early_param("efi", parse_efi_cmdline);
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 40e446941dd7..249b183cf417 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -37,9 +37,19 @@
  * claim EFI runtime service handler exclusively and to duplicate a memory in
  * low memory space say 0 - 3G.
  */
-
 static unsigned long efi_rt_eflags;
 
+void efi_sync_low_kernel_mappings(void) {}
+void efi_setup_page_tables(void) {}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	old_map_region(md);
+}
+
+void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
+
 void efi_call_phys_prelog(void)
 {
 	struct desc_ptr gdt_descr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 39a0e7f1f0a3..6284f158a47d 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -38,10 +38,28 @@
 #include <asm/efi.h>
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
+#include <asm/realmode.h>
 
 static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
+/*
+ * We allocate runtime services regions bottom-up, starting from -4G, i.e.
+ * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
+ */
+static u64 efi_va	= -4 * (1UL << 30);
+#define EFI_VA_END	(-68 * (1UL << 30))
+
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64 r15;
+	u64 prev_cr3;
+	pgd_t *efi_pgt;
+	bool use_pgd;
+};
+
 static void __init early_code_mapping_set_exec(int executable)
 {
 	efi_memory_desc_t *md;
@@ -65,6 +83,9 @@ void __init efi_call_phys_prelog(void)
 	int pgd;
 	int n_pgds;
 
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
 
@@ -86,6 +107,10 @@ void __init efi_call_phys_epilog(void)
 	 */
 	int pgd;
 	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
 	for (pgd = 0; pgd < n_pgds; pgd++)
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
 	kfree(save_pgd);
@@ -94,6 +119,96 @@ void __init efi_call_phys_epilog(void)
 	early_code_mapping_set_exec(0);
 }
 
+/*
+ * Add low kernel mappings for passing arguments to EFI functions.
+ */
+void efi_sync_low_kernel_mappings(void)
+{
+	unsigned num_pgds;
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
+
+	memcpy(pgd + pgd_index(PAGE_OFFSET),
+		init_mm.pgd + pgd_index(PAGE_OFFSET),
+		sizeof(pgd_t) * num_pgds);
+}
+
+void efi_setup_page_tables(void)
+{
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		efi_scratch.use_pgd = true;
+}
+
+static void __init __map_region(efi_memory_desc_t *md, u64 va)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned long pf = 0;
+
+	if (!(md->attribute & EFI_MEMORY_WB))
+		pf |= _PAGE_PCD;
+
+	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
+		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, va);
+}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	unsigned long size = md->num_pages << PAGE_SHIFT;
+	u64 pa = md->phys_addr;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return old_map_region(md);
+
+	/*
+	 * Make sure the 1:1 mappings are present as a catch-all for b0rked
+	 * firmware which doesn't update all internal pointers after switching
+	 * to virtual mode and would otherwise crap on us.
+	 */
+	__map_region(md, md->phys_addr);
+
+	efi_va -= size;
+
+	/* Is PA 2M-aligned? */
+	if (!(pa & (PMD_SIZE - 1))) {
+		efi_va &= PMD_MASK;
+	} else {
+		u64 pa_offset = pa & (PMD_SIZE - 1);
+		u64 prev_va = efi_va;
+
+		/* get us the same offset within this 2M page */
+		efi_va = (efi_va & PMD_MASK) + pa_offset;
+
+		if (efi_va > prev_va)
+			efi_va -= PMD_SIZE;
+	}
+
+	if (efi_va < EFI_VA_END) {
+		pr_warn(FW_WARN "VA address range overflow!\n");
+		return;
+	}
+
+	/* Do the VA map */
+	__map_region(md, efi_va);
+	md->virt_addr = efi_va;
+}
+
+/*
+ * kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges.
+ * md->virt_addr is the original virtual address which had been mapped in kexec
+ * 1st kernel.
+ */
+void __init efi_map_region_fixed(efi_memory_desc_t *md)
+{
+	__map_region(md, md->virt_addr);
+}
+
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 				 u32 type, u64 attribute)
 {
@@ -113,3 +228,8 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 
 	return (void __iomem *)__va(phys_addr);
 }
+
+void __init parse_efi_setup(u64 phys_addr, u32 data_len)
+{
+	efi_setup = phys_addr + sizeof(struct setup_data);
+}
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 4c07ccab8146..88073b140298 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -34,10 +34,47 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
+	/* stolen from gcc */
+	.macro FLUSH_TLB_ALL
+	movq %r15, efi_scratch(%rip)
+	movq %r14, efi_scratch+8(%rip)
+	movq %cr4, %r15
+	movq %r15, %r14
+	andb $0x7f, %r14b
+	movq %r14, %cr4
+	movq %r15, %cr4
+	movq efi_scratch+8(%rip), %r14
+	movq efi_scratch(%rip), %r15
+	.endm
+
+	.macro SWITCH_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 1f
+	movq %r15, efi_scratch(%rip)		# r15
+	# save previous CR3
+	movq %cr3, %r15
+	movq %r15, efi_scratch+8(%rip)		# prev_cr3
+	movq efi_scratch+16(%rip), %r15		# EFI pgt
+	movq %r15, %cr3
+	1:
+	.endm
+
+	.macro RESTORE_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 2f
+	movq efi_scratch+8(%rip), %r15
+	movq %r15, %cr3
+	movq efi_scratch(%rip), %r15
+	FLUSH_TLB_ALL
+	2:
+	.endm
+
 ENTRY(efi_call0)
 	SAVE_XMM
 	subq $32, %rsp
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -47,7 +84,9 @@ ENTRY(efi_call1)
 	SAVE_XMM
 	subq $32, %rsp
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -57,7 +96,9 @@ ENTRY(efi_call2)
 	SAVE_XMM
 	subq $32, %rsp
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -68,7 +109,9 @@ ENTRY(efi_call3)
 	subq $32, %rsp
 	mov  %rcx, %r8
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -80,7 +123,9 @@ ENTRY(efi_call4)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -93,7 +138,9 @@ ENTRY(efi_call5)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
@@ -109,8 +156,15 @@ ENTRY(efi_call6)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
 ENDPROC(efi_call6)
+
+	.data
+ENTRY(efi_scratch)
+	.fill 3,8,0
+	.byte 0
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index a44f457e70a1..bad628a620c4 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -29,12 +29,10 @@ void __init reserve_real_mode(void)
 void __init setup_real_mode(void)
 {
 	u16 real_mode_seg;
-	u32 *rel;
+	const u32 *rel;
 	u32 count;
-	u32 *ptr;
-	u16 *seg;
-	int i;
 	unsigned char *base;
+	unsigned long phys_base;
 	struct trampoline_header *trampoline_header;
 	size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
 #ifdef CONFIG_X86_64
@@ -46,23 +44,23 @@ void __init setup_real_mode(void)
 
 	memcpy(base, real_mode_blob, size);
 
-	real_mode_seg = __pa(base) >> 4;
+	phys_base = __pa(base);
+	real_mode_seg = phys_base >> 4;
+
 	rel = (u32 *) real_mode_relocs;
 
 	/* 16-bit segment relocations. */
-	count = rel[0];
-	rel = &rel[1];
-	for (i = 0; i < count; i++) {
-		seg = (u16 *) (base + rel[i]);
+	count = *rel++;
+	while (count--) {
+		u16 *seg = (u16 *) (base + *rel++);
 		*seg = real_mode_seg;
 	}
 
 	/* 32-bit linear relocations. */
-	count = rel[i];
-	rel =  &rel[i + 1];
-	for (i = 0; i < count; i++) {
-		ptr = (u32 *) (base + rel[i]);
-		*ptr += __pa(base);
+	count = *rel++;
+	while (count--) {
+		u32 *ptr = (u32 *) (base + *rel++);
+		*ptr += phys_base;
 	}
 
 	/* Must be perfomed *after* relocation. */
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index f7bab68a4b83..11f9285a2ff6 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -722,15 +722,25 @@ static void percpu_init(void)
 
 /*
  * Check to see if a symbol lies in the .data..percpu section.
- * For some as yet not understood reason the "__init_begin"
- * symbol which immediately preceeds the .data..percpu section
- * also shows up as it it were part of it so we do an explict
- * check for that symbol name and ignore it.
+ *
+ * The linker incorrectly associates some symbols with the
+ * .data..percpu section so we also need to check the symbol
+ * name to make sure that we classify the symbol correctly.
+ *
+ * The GNU linker incorrectly associates:
+ *	__init_begin
+ *	__per_cpu_load
+ *
+ * The "gold" linker incorrectly associates:
+ *	init_per_cpu__irq_stack_union
+ *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
 {
 	return (sym->st_shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin");
+		strcmp(symname, "__init_begin") &&
+		strcmp(symname, "__per_cpu_load") &&
+		strncmp(symname, "init_per_cpu_", 13);
 }
 
 
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index 94166680b3a3..c4a5d87ede7e 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -11,6 +11,7 @@
 #include <linux/acpi.h>
 #include <linux/cper.h>
 #include <linux/ratelimit.h>
+#include <linux/edac.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
 
@@ -40,6 +41,8 @@ struct extlog_l1_head {
 	u8  rev1[12];
 };
 
+static int old_edac_report_status;
+
 static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";
 
 /* L1 table related physical address */
@@ -147,7 +150,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 
 	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
 
-	return NOTIFY_DONE;
+	return NOTIFY_STOP;
 }
 
 static bool __init extlog_get_l1addr(void)
@@ -193,8 +196,12 @@ static int __init extlog_init(void)
 	u64 cap;
 	int rc;
 
-	rc = -ENODEV;
+	if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
+		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
+		return -EPERM;
+	}
 
+	rc = -ENODEV;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (!(cap & MCG_ELOG_P))
 		return rc;
@@ -249,6 +256,12 @@ static int __init extlog_init(void)
 	if (elog_buf == NULL)
 		goto err_release_elog;
 
+	/*
+	 * eMCA event report method has higher priority than EDAC method,
+	 * unless EDAC event report method is mandatory.
+	 */
+	old_edac_report_status = get_edac_report_status();
+	set_edac_report_status(EDAC_REPORTING_DISABLED);
 	mce_register_decode_chain(&extlog_mce_dec);
 	/* enable OS to be involved to take over management from BIOS */
 	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
@@ -270,6 +283,7 @@ err:
 
 static void __exit extlog_exit(void)
 {
+	set_edac_report_status(old_edac_report_status);
 	mce_unregister_decode_chain(&extlog_mce_dec);
 	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 	if (extlog_l1_addr)
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 65610c0e7243..df96a0fe4890 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -192,10 +192,7 @@ static int power_saving_thread(void *data)
 					CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 			stop_critical_timings();
 
-			__monitor((void *)&current_thread_info()->flags, 0, 0);
-			smp_mb();
-			if (!need_resched())
-				__mwait(power_saving_mwait_eax, 1);
+			mwait_idle_with_hints(power_saving_mwait_eax, 1);
 
 			start_critical_timings();
 			if (lapic_marked_unstable)
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index ca0c6d7ec0d4..1fdf2c6e9d86 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -415,7 +415,8 @@ out:
 	return rc;
 }
 
-static int __einj_error_inject(u32 type, u64 param1, u64 param2)
+static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			       u64 param3, u64 param4)
 {
 	struct apei_exec_context ctx;
 	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
@@ -445,6 +446,12 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 				break;
 			}
 			v5param->flags = vendor_flags;
+		} else if (flags) {
+				v5param->flags = flags;
+				v5param->memory_address = param1;
+				v5param->memory_address_range = param2;
+				v5param->apicid = param3;
+				v5param->pcie_sbdf = param4;
 		} else {
 			switch (type) {
 			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
@@ -513,11 +520,17 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 }
 
 /* Inject the specified hardware error */
-static int einj_error_inject(u32 type, u64 param1, u64 param2)
+static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			     u64 param3, u64 param4)
 {
 	int rc;
 	unsigned long pfn;
 
+	/* If user manually set "flags", make sure it is legal */
+	if (flags && (flags &
+		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
+		return -EINVAL;
+
 	/*
 	 * We need extra sanity checks for memory errors.
 	 * Other types leap directly to injection.
@@ -531,7 +544,7 @@ static int einj_error_inject(u32 type, u64 param1, u64 param2)
 	if (type & ACPI5_VENDOR_BIT) {
 		if (vendor_flags != SETWA_FLAGS_MEM)
 			goto inject;
-	} else if (!(type & MEM_ERROR_MASK))
+	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM))
 		goto inject;
 
 	/*
@@ -545,15 +558,18 @@ static int einj_error_inject(u32 type, u64 param1, u64 param2)
 
 inject:
 	mutex_lock(&einj_mutex);
-	rc = __einj_error_inject(type, param1, param2);
+	rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
 	mutex_unlock(&einj_mutex);
 
 	return rc;
 }
 
 static u32 error_type;
+static u32 error_flags;
 static u64 error_param1;
 static u64 error_param2;
+static u64 error_param3;
+static u64 error_param4;
 static struct dentry *einj_debug_dir;
 
 static int available_error_type_show(struct seq_file *m, void *v)
@@ -647,7 +663,8 @@ static int error_inject_set(void *data, u64 val)
 	if (!error_type)
 		return -EINVAL;
 
-	return einj_error_inject(error_type, error_param1, error_param2);
+	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
+		error_param3, error_param4);
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL,
@@ -728,6 +745,10 @@ static int __init einj_init(void)
 	rc = -ENOMEM;
 	einj_param = einj_get_parameter_address();
 	if ((param_extension || acpi5) && einj_param) {
+		fentry = debugfs_create_x32("flags", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &error_flags);
+		if (!fentry)
+			goto err_unmap;
 		fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR,
 					    einj_debug_dir, &error_param1);
 		if (!fentry)
@@ -736,6 +757,14 @@ static int __init einj_init(void)
 					    einj_debug_dir, &error_param2);
 		if (!fentry)
 			goto err_unmap;
+		fentry = debugfs_create_x64("param3", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &error_param3);
+		if (!fentry)
+			goto err_unmap;
+		fentry = debugfs_create_x64("param4", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &error_param4);
+		if (!fentry)
+			goto err_unmap;
 
 		fentry = debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
 					    einj_debug_dir, &notrigger);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 1fc455b8ce17..3dca36d4ad26 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -725,11 +725,6 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
-	if (cx->entry_method == ACPI_CSTATE_FFH) {
-		if (current_set_polling_and_test())
-			return -EINVAL;
-	}
-
 	lapic_timer_state_broadcast(pr, cx, 1);
 	acpi_idle_do_entry(cx);
 
@@ -790,11 +785,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 		return acpi_idle_enter_c1(dev, drv, CPUIDLE_DRIVER_STATE_START);
 #endif
 
-	if (cx->entry_method == ACPI_CSTATE_FFH) {
-		if (current_set_polling_and_test())
-			return -EINVAL;
-	}
-
 	/*
 	 * Must be done before busmaster disable as we might need to
 	 * access HPET !
@@ -853,11 +843,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		}
 	}
 
-	if (cx->entry_method == ACPI_CSTATE_FFH) {
-		if (current_set_polling_and_test())
-			return -EINVAL;
-	}
-
 	acpi_unlazy_tlb(smp_processor_id());
 
 	/* Tell the scheduler that we are going deep-idle: */
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
index 351945fa2ecd..9d9e18aefaaa 100644
--- a/drivers/edac/edac_stub.c
+++ b/drivers/edac/edac_stub.c
@@ -29,6 +29,25 @@ EXPORT_SYMBOL_GPL(edac_err_assert);
 
 static atomic_t edac_subsys_valid = ATOMIC_INIT(0);
 
+int edac_report_status = EDAC_REPORTING_ENABLED;
+EXPORT_SYMBOL_GPL(edac_report_status);
+
+static int __init edac_report_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		set_edac_report_status(EDAC_REPORTING_ENABLED);
+	else if (!strncmp(str, "off", 3))
+		set_edac_report_status(EDAC_REPORTING_DISABLED);
+	else if (!strncmp(str, "force", 5))
+		set_edac_report_status(EDAC_REPORTING_FORCE);
+
+	return 0;
+}
+__setup("edac_report=", edac_report_setup);
+
 /*
  * called to determine if there is an EDAC driver interested in
  * knowing an event (such as NMI) occurred
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index d7f1b57bd3be..1229123ccb59 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -1829,6 +1829,9 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 	struct sbridge_pvt *pvt;
 
+	if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+		return NOTIFY_DONE;
+
 	mci = get_mci_for_node_id(mce->socketid);
 	if (!mci)
 		return NOTIFY_BAD;
@@ -2142,9 +2145,10 @@ static int __init sbridge_init(void)
 	opstate_init();
 
 	pci_rc = pci_register_driver(&sbridge_driver);
-
 	if (pci_rc >= 0) {
 		mce_register_decode_chain(&sbridge_mce_dec);
+		if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+			sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
 		return 0;
 	}
 
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 6aecbc86ec94..1e75f48b61f8 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -36,6 +36,17 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE
 	  backend for pstore by default. This setting can be overridden
 	  using the efivars module's pstore_disable parameter.
 
+config EFI_RUNTIME_MAP
+	bool "Export efi runtime maps to sysfs"
+	depends on X86 && EFI && KEXEC
+	default y
+	help
+	  Export efi runtime memory maps to /sys/firmware/efi/runtime-map.
+	  That memory map is used for example by kexec to set up efi virtual
+	  mapping the 2nd kernel, but can also be used for debugging purposes.
+
+	  See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map.
+
 endmenu
 
 config UEFI_CPER
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 6c2a41ec21ba..9553496b0f43 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_EFI)			+= efi.o vars.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
+obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 2e2fbdec0845..4753bac65279 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -32,6 +32,9 @@ struct efi __read_mostly efi = {
 	.hcdp       = EFI_INVALID_TABLE_ADDR,
 	.uga        = EFI_INVALID_TABLE_ADDR,
 	.uv_systab  = EFI_INVALID_TABLE_ADDR,
+	.fw_vendor  = EFI_INVALID_TABLE_ADDR,
+	.runtime    = EFI_INVALID_TABLE_ADDR,
+	.config_table  = EFI_INVALID_TABLE_ADDR,
 };
 EXPORT_SYMBOL(efi);
 
@@ -71,13 +74,49 @@ static ssize_t systab_show(struct kobject *kobj,
 static struct kobj_attribute efi_attr_systab =
 			__ATTR(systab, 0400, systab_show, NULL);
 
+#define EFI_FIELD(var) efi.var
+
+#define EFI_ATTR_SHOW(name) \
+static ssize_t name##_show(struct kobject *kobj, \
+				struct kobj_attribute *attr, char *buf) \
+{ \
+	return sprintf(buf, "0x%lx\n", EFI_FIELD(name)); \
+}
+
+EFI_ATTR_SHOW(fw_vendor);
+EFI_ATTR_SHOW(runtime);
+EFI_ATTR_SHOW(config_table);
+
+static struct kobj_attribute efi_attr_fw_vendor = __ATTR_RO(fw_vendor);
+static struct kobj_attribute efi_attr_runtime = __ATTR_RO(runtime);
+static struct kobj_attribute efi_attr_config_table = __ATTR_RO(config_table);
+
 static struct attribute *efi_subsys_attrs[] = {
 	&efi_attr_systab.attr,
-	NULL,	/* maybe more in the future? */
+	&efi_attr_fw_vendor.attr,
+	&efi_attr_runtime.attr,
+	&efi_attr_config_table.attr,
+	NULL,
 };
 
+static umode_t efi_attr_is_visible(struct kobject *kobj,
+				   struct attribute *attr, int n)
+{
+	umode_t mode = attr->mode;
+
+	if (attr == &efi_attr_fw_vendor.attr)
+		return (efi.fw_vendor == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	else if (attr == &efi_attr_runtime.attr)
+		return (efi.runtime == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	else if (attr == &efi_attr_config_table.attr)
+		return (efi.config_table == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+
+	return mode;
+}
+
 static struct attribute_group efi_subsys_attr_group = {
 	.attrs = efi_subsys_attrs,
+	.is_visible = efi_attr_is_visible,
 };
 
 static struct efivars generic_efivars;
@@ -128,6 +167,10 @@ static int __init efisubsys_init(void)
 		goto err_unregister;
 	}
 
+	error = efi_runtime_map_init(efi_kobj);
+	if (error)
+		goto err_remove_group;
+
 	/* and the standard mountpoint for efivarfs */
 	efivars_kobj = kobject_create_and_add("efivars", efi_kobj);
 	if (!efivars_kobj) {
diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c
new file mode 100644
index 000000000000..97cdd16a2169
--- /dev/null
+++ b/drivers/firmware/efi/runtime-map.c
@@ -0,0 +1,181 @@
+/*
+ * linux/drivers/efi/runtime-map.c
+ * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+
+#include <asm/setup.h>
+
+static void *efi_runtime_map;
+static int nr_efi_runtime_map;
+static u32 efi_memdesc_size;
+
+struct efi_runtime_map_entry {
+	efi_memory_desc_t md;
+	struct kobject kobj;   /* kobject for each entry */
+};
+
+static struct efi_runtime_map_entry **map_entries;
+
+struct map_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct efi_runtime_map_entry *entry, char *buf);
+};
+
+static inline struct map_attribute *to_map_attr(struct attribute *attr)
+{
+	return container_of(attr, struct map_attribute, attr);
+}
+
+static ssize_t type_show(struct efi_runtime_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%x\n", entry->md.type);
+}
+
+#define EFI_RUNTIME_FIELD(var) entry->md.var
+
+#define EFI_RUNTIME_U64_ATTR_SHOW(name) \
+static ssize_t name##_show(struct efi_runtime_map_entry *entry, char *buf) \
+{ \
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", EFI_RUNTIME_FIELD(name)); \
+}
+
+EFI_RUNTIME_U64_ATTR_SHOW(phys_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(virt_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(num_pages);
+EFI_RUNTIME_U64_ATTR_SHOW(attribute);
+
+static inline struct efi_runtime_map_entry *to_map_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct efi_runtime_map_entry, kobj);
+}
+
+static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct efi_runtime_map_entry *entry = to_map_entry(kobj);
+	struct map_attribute *map_attr = to_map_attr(attr);
+
+	return map_attr->show(entry, buf);
+}
+
+static struct map_attribute map_type_attr = __ATTR_RO(type);
+static struct map_attribute map_phys_addr_attr   = __ATTR_RO(phys_addr);
+static struct map_attribute map_virt_addr_attr  = __ATTR_RO(virt_addr);
+static struct map_attribute map_num_pages_attr  = __ATTR_RO(num_pages);
+static struct map_attribute map_attribute_attr  = __ATTR_RO(attribute);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&map_type_attr.attr,
+	&map_phys_addr_attr.attr,
+	&map_virt_addr_attr.attr,
+	&map_num_pages_attr.attr,
+	&map_attribute_attr.attr,
+	NULL
+};
+
+static const struct sysfs_ops map_attr_ops = {
+	.show = map_attr_show,
+};
+
+static void map_release(struct kobject *kobj)
+{
+	struct efi_runtime_map_entry *entry;
+
+	entry = to_map_entry(kobj);
+	kfree(entry);
+}
+
+static struct kobj_type __refdata map_ktype = {
+	.sysfs_ops	= &map_attr_ops,
+	.default_attrs	= def_attrs,
+	.release	= map_release,
+};
+
+static struct kset *map_kset;
+
+static struct efi_runtime_map_entry *
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
+{
+	int ret;
+	struct efi_runtime_map_entry *entry;
+
+	if (!map_kset) {
+		map_kset = kset_create_and_add("runtime-map", NULL, kobj);
+		if (!map_kset)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		kset_unregister(map_kset);
+		return entry;
+	}
+
+	memcpy(&entry->md, efi_runtime_map + nr * efi_memdesc_size,
+	       sizeof(efi_memory_desc_t));
+
+	kobject_init(&entry->kobj, &map_ktype);
+	entry->kobj.kset = map_kset;
+	ret = kobject_add(&entry->kobj, NULL, "%d", nr);
+	if (ret) {
+		kobject_put(&entry->kobj);
+		kset_unregister(map_kset);
+		return ERR_PTR(ret);
+	}
+
+	return entry;
+}
+
+void efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size)
+{
+	efi_runtime_map = map;
+	nr_efi_runtime_map = nr_entries;
+	efi_memdesc_size = desc_size;
+}
+
+int __init efi_runtime_map_init(struct kobject *efi_kobj)
+{
+	int i, j, ret = 0;
+	struct efi_runtime_map_entry *entry;
+
+	if (!efi_runtime_map)
+		return 0;
+
+	map_entries = kzalloc(nr_efi_runtime_map * sizeof(entry), GFP_KERNEL);
+	if (!map_entries) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < nr_efi_runtime_map; i++) {
+		entry = add_sysfs_runtime_map_entry(efi_kobj, i);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry);
+			goto out_add_entry;
+		}
+		*(map_entries + i) = entry;
+	}
+
+	return 0;
+out_add_entry:
+	for (j = i - 1; j > 0; j--) {
+		entry = *(map_entries + j);
+		kobject_put(&entry->kobj);
+	}
+	if (map_kset)
+		kset_unregister(map_kset);
+out:
+	return ret;
+}
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index d2fc8d0540a6..d15fce82117f 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -373,16 +373,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	if (!current_set_polling_and_test()) {
-
-		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
-			clflush((void *)&current_thread_info()->flags);
-
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(eax, ecx);
-	}
+	mwait_idle_with_hints(eax, ecx);
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e06c4453eabb..91a4ac7318f6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1737,7 +1737,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	}
 
 	if (all) {
-		rcu_assign_pointer(bond->curr_active_slave, NULL);
+		RCU_INIT_POINTER(bond->curr_active_slave, NULL);
 	} else if (oldcurrent == slave) {
 		/*
 		 * Note that we hold RTNL over this sequence, so there
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 67b608ef2cb2..00b93724150b 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -447,9 +447,7 @@ static int clamp_thread(void *arg)
 			 */
 			local_touch_nmi();
 			stop_critical_timings();
-			__monitor((void *)&current_thread_info()->flags, 0, 0);
-			cpu_relax(); /* allow HT sibling to run */
-			__mwait(eax, ecx);
+			mwait_idle_with_hints(eax, ecx);
 			start_critical_timings();
 			atomic_inc(&idle_wakeup_counter);
 		}
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 158158704c30..37b81bd51ec0 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -17,13 +17,13 @@ extern void __context_tracking_task_switch(struct task_struct *prev,
 
 static inline void user_enter(void)
 {
-	if (static_key_false(&context_tracking_enabled))
+	if (context_tracking_is_enabled())
 		context_tracking_user_enter();
 
 }
 static inline void user_exit(void)
 {
-	if (static_key_false(&context_tracking_enabled))
+	if (context_tracking_is_enabled())
 		context_tracking_user_exit();
 }
 
@@ -31,7 +31,7 @@ static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -42,7 +42,7 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (static_key_false(&context_tracking_enabled)) {
+	if (context_tracking_is_enabled()) {
 		if (prev_ctx == IN_USER)
 			context_tracking_user_enter();
 	}
@@ -51,7 +51,7 @@ static inline void exception_exit(enum ctx_state prev_ctx)
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next)
 {
-	if (static_key_false(&context_tracking_enabled))
+	if (context_tracking_is_enabled())
 		__context_tracking_task_switch(prev, next);
 }
 #else
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index 0f1979d0674f..97a81225d037 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -22,15 +22,20 @@ struct context_tracking {
 extern struct static_key context_tracking_enabled;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
-static inline bool context_tracking_in_user(void)
+static inline bool context_tracking_is_enabled(void)
 {
-	return __this_cpu_read(context_tracking.state) == IN_USER;
+	return static_key_false(&context_tracking_enabled);
 }
 
-static inline bool context_tracking_active(void)
+static inline bool context_tracking_cpu_is_enabled(void)
 {
 	return __this_cpu_read(context_tracking.active);
 }
+
+static inline bool context_tracking_in_user(void)
+{
+	return __this_cpu_read(context_tracking.state) == IN_USER;
+}
 #else
 static inline bool context_tracking_in_user(void) { return false; }
 static inline bool context_tracking_active(void) { return false; }
diff --git a/include/linux/edac.h b/include/linux/edac.h
index dbdffe8d4469..8e6c20af11a2 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -35,6 +35,34 @@ extern void edac_atomic_assert_error(void);
 extern struct bus_type *edac_get_sysfs_subsys(void);
 extern void edac_put_sysfs_subsys(void);
 
+enum {
+	EDAC_REPORTING_ENABLED,
+	EDAC_REPORTING_DISABLED,
+	EDAC_REPORTING_FORCE
+};
+
+extern int edac_report_status;
+#ifdef CONFIG_EDAC
+static inline int get_edac_report_status(void)
+{
+	return edac_report_status;
+}
+
+static inline void set_edac_report_status(int new)
+{
+	edac_report_status = new;
+}
+#else
+static inline int get_edac_report_status(void)
+{
+	return EDAC_REPORTING_DISABLED;
+}
+
+static inline void set_edac_report_status(int new)
+{
+}
+#endif
+
 static inline void opstate_init(void)
 {
 	switch (edac_op_state) {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 11ce6784a196..0a819e7a60c9 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -556,6 +556,9 @@ extern struct efi {
 	unsigned long hcdp;		/* HCDP table */
 	unsigned long uga;		/* UGA table */
 	unsigned long uv_systab;	/* UV system table */
+	unsigned long fw_vendor;	/* fw_vendor */
+	unsigned long runtime;		/* runtime table */
+	unsigned long config_table;	/* config tables */
 	efi_get_time_t *get_time;
 	efi_set_time_t *set_time;
 	efi_get_wakeup_time_t *get_wakeup_time;
@@ -653,6 +656,7 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
 #define EFI_MEMMAP		4	/* Can we use EFI memory map? */
 #define EFI_64BIT		5	/* Is the firmware 64-bit? */
+#define EFI_ARCH_1		6	/* First arch-specific bit */
 
 #ifdef CONFIG_EFI
 # ifdef CONFIG_X86
@@ -872,4 +876,17 @@ int efivars_sysfs_init(void);
 
 #endif /* CONFIG_EFI_VARS */
 
+#ifdef CONFIG_EFI_RUNTIME_MAP
+int efi_runtime_map_init(struct kobject *);
+void efi_runtime_map_setup(void *, int, u32);
+#else
+static inline int efi_runtime_map_init(struct kobject *kobj)
+{
+	return 0;
+}
+
+static inline void
+efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size) {}
+#endif
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index ecb87544cc5d..2aa3d4b000e6 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -394,6 +394,15 @@ extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
 extern int sysctl_panic_on_stackoverflow;
+/*
+ * Only to be used by arch init code. If the user over-wrote the default
+ * CONFIG_PANIC_TIMEOUT, honor it.
+ */
+static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout)
+{
+	if (panic_timeout == arch_default_timeout)
+		panic_timeout = timeout;
+}
 extern const char *print_tainted(void);
 enum lockdep_ok {
 	LOCKDEP_STILL_OK,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2e069d1288df..8f4a70f2eca8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -319,7 +319,10 @@ struct perf_event {
 	 */
 	struct list_head		migrate_entry;
 
-	struct hlist_node		hlist_entry;
+	union {
+		struct hlist_node	hlist_entry;
+		struct list_head	active_entry;
+	};
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 45a0a9e81478..dbaf99084112 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -55,8 +55,8 @@ static inline void __list_add_rcu(struct list_head *new,
 	next->prev = new;
 }
 #else
-extern void __list_add_rcu(struct list_head *new,
-		struct list_head *prev, struct list_head *next);
+void __list_add_rcu(struct list_head *new,
+		    struct list_head *prev, struct list_head *next);
 #endif
 
 /**
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 39cbb889e20d..3e355c688618 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -50,13 +50,13 @@ extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
-extern void rcutorture_record_test_transition(void);
-extern void rcutorture_record_progress(unsigned long vernum);
-extern void do_trace_rcu_torture_read(const char *rcutorturename,
-				      struct rcu_head *rhp,
-				      unsigned long secs,
-				      unsigned long c_old,
-				      unsigned long c);
+void rcutorture_record_test_transition(void);
+void rcutorture_record_progress(unsigned long vernum);
+void do_trace_rcu_torture_read(const char *rcutorturename,
+			       struct rcu_head *rhp,
+			       unsigned long secs,
+			       unsigned long c_old,
+			       unsigned long c);
 #else
 static inline void rcutorture_record_test_transition(void)
 {
@@ -65,11 +65,11 @@ static inline void rcutorture_record_progress(unsigned long vernum)
 {
 }
 #ifdef CONFIG_RCU_TRACE
-extern void do_trace_rcu_torture_read(const char *rcutorturename,
-				      struct rcu_head *rhp,
-				      unsigned long secs,
-				      unsigned long c_old,
-				      unsigned long c);
+void do_trace_rcu_torture_read(const char *rcutorturename,
+			       struct rcu_head *rhp,
+			       unsigned long secs,
+			       unsigned long c_old,
+			       unsigned long c);
 #else
 #define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
 	do { } while (0)
@@ -118,8 +118,8 @@ extern void do_trace_rcu_torture_read(const char *rcutorturename,
  * if CPU A and CPU B are the same CPU (but again only if the system has
  * more than one CPU).
  */
-extern void call_rcu(struct rcu_head *head,
-			      void (*func)(struct rcu_head *head));
+void call_rcu(struct rcu_head *head,
+	      void (*func)(struct rcu_head *head));
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
@@ -149,8 +149,8 @@ extern void call_rcu(struct rcu_head *head,
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
  */
-extern void call_rcu_bh(struct rcu_head *head,
-			void (*func)(struct rcu_head *head));
+void call_rcu_bh(struct rcu_head *head,
+		 void (*func)(struct rcu_head *head));
 
 /**
  * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
@@ -171,16 +171,16 @@ extern void call_rcu_bh(struct rcu_head *head,
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
  */
-extern void call_rcu_sched(struct rcu_head *head,
-			   void (*func)(struct rcu_head *rcu));
+void call_rcu_sched(struct rcu_head *head,
+		    void (*func)(struct rcu_head *rcu));
 
-extern void synchronize_sched(void);
+void synchronize_sched(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
-extern void __rcu_read_lock(void);
-extern void __rcu_read_unlock(void);
-extern void rcu_read_unlock_special(struct task_struct *t);
+void __rcu_read_lock(void);
+void __rcu_read_unlock(void);
+void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
@@ -216,19 +216,19 @@ static inline int rcu_preempt_depth(void)
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /* Internal to kernel */
-extern void rcu_init(void);
-extern void rcu_sched_qs(int cpu);
-extern void rcu_bh_qs(int cpu);
-extern void rcu_check_callbacks(int cpu, int user);
+void rcu_init(void);
+void rcu_sched_qs(int cpu);
+void rcu_bh_qs(int cpu);
+void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
-extern void rcu_idle_enter(void);
-extern void rcu_idle_exit(void);
-extern void rcu_irq_enter(void);
-extern void rcu_irq_exit(void);
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
 
 #ifdef CONFIG_RCU_USER_QS
-extern void rcu_user_enter(void);
-extern void rcu_user_exit(void);
+void rcu_user_enter(void);
+void rcu_user_exit(void);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
@@ -262,7 +262,7 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 	} while (0)
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
-extern bool __rcu_is_watching(void);
+bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
@@ -289,8 +289,8 @@ void wait_rcu_gp(call_rcu_func_t crf);
  * initialization.
  */
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-extern void init_rcu_head_on_stack(struct rcu_head *head);
-extern void destroy_rcu_head_on_stack(struct rcu_head *head);
+void init_rcu_head_on_stack(struct rcu_head *head);
+void destroy_rcu_head_on_stack(struct rcu_head *head);
 #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
@@ -325,6 +325,7 @@ static inline void rcu_lock_release(struct lockdep_map *map)
 extern struct lockdep_map rcu_lock_map;
 extern struct lockdep_map rcu_bh_lock_map;
 extern struct lockdep_map rcu_sched_lock_map;
+extern struct lockdep_map rcu_callback_map;
 extern int debug_lockdep_rcu_enabled(void);
 
 /**
@@ -362,7 +363,7 @@ static inline int rcu_read_lock_held(void)
  * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
  * hell.
  */
-extern int rcu_read_lock_bh_held(void);
+int rcu_read_lock_bh_held(void);
 
 /**
  * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
@@ -448,7 +449,7 @@ static inline int rcu_read_lock_sched_held(void)
 
 #ifdef CONFIG_PROVE_RCU
 
-extern int rcu_my_thread_group_empty(void);
+int rcu_my_thread_group_empty(void);
 
 /**
  * rcu_lockdep_assert - emit lockdep splat if specified condition not met
@@ -548,10 +549,48 @@ static inline void rcu_preempt_sleep_check(void)
 		smp_read_barrier_depends(); \
 		(_________p1); \
 	})
-#define __rcu_assign_pointer(p, v, space) \
+
+/**
+ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
+ * @v: The value to statically initialize with.
+ */
+#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
+
+/**
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
+ *
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.
+ *
+ * Inserts memory barriers on architectures that require them
+ * (which is most of them), and also prevents the compiler from
+ * reordering the code that initializes the structure after the pointer
+ * assignment.  More importantly, this call documents which pointers
+ * will be dereferenced by RCU read-side code.
+ *
+ * In some special cases, you may use RCU_INIT_POINTER() instead
+ * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
+ * to the fact that it does not constrain either the CPU or the compiler.
+ * That said, using RCU_INIT_POINTER() when you should have used
+ * rcu_assign_pointer() is a very bad thing that results in
+ * impossible-to-diagnose memory corruption.  So please be careful.
+ * See the RCU_INIT_POINTER() comment header for details.
+ *
+ * Note that rcu_assign_pointer() evaluates each of its arguments only
+ * once, appearances notwithstanding.  One of the "extra" evaluations
+ * is in typeof() and the other visible only to sparse (__CHECKER__),
+ * neither of which actually execute the argument.  As with most cpp
+ * macros, this execute-arguments-only-once property is important, so
+ * please be careful when making changes to rcu_assign_pointer() and the
+ * other macros that it invokes.
+ */
+#define rcu_assign_pointer(p, v) \
 	do { \
 		smp_wmb(); \
-		(p) = (typeof(*v) __force space *)(v); \
+		ACCESS_ONCE(p) = RCU_INITIALIZER(v); \
 	} while (0)
 
 
@@ -890,32 +929,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 }
 
 /**
- * rcu_assign_pointer() - assign to RCU-protected pointer
- * @p: pointer to assign to
- * @v: value to assign (publish)
- *
- * Assigns the specified value to the specified RCU-protected
- * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.
- *
- * Inserts memory barriers on architectures that require them
- * (which is most of them), and also prevents the compiler from
- * reordering the code that initializes the structure after the pointer
- * assignment.  More importantly, this call documents which pointers
- * will be dereferenced by RCU read-side code.
- *
- * In some special cases, you may use RCU_INIT_POINTER() instead
- * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
- * to the fact that it does not constrain either the CPU or the compiler.
- * That said, using RCU_INIT_POINTER() when you should have used
- * rcu_assign_pointer() is a very bad thing that results in
- * impossible-to-diagnose memory corruption.  So please be careful.
- * See the RCU_INIT_POINTER() comment header for details.
- */
-#define rcu_assign_pointer(p, v) \
-	__rcu_assign_pointer((p), (v), __rcu)
-
-/**
  * RCU_INIT_POINTER() - initialize an RCU protected pointer
  *
  * Initialize an RCU-protected pointer in special cases where readers
@@ -949,7 +962,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  */
 #define RCU_INIT_POINTER(p, v) \
 	do { \
-		p = (typeof(*v) __force __rcu *)(v); \
+		p = RCU_INITIALIZER(v); \
 	} while (0)
 
 /**
@@ -958,7 +971,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * GCC-style initialization for an RCU-protected pointer in a structure field.
  */
 #define RCU_POINTER_INITIALIZER(p, v) \
-		.p = (typeof(*v) __force __rcu *)(v)
+		.p = RCU_INITIALIZER(v)
 
 /*
  * Does the specified offset indicate that the corresponding rcu_head
@@ -1005,7 +1018,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
 #ifdef CONFIG_RCU_NOCB_CPU
-extern bool rcu_is_nocb_cpu(int cpu);
+bool rcu_is_nocb_cpu(int cpu);
 #else
 static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
@@ -1013,8 +1026,8 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 
 /* Only for use by adaptive-ticks code. */
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
-extern bool rcu_sys_is_idle(void);
-extern void rcu_sysidle_force_exit(void);
+bool rcu_sys_is_idle(void);
+void rcu_sysidle_force_exit(void);
 #else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 
 static inline bool rcu_sys_is_idle(void)
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 09ebcbe9fd78..6f01771b571c 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -125,7 +125,7 @@ static inline void exit_rcu(void)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern int rcu_scheduler_active __read_mostly;
-extern void rcu_scheduler_starting(void);
+void rcu_scheduler_starting(void);
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 static inline void rcu_scheduler_starting(void)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 4b9c81548742..72137ee8c603 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,9 +30,9 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-extern void rcu_note_context_switch(int cpu);
-extern int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
-extern void rcu_cpu_stall_reset(void);
+void rcu_note_context_switch(int cpu);
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
+void rcu_cpu_stall_reset(void);
 
 /*
  * Note a virtualization-based context switch.  This is simply a
@@ -44,9 +44,9 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	rcu_note_context_switch(cpu);
 }
 
-extern void synchronize_rcu_bh(void);
-extern void synchronize_sched_expedited(void);
-extern void synchronize_rcu_expedited(void);
+void synchronize_rcu_bh(void);
+void synchronize_sched_expedited(void);
+void synchronize_rcu_expedited(void);
 
 void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 
@@ -71,25 +71,25 @@ static inline void synchronize_rcu_bh_expedited(void)
 	synchronize_sched_expedited();
 }
 
-extern void rcu_barrier(void);
-extern void rcu_barrier_bh(void);
-extern void rcu_barrier_sched(void);
+void rcu_barrier(void);
+void rcu_barrier_bh(void);
+void rcu_barrier_sched(void);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
-extern long rcu_batches_completed_sched(void);
+long rcu_batches_completed(void);
+long rcu_batches_completed_bh(void);
+long rcu_batches_completed_sched(void);
 
-extern void rcu_force_quiescent_state(void);
-extern void rcu_bh_force_quiescent_state(void);
-extern void rcu_sched_force_quiescent_state(void);
+void rcu_force_quiescent_state(void);
+void rcu_bh_force_quiescent_state(void);
+void rcu_sched_force_quiescent_state(void);
 
-extern void exit_rcu(void);
+void exit_rcu(void);
 
-extern void rcu_scheduler_starting(void);
+void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 
-extern bool rcu_is_watching(void);
+bool rcu_is_watching(void);
 
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 53f97eb8dbc7..3a1e9857b393 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -168,7 +168,6 @@ extern char ___assert_task_state[1 - 2*!!(
 
 #define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
 #define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
-#define task_is_dead(task)	((task)->exit_state != 0)
 #define task_is_stopped_or_traced(task)	\
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 41467f8ff8ec..31e0193cb0c5 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -48,7 +48,6 @@ extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
 extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
 
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 75f34949d9ab..3f2867ff0ced 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -130,6 +130,16 @@ do {								\
 #define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifndef smp_mb__after_unlock_lock
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif
+
 /**
  * raw_spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 5128d33bbb39..0175d8663b6c 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -104,7 +104,7 @@ extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 extern void tick_clock_notify(void);
 extern int tick_check_oneshot_change(int allow_nohz);
 extern struct tick_sched *tick_get_tick_sched(int cpu);
-extern void tick_check_idle(int cpu);
+extern void tick_check_idle(void);
 extern int tick_oneshot_mode_active(void);
 #  ifndef arch_needs_cpu
 #   define arch_needs_cpu(cpu) (0)
@@ -112,7 +112,7 @@ extern int tick_oneshot_mode_active(void);
 # else
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
-static inline void tick_check_idle(int cpu) { }
+static inline void tick_check_idle(void) { }
 static inline int tick_oneshot_mode_active(void) { return 0; }
 # endif
 
@@ -121,7 +121,7 @@ static inline void tick_init(void) { }
 static inline void tick_cancel_sched_timer(int cpu) { }
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
-static inline void tick_check_idle(int cpu) { }
+static inline void tick_check_idle(void) { }
 static inline int tick_oneshot_mode_active(void) { return 0; }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
@@ -165,7 +165,7 @@ extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return false;
 
 	return tick_nohz_full_running;
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 319eae70fe84..e32251e00e62 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -26,16 +26,13 @@
 
 #include <linux/errno.h>
 #include <linux/rbtree.h>
+#include <linux/types.h>
 
 struct vm_area_struct;
 struct mm_struct;
 struct inode;
 struct notifier_block;
 
-#ifdef CONFIG_ARCH_SUPPORTS_UPROBES
-# include <asm/uprobes.h>
-#endif
-
 #define UPROBE_HANDLER_REMOVE		1
 #define UPROBE_HANDLER_MASK		1
 
@@ -60,6 +57,8 @@ struct uprobe_consumer {
 };
 
 #ifdef CONFIG_UPROBES
+#include <asm/uprobes.h>
+
 enum uprobe_task_state {
 	UTASK_RUNNING,
 	UTASK_SSTEP,
@@ -72,35 +71,28 @@ enum uprobe_task_state {
  */
 struct uprobe_task {
 	enum uprobe_task_state		state;
-	struct arch_uprobe_task		autask;
 
-	struct return_instance		*return_instances;
-	unsigned int			depth;
-	struct uprobe			*active_uprobe;
+	union {
+		struct {
+			struct arch_uprobe_task	autask;
+			unsigned long		vaddr;
+		};
 
+		struct {
+			struct callback_head	dup_xol_work;
+			unsigned long		dup_xol_addr;
+		};
+	};
+
+	struct uprobe			*active_uprobe;
 	unsigned long			xol_vaddr;
-	unsigned long			vaddr;
-};
 
-/*
- * On a breakpoint hit, thread contests for a slot.  It frees the
- * slot after singlestep. Currently a fixed number of slots are
- * allocated.
- */
-struct xol_area {
-	wait_queue_head_t 	wq;		/* if all slots are busy */
-	atomic_t 		slot_count;	/* number of in-use slots */
-	unsigned long 		*bitmap;	/* 0 = free slot */
-	struct page 		*page;
-
-	/*
-	 * We keep the vma's vm_start rather than a pointer to the vma
-	 * itself.  The probed process or a naughty kernel module could make
-	 * the vma go away, and we must handle that reasonably gracefully.
-	 */
-	unsigned long 		vaddr;		/* Page(s) of instruction slots */
+	struct return_instance		*return_instances;
+	unsigned int			depth;
 };
 
+struct xol_area;
+
 struct uprobes_state {
 	struct xol_area		*xol_area;
 };
@@ -109,6 +101,7 @@ extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsign
 extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
+extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
@@ -120,7 +113,6 @@ extern void uprobe_end_dup_mmap(void);
 extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t, unsigned long flags);
-extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
 extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);
@@ -176,10 +168,6 @@ static inline bool uprobe_deny_signal(void)
 {
 	return false;
 }
-static inline unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
-{
-	return 0;
-}
 static inline void uprobe_free_utask(struct task_struct *t)
 {
 }
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index f5b72b364bda..c5165fd256f9 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -19,8 +19,8 @@ static inline bool vtime_accounting_enabled(void) { return true; }
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 static inline bool vtime_accounting_enabled(void)
 {
-	if (static_key_false(&context_tracking_enabled)) {
-		if (context_tracking_active())
+	if (context_tracking_is_enabled()) {
+		if (context_tracking_cpu_is_enabled())
 			return true;
 	}
 
diff --git a/include/trace/events/ras.h b/include/trace/events/ras.h
index 88b878383797..1c875ad1ee5f 100644
--- a/include/trace/events/ras.h
+++ b/include/trace/events/ras.h
@@ -5,7 +5,7 @@
 #define _TRACE_AER_H
 
 #include <linux/tracepoint.h>
-#include <linux/edac.h>
+#include <linux/aer.h>
 
 
 /*
@@ -63,10 +63,10 @@ TRACE_EVENT(aer_event,
 
 	TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
 		__get_str(dev_name),
-		__entry->severity == HW_EVENT_ERR_CORRECTED ? "Corrected" :
-			__entry->severity == HW_EVENT_ERR_FATAL ?
-			"Fatal" : "Uncorrected",
-		__entry->severity == HW_EVENT_ERR_CORRECTED ?
+		__entry->severity == AER_CORRECTABLE ? "Corrected" :
+			__entry->severity == AER_FATAL ?
+			"Fatal" : "Uncorrected, non-fatal",
+		__entry->severity == AER_CORRECTABLE ?
 		__print_flags(__entry->status, "|", aer_correctable_errors) :
 		__print_flags(__entry->status, "|", aer_uncorrectable_errors))
 );
diff --git a/include/uapi/asm-generic/statfs.h b/include/uapi/asm-generic/statfs.h
index 0999647fca13..cb89cc730f0b 100644
--- a/include/uapi/asm-generic/statfs.h
+++ b/include/uapi/asm-generic/statfs.h
@@ -13,7 +13,7 @@
  */
 #ifndef __statfs_word
 #if __BITS_PER_LONG == 64
-#define __statfs_word long
+#define __statfs_word __kernel_long_t
 #else
 #define __statfs_word __u32
 #endif
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index e5f3917aa05b..6cb20d2e7ee0 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -53,10 +53,10 @@ void context_tracking_user_enter(void)
 	/*
 	 * Repeat the user_enter() check here because some archs may be calling
 	 * this from asm and if no CPU needs context tracking, they shouldn't
-	 * go further. Repeat the check here until they support the static key
-	 * check.
+	 * go further. Repeat the check here until they support the inline static
+	 * key check.
 	 */
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return;
 
 	/*
@@ -160,7 +160,7 @@ void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return;
 
 	if (in_interrupt())
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f5744010a8d2..4b743b299124 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3542,7 +3542,7 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	int ret = 0;
+	int ret = 0, active;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -3566,6 +3566,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->attr.sample_period = value;
 		event->hw.sample_period = value;
 	}
+
+	active = (event->state == PERF_EVENT_STATE_ACTIVE);
+	if (active) {
+		perf_pmu_disable(ctx->pmu);
+		event->pmu->stop(event, PERF_EF_UPDATE);
+	}
+
+	local64_set(&event->hw.period_left, 0);
+
+	if (active) {
+		event->pmu->start(event, PERF_EF_RELOAD);
+		perf_pmu_enable(ctx->pmu);
+	}
+
 unlock:
 	raw_spin_unlock_irq(&ctx->lock);
 
@@ -6670,6 +6684,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
+	INIT_LIST_HEAD(&event->active_entry);
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8b168af135b..146a5792b1d2 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -61,19 +61,20 @@ again:
 	 *
 	 *   kernel				user
 	 *
-	 *   READ ->data_tail			READ ->data_head
-	 *   smp_mb()	(A)			smp_rmb()	(C)
-	 *   WRITE $data			READ $data
-	 *   smp_wmb()	(B)			smp_mb()	(D)
-	 *   STORE ->data_head			WRITE ->data_tail
+	 *   if (LOAD ->data_tail) {		LOAD ->data_head
+	 *			(A)		smp_rmb()	(C)
+	 *	STORE $data			LOAD $data
+	 *	smp_wmb()	(B)		smp_mb()	(D)
+	 *	STORE ->data_head		STORE ->data_tail
+	 *   }
 	 *
 	 * Where A pairs with D, and B pairs with C.
 	 *
-	 * I don't think A needs to be a full barrier because we won't in fact
-	 * write data until we see the store from userspace. So we simply don't
-	 * issue the data WRITE until we observe it. Be conservative for now.
+	 * In our case (A) is a control dependency that separates the load of
+	 * the ->data_tail and the stores of $data. In case ->data_tail
+	 * indicates there is no room in the buffer to store $data we do not.
 	 *
-	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * D needs to be a full barrier since it separates the data READ
 	 * from the tail WRITE.
 	 *
 	 * For B a WMB is sufficient since it separates two WRITEs, and for C
@@ -81,7 +82,7 @@ again:
 	 *
 	 * See perf_output_begin().
 	 */
-	smp_wmb();
+	smp_wmb(); /* B, matches C */
 	rb->user_page->data_head = head;
 
 	/*
@@ -144,17 +145,26 @@ int perf_output_begin(struct perf_output_handle *handle,
 		if (!rb->overwrite &&
 		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
 			goto fail;
+
+		/*
+		 * The above forms a control dependency barrier separating the
+		 * @tail load above from the data stores below. Since the @tail
+		 * load is required to compute the branch to fail below.
+		 *
+		 * A, matches D; the full memory barrier userspace SHOULD issue
+		 * after reading the data and before storing the new tail
+		 * position.
+		 *
+		 * See perf_output_put_handle().
+		 */
+
 		head += size;
 	} while (local_cmpxchg(&rb->head, offset, head) != offset);
 
 	/*
-	 * Separate the userpage->tail read from the data stores below.
-	 * Matches the MB userspace SHOULD issue after reading the data
-	 * and before storing the new tail position.
-	 *
-	 * See perf_output_put_handle().
+	 * We rely on the implied barrier() by local_cmpxchg() to ensure
+	 * none of the data stores below can be lifted up by the compiler.
 	 */
-	smp_mb();
 
 	if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
 		local_add(rb->watermark, &rb->wakeup);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 24b7d6ca871b..b886a5e7d4ff 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -73,6 +73,17 @@ struct uprobe {
 	struct inode		*inode;		/* Also hold a ref to inode */
 	loff_t			offset;
 	unsigned long		flags;
+
+	/*
+	 * The generic code assumes that it has two members of unknown type
+	 * owned by the arch-specific code:
+	 *
+	 * 	insn -	copy_insn() saves the original instruction here for
+	 *		arch_uprobe_analyze_insn().
+	 *
+	 *	ixol -	potentially modified instruction to execute out of
+	 *		line, copied to xol_area by xol_get_insn_slot().
+	 */
 	struct arch_uprobe	arch;
 };
 
@@ -86,6 +97,29 @@ struct return_instance {
 };
 
 /*
+ * Execute out of line area: anonymous executable mapping installed
+ * by the probed task to execute the copy of the original instruction
+ * mangled by set_swbp().
+ *
+ * On a breakpoint hit, thread contests for a slot.  It frees the
+ * slot after singlestep. Currently a fixed number of slots are
+ * allocated.
+ */
+struct xol_area {
+	wait_queue_head_t 	wq;		/* if all slots are busy */
+	atomic_t 		slot_count;	/* number of in-use slots */
+	unsigned long 		*bitmap;	/* 0 = free slot */
+	struct page 		*page;
+
+	/*
+	 * We keep the vma's vm_start rather than a pointer to the vma
+	 * itself.  The probed process or a naughty kernel module could make
+	 * the vma go away, and we must handle that reasonably gracefully.
+	 */
+	unsigned long 		vaddr;		/* Page(s) of instruction slots */
+};
+
+/*
  * valid_vma: Verify if the specified vma is an executable vma
  * Relax restrictions while unregistering: vm_flags might have
  * changed after breakpoint was inserted.
@@ -330,7 +364,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
 }
 
 static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -529,8 +563,8 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp)
 {
 	struct address_space *mapping = uprobe->inode->i_mapping;
 	loff_t offs = uprobe->offset;
-	void *insn = uprobe->arch.insn;
-	int size = MAX_UINSN_BYTES;
+	void *insn = &uprobe->arch.insn;
+	int size = sizeof(uprobe->arch.insn);
 	int len, err = -EIO;
 
 	/* Copy only available bytes, -EIO if nothing was read */
@@ -569,7 +603,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 		goto out;
 
 	ret = -ENOTSUPP;
-	if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
+	if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
 		goto out;
 
 	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
@@ -1264,7 +1298,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 
 	/* Initialize the slot */
 	copy_to_page(area->page, xol_vaddr,
-			uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
+			&uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
 	/*
 	 * We probably need flush_icache_user_range() but it needs vma.
 	 * This should work on supported architectures too.
@@ -1403,12 +1437,10 @@ static void uprobe_warn(struct task_struct *t, const char *msg)
 
 static void dup_xol_work(struct callback_head *work)
 {
-	kfree(work);
-
 	if (current->flags & PF_EXITING)
 		return;
 
-	if (!__create_xol_area(current->utask->vaddr))
+	if (!__create_xol_area(current->utask->dup_xol_addr))
 		uprobe_warn(current, "dup xol area");
 }
 
@@ -1419,7 +1451,6 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 {
 	struct uprobe_task *utask = current->utask;
 	struct mm_struct *mm = current->mm;
-	struct callback_head *work;
 	struct xol_area *area;
 
 	t->utask = NULL;
@@ -1441,14 +1472,9 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 	if (mm == t->mm)
 		return;
 
-	/* TODO: move it into the union in uprobe_task */
-	work = kmalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return uprobe_warn(t, "dup xol area");
-
-	t->utask->vaddr = area->vaddr;
-	init_task_work(work, dup_xol_work);
-	task_work_add(t, work, true);
+	t->utask->dup_xol_addr = area->vaddr;
+	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
+	task_work_add(t, &t->utask->dup_xol_work, true);
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 5721f0e3f2da..6023d150a305 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1403,13 +1403,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->tgid = p->pid;
 	}
 
-	p->pdeath_signal = 0;
-	p->exit_state = 0;
-
 	p->nr_dirtied = 0;
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
 	p->dirty_paused_when = 0;
 
+	p->pdeath_signal = 0;
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 576ba756a32d..eb8a54783fa0 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
 /*
  * Is this the address of a static object:
  */
+#ifdef __KERNEL__
 static int static_obj(void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
 	 */
 	return is_module_address(addr) || is_module_percpu_address(addr);
 }
+#endif
 
 /*
  * To make lock name printouts unique, we calculate a unique
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
+#ifdef __KERNEL__
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ retry:
 		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
 
 /*
  * Careful: only use this function if you are sure that
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443fe1f48..faf6f5b53e77 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
 		return;
 
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+	if (!lock->owner)
+		DEBUG_LOCKS_WARN_ON(!lock->owner);
+	else
+		DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
 }
diff --git a/kernel/panic.c b/kernel/panic.c
index c00b4ceb39e8..6d6300375090 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,7 +33,7 @@ static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 
-int panic_timeout;
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
 
 ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c7f31aa272f7..3b8946416a5f 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -233,7 +233,8 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 
 /*
  * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
 static int cpu_clock_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
@@ -260,30 +261,53 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 	return 0;
 }
 
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+				    const clockid_t which_clock,
+				    struct timespec *tp)
+{
+	int err = -EINVAL;
+	unsigned long long rtn;
+
+	if (CPUCLOCK_PERTHREAD(which_clock)) {
+		if (same_thread_group(tsk, current))
+			err = cpu_clock_sample(which_clock, tsk, &rtn);
+	} else {
+		unsigned long flags;
+		struct sighand_struct *sighand;
+
+		/*
+		 * while_each_thread() is not yet entirely RCU safe,
+		 * keep locking the group while sampling process
+		 * clock for now.
+		 */
+		sighand = lock_task_sighand(tsk, &flags);
+		if (!sighand)
+			return err;
+
+		if (tsk == current || thread_group_leader(tsk))
+			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+		unlock_task_sighand(tsk, &flags);
+	}
+
+	if (!err)
+		sample_to_timespec(which_clock, rtn, tp);
+
+	return err;
+}
+
 
 static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
-	int error = -EINVAL;
-	unsigned long long rtn;
+	int err = -EINVAL;
 
 	if (pid == 0) {
 		/*
 		 * Special case constant value for our own clocks.
 		 * We don't have to do any lookup to find ourselves.
 		 */
-		if (CPUCLOCK_PERTHREAD(which_clock)) {
-			/*
-			 * Sampling just ourselves we can do with no locking.
-			 */
-			error = cpu_clock_sample(which_clock,
-						 current, &rtn);
-		} else {
-			read_lock(&tasklist_lock);
-			error = cpu_clock_sample_group(which_clock,
-						       current, &rtn);
-			read_unlock(&tasklist_lock);
-		}
+		err = posix_cpu_clock_get_task(current, which_clock, tp);
 	} else {
 		/*
 		 * Find the given PID, and validate that the caller
@@ -292,29 +316,12 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 		struct task_struct *p;
 		rcu_read_lock();
 		p = find_task_by_vpid(pid);
-		if (p) {
-			if (CPUCLOCK_PERTHREAD(which_clock)) {
-				if (same_thread_group(p, current)) {
-					error = cpu_clock_sample(which_clock,
-								 p, &rtn);
-				}
-			} else {
-				read_lock(&tasklist_lock);
-				if (thread_group_leader(p) && p->sighand) {
-					error =
-					    cpu_clock_sample_group(which_clock,
-							           p, &rtn);
-				}
-				read_unlock(&tasklist_lock);
-			}
-		}
+		if (p)
+			err = posix_cpu_clock_get_task(p, which_clock, tp);
 		rcu_read_unlock();
 	}
 
-	if (error)
-		return error;
-	sample_to_timespec(which_clock, rtn, tp);
-	return 0;
+	return err;
 }
 
 
@@ -371,36 +378,40 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
  */
 static int posix_cpu_timer_del(struct k_itimer *timer)
 {
-	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
+	unsigned long flags;
+	struct sighand_struct *sighand;
+	struct task_struct *p = timer->it.cpu.task;
 
-	if (likely(p != NULL)) {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
-			/*
-			 * We raced with the reaping of the task.
-			 * The deletion should have cleared us off the list.
-			 */
-			BUG_ON(!list_empty(&timer->it.cpu.entry));
-		} else {
-			spin_lock(&p->sighand->siglock);
-			if (timer->it.cpu.firing)
-				ret = TIMER_RETRY;
-			else
-				list_del(&timer->it.cpu.entry);
-			spin_unlock(&p->sighand->siglock);
-		}
-		read_unlock(&tasklist_lock);
+	WARN_ON_ONCE(p == NULL);
 
-		if (!ret)
-			put_task_struct(p);
+	/*
+	 * Protect against sighand release/switch in exit/exec and process/
+	 * thread timer list entry concurrent read/writes.
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	if (unlikely(sighand == NULL)) {
+		/*
+		 * We raced with the reaping of the task.
+		 * The deletion should have cleared us off the list.
+		 */
+		WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
+	} else {
+		if (timer->it.cpu.firing)
+			ret = TIMER_RETRY;
+		else
+			list_del(&timer->it.cpu.entry);
+
+		unlock_task_sighand(p, &flags);
 	}
 
+	if (!ret)
+		put_task_struct(p);
+
 	return ret;
 }
 
-static void cleanup_timers_list(struct list_head *head,
-				unsigned long long curr)
+static void cleanup_timers_list(struct list_head *head)
 {
 	struct cpu_timer_list *timer, *next;
 
@@ -414,16 +425,11 @@ static void cleanup_timers_list(struct list_head *head,
  * time for later timer_gettime calls to return.
  * This must be called with the siglock held.
  */
-static void cleanup_timers(struct list_head *head,
-			   cputime_t utime, cputime_t stime,
-			   unsigned long long sum_exec_runtime)
+static void cleanup_timers(struct list_head *head)
 {
-
-	cputime_t ptime = utime + stime;
-
-	cleanup_timers_list(head, cputime_to_expires(ptime));
-	cleanup_timers_list(++head, cputime_to_expires(utime));
-	cleanup_timers_list(++head, sum_exec_runtime);
+	cleanup_timers_list(head);
+	cleanup_timers_list(++head);
+	cleanup_timers_list(++head);
 }
 
 /*
@@ -433,41 +439,14 @@ static void cleanup_timers(struct list_head *head,
  */
 void posix_cpu_timers_exit(struct task_struct *tsk)
 {
-	cputime_t utime, stime;
-
 	add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
 						sizeof(unsigned long long));
-	task_cputime(tsk, &utime, &stime);
-	cleanup_timers(tsk->cpu_timers,
-		       utime, stime, tsk->se.sum_exec_runtime);
+	cleanup_timers(tsk->cpu_timers);
 
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	struct signal_struct *const sig = tsk->signal;
-	cputime_t utime, stime;
-
-	task_cputime(tsk, &utime, &stime);
-	cleanup_timers(tsk->signal->cpu_timers,
-		       utime + sig->utime, stime + sig->stime,
-		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
-}
-
-static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
-{
-	struct cpu_timer_list *timer = &itimer->it.cpu;
-
-	/*
-	 * That's all for this thread or process.
-	 * We leave our residual in expires to be reported.
-	 */
-	put_task_struct(timer->task);
-	timer->task = NULL;
-	if (timer->expires < now) {
-		timer->expires = 0;
-	} else {
-		timer->expires -= now;
-	}
+	cleanup_timers(tsk->signal->cpu_timers);
 }
 
 static inline int expires_gt(cputime_t expires, cputime_t new_exp)
@@ -477,8 +456,7 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 
 /*
  * Insert the timer on the appropriate list before any timers that
- * expire later.  This must be called with the tasklist_lock held
- * for reading, interrupts disabled and p->sighand->siglock taken.
+ * expire later.  This must be called with the sighand lock held.
  */
 static void arm_timer(struct k_itimer *timer)
 {
@@ -569,7 +547,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
 
 /*
  * Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
 static int cpu_timer_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
@@ -608,7 +587,8 @@ static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
  */
 static void posix_cpu_timer_kick_nohz(void)
 {
-	schedule_work(&nohz_kick_work);
+	if (context_tracking_is_enabled())
+		schedule_work(&nohz_kick_work);
 }
 
 bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
@@ -631,43 +611,39 @@ static inline void posix_cpu_timer_kick_nohz(void) { }
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			       struct itimerspec *new, struct itimerspec *old)
 {
+	unsigned long flags;
+	struct sighand_struct *sighand;
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long old_expires, new_expires, old_incr, val;
 	int ret;
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * Timer refers to a dead task's clock.
-		 */
-		return -ESRCH;
-	}
+	WARN_ON_ONCE(p == NULL);
 
 	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
 
-	read_lock(&tasklist_lock);
 	/*
-	 * We need the tasklist_lock to protect against reaping that
-	 * clears p->sighand.  If p has just been reaped, we can no
+	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
+	 * and p->signal->cpu_timers read/write in arm_timer()
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	/*
+	 * If p has just been reaped, we can no
 	 * longer get any information about it at all.
 	 */
-	if (unlikely(p->sighand == NULL)) {
-		read_unlock(&tasklist_lock);
-		put_task_struct(p);
-		timer->it.cpu.task = NULL;
+	if (unlikely(sighand == NULL)) {
 		return -ESRCH;
 	}
 
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
-	spin_lock(&p->sighand->siglock);
 	old_expires = timer->it.cpu.expires;
 	if (unlikely(timer->it.cpu.firing)) {
 		timer->it.cpu.firing = -1;
@@ -724,12 +700,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		 * disable this firing since we are already reporting
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
-		spin_unlock(&p->sighand->siglock);
-		read_unlock(&tasklist_lock);
+		unlock_task_sighand(p, &flags);
 		goto out;
 	}
 
-	if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
 		new_expires += val;
 	}
 
@@ -743,9 +718,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		arm_timer(timer);
 	}
 
-	spin_unlock(&p->sighand->siglock);
-	read_unlock(&tasklist_lock);
-
+	unlock_task_sighand(p, &flags);
 	/*
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
@@ -787,7 +760,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
 	unsigned long long now;
 	struct task_struct *p = timer->it.cpu.task;
-	int clear_dead;
+
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Easy part: convert the reload time.
@@ -800,52 +774,34 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 		return;
 	}
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * This task already died and the timer will never fire.
-		 * In this case, expires is actually the dead value.
-		 */
-	dead:
-		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
-				   &itp->it_value);
-		return;
-	}
-
 	/*
 	 * Sample the clock to take the difference with the expiry time.
 	 */
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
-		clear_dead = p->exit_state;
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
+		struct sighand_struct *sighand;
+		unsigned long flags;
+
+		/*
+		 * Protect against sighand release/switch in exit/exec and
+		 * also make timer sampling safe if it ends up calling
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 * Call the timer disarmed, nothing else to do.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = NULL;
 			timer->it.cpu.expires = 0;
-			read_unlock(&tasklist_lock);
-			goto dead;
+			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+					   &itp->it_value);
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
-			clear_dead = (unlikely(p->exit_state) &&
-				      thread_group_empty(p));
+			unlock_task_sighand(p, &flags);
 		}
-		read_unlock(&tasklist_lock);
-	}
-
-	if (unlikely(clear_dead)) {
-		/*
-		 * We've noticed that the thread is dead, but
-		 * not yet reaped.  Take this opportunity to
-		 * drop our task ref.
-		 */
-		clear_dead_task(timer, now);
-		goto dead;
 	}
 
 	if (now < timer->it.cpu.expires) {
@@ -1059,14 +1015,12 @@ static void check_process_timers(struct task_struct *tsk,
  */
 void posix_cpu_timer_schedule(struct k_itimer *timer)
 {
+	struct sighand_struct *sighand;
+	unsigned long flags;
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long now;
 
-	if (unlikely(p == NULL))
-		/*
-		 * The task was cleaned up already, no future firings.
-		 */
-		goto out;
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
@@ -1074,49 +1028,45 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		if (unlikely(p->exit_state)) {
-			clear_dead_task(timer, now);
+		if (unlikely(p->exit_state))
+			goto out;
+
+		/* Protect timer list r/w in arm_timer() */
+		sighand = lock_task_sighand(p, &flags);
+		if (!sighand)
 			goto out;
-		}
-		read_lock(&tasklist_lock); /* arm_timer needs it.  */
-		spin_lock(&p->sighand->siglock);
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
+		/*
+		 * Protect arm_timer() and timer sampling in case of call to
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = p = NULL;
 			timer->it.cpu.expires = 0;
-			goto out_unlock;
+			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
-			/*
-			 * We've noticed that the thread is dead, but
-			 * not yet reaped.  Take this opportunity to
-			 * drop our task ref.
-			 */
-			cpu_timer_sample_group(timer->it_clock, p, &now);
-			clear_dead_task(timer, now);
-			goto out_unlock;
+			unlock_task_sighand(p, &flags);
+			/* Optimizations: if the process is dying, no need to rearm */
+			goto out;
 		}
-		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		/* Leave the tasklist_lock locked for the call below.  */
+		/* Leave the sighand locked for the call below.  */
 	}
 
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 	arm_timer(timer);
-	spin_unlock(&p->sighand->siglock);
-
-out_unlock:
-	read_unlock(&tasklist_lock);
+	unlock_task_sighand(p, &flags);
 
+	/* Kick full dynticks CPUs in case they need to tick on the new timer */
+	posix_cpu_timer_kick_nohz();
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
@@ -1200,7 +1150,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	struct k_itimer *timer, *next;
 	unsigned long flags;
 
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	/*
 	 * The fast path checks that there are no expired thread or thread
@@ -1256,13 +1206,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 			cpu_timer_fire(timer);
 		spin_unlock(&timer->it_lock);
 	}
-
-	/*
-	 * In case some timers were rescheduled after the queue got emptied,
-	 * wake up full dynticks CPUs.
-	 */
-	if (tsk->signal->cputimer.running)
-		posix_cpu_timer_kick_nohz();
 }
 
 /*
@@ -1274,7 +1217,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 {
 	unsigned long long now;
 
-	BUG_ON(clock_idx == CPUCLOCK_SCHED);
+	WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7859a0a3951e..79c3877e9c5b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -96,19 +96,22 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-extern void kfree(const void *);
+void kfree(const void *);
 
 static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
 	unsigned long offset = (unsigned long)head->func;
 
+	rcu_lock_acquire(&rcu_callback_map);
 	if (__is_kfree_rcu_offset(offset)) {
 		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
 		kfree((void *)head - offset);
+		rcu_lock_release(&rcu_callback_map);
 		return 1;
 	} else {
 		RCU_TRACE(trace_rcu_invoke_callback(rn, head));
 		head->func(head);
+		rcu_lock_release(&rcu_callback_map);
 		return 0;
 	}
 }
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 01d5ccb8bfe3..3318d8284384 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -363,6 +363,29 @@ static void srcu_flip(struct srcu_struct *sp)
 /*
  * Enqueue an SRCU callback on the specified srcu_struct structure,
  * initiating grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section.  On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu().  It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
  */
 void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head))
@@ -459,7 +482,30 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  * Note that it is illegal to call synchronize_srcu() from the corresponding
  * SRCU read-side critical section; doing so will result in deadlock.
  * However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu().  In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section.  Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu().  This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
@@ -476,12 +522,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  * Wait for an SRCU grace period to elapse, but be more aggressive about
  * spinning rather than blocking when waiting.
  *
- * Note that it is also illegal to call synchronize_srcu_expedited()
- * from the corresponding SRCU read-side critical section;
- * doing so will result in deadlock.  However, it is perfectly legal
- * to call synchronize_srcu_expedited() on one srcu_struct from some
- * other srcu_struct's read-side critical section, as long as
- * the resulting graph of srcu_structs is acyclic.
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
  */
 void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
@@ -491,6 +533,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
 
 /**
  * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
  */
 void srcu_barrier(struct srcu_struct *sp)
 {
diff --git a/kernel/rcu/torture.c b/kernel/rcu/torture.c
index 3929cd451511..732f8ae3086a 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/torture.c
@@ -139,8 +139,6 @@ MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
 #define VERBOSE_PRINTK_ERRSTRING(s) \
 	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
 
-static char printk_buf[4096];
-
 static int nrealreaders;
 static struct task_struct *writer_task;
 static struct task_struct **fakewriter_tasks;
@@ -376,7 +374,7 @@ struct rcu_torture_ops {
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
-	int (*stats)(char *page);
+	void (*stats)(char *page);
 	int irq_capable;
 	int can_boost;
 	const char *name;
@@ -578,21 +576,19 @@ static void srcu_torture_barrier(void)
 	srcu_barrier(&srcu_ctl);
 }
 
-static int srcu_torture_stats(char *page)
+static void srcu_torture_stats(char *page)
 {
-	int cnt = 0;
 	int cpu;
 	int idx = srcu_ctl.completed & 0x1;
 
-	cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
+	page += sprintf(page, "%s%s per-CPU(idx=%d):",
 		       torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
-		cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
+		page += sprintf(page, " %d(%lu,%lu)", cpu,
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
 	}
-	cnt += sprintf(&page[cnt], "\n");
-	return cnt;
+	sprintf(page, "\n");
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -1052,10 +1048,9 @@ rcu_torture_reader(void *arg)
 /*
  * Create an RCU-torture statistics message in the specified buffer.
  */
-static int
+static void
 rcu_torture_printk(char *page)
 {
-	int cnt = 0;
 	int cpu;
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
@@ -1071,8 +1066,8 @@ rcu_torture_printk(char *page)
 		if (pipesummary[i] != 0)
 			break;
 	}
-	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt],
+	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page,
 		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
@@ -1080,53 +1075,52 @@ rcu_torture_printk(char *page)
 		       atomic_read(&n_rcu_torture_alloc),
 		       atomic_read(&n_rcu_torture_alloc_fail),
 		       atomic_read(&n_rcu_torture_free));
-	cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
+	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
 		       atomic_read(&n_rcu_torture_mberror),
 		       n_rcu_torture_boost_ktrerror,
 		       n_rcu_torture_boost_rterror);
-	cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
+	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
 		       n_rcu_torture_timers);
-	cnt += sprintf(&page[cnt],
+	page += sprintf(page,
 		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
 		       n_online_successes, n_online_attempts,
 		       n_offline_successes, n_offline_attempts,
 		       min_online, max_online,
 		       min_offline, max_offline,
 		       sum_online, sum_offline, HZ);
-	cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
+	page += sprintf(page, "barrier: %ld/%ld:%ld",
 		       n_barrier_successes,
 		       n_barrier_attempts,
 		       n_rcu_torture_barrier_error);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_barrier_error != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
 	    n_rcu_torture_boost_failure != 0 ||
 	    i > 1) {
-		cnt += sprintf(&page[cnt], "!!! ");
+		page += sprintf(page, "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(1);
 	}
-	cnt += sprintf(&page[cnt], "Reader Pipe: ");
+	page += sprintf(page, "Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		cnt += sprintf(&page[cnt], " %ld", pipesummary[i]);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt], "Reader Batch: ");
+		page += sprintf(page, " %ld", pipesummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Reader Batch: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		cnt += sprintf(&page[cnt], " %ld", batchsummary[i]);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt], "Free-Block Circulation: ");
+		page += sprintf(page, " %ld", batchsummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Free-Block Circulation: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-		cnt += sprintf(&page[cnt], " %d",
+		page += sprintf(page, " %d",
 			       atomic_read(&rcu_torture_wcount[i]));
 	}
-	cnt += sprintf(&page[cnt], "\n");
+	page += sprintf(page, "\n");
 	if (cur_ops->stats)
-		cnt += cur_ops->stats(&page[cnt]);
-	return cnt;
+		cur_ops->stats(page);
 }
 
 /*
@@ -1140,10 +1134,17 @@ rcu_torture_printk(char *page)
 static void
 rcu_torture_stats_print(void)
 {
-	int cnt;
+	int size = nr_cpu_ids * 200 + 8192;
+	char *buf;
 
-	cnt = rcu_torture_printk(printk_buf);
-	pr_alert("%s", printk_buf);
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		pr_err("rcu-torture: Out of memory, need: %d", size);
+		return;
+	}
+	rcu_torture_printk(buf);
+	pr_alert("%s", buf);
+	kfree(buf);
 }
 
 /*
@@ -1578,6 +1579,7 @@ static int rcu_torture_barrier_cbs(void *arg)
 {
 	long myid = (long)arg;
 	bool lastphase = 0;
+	bool newphase;
 	struct rcu_head rcu;
 
 	init_rcu_head_on_stack(&rcu);
@@ -1585,10 +1587,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 	set_user_nice(current, 19);
 	do {
 		wait_event(barrier_cbs_wq[myid],
-			   barrier_phase != lastphase ||
+			   (newphase =
+			    ACCESS_ONCE(barrier_phase)) != lastphase ||
 			   kthread_should_stop() ||
 			   fullstop != FULLSTOP_DONTSTOP);
-		lastphase = barrier_phase;
+		lastphase = newphase;
 		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
@@ -1625,7 +1628,7 @@ static int rcu_torture_barrier(void *arg)
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
 		n_barrier_attempts++;
-		cur_ops->cb_barrier();
+		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
 		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
 			n_rcu_torture_barrier_error++;
 			WARN_ON_ONCE(1);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd081987a8ec..b3d116cd072d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -369,6 +369,9 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 				bool user)
 {
+	struct rcu_state *rsp;
+	struct rcu_data *rdp;
+
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
@@ -380,6 +383,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		do_nocb_deferred_wakeup(rdp);
+	}
 	rcu_prepare_for_idle(smp_processor_id());
 	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
 	smp_mb__before_atomic_inc();  /* See above. */
@@ -411,11 +418,12 @@ static void rcu_eqs_enter(bool user)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
 		rdtp->dynticks_nesting = 0;
-	else
+		rcu_eqs_enter_common(rdtp, oldval, user);
+	} else {
 		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
-	rcu_eqs_enter_common(rdtp, oldval, user);
+	}
 }
 
 /**
@@ -533,11 +541,12 @@ static void rcu_eqs_exit(bool user)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(oldval < 0);
-	if (oldval & DYNTICK_TASK_NEST_MASK)
+	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
-	else
+	} else {
 		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-	rcu_eqs_exit_common(rdtp, oldval, user);
+		rcu_eqs_exit_common(rdtp, oldval, user);
+	}
 }
 
 /**
@@ -716,7 +725,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	bool ret;
 
 	if (in_nmi())
-		return 1;
+		return true;
 	preempt_disable();
 	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
@@ -755,6 +764,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 }
 
 /*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
+/*
  * 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()
@@ -812,16 +827,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 */
 	rcu_kick_nohz_cpu(rdp->cpu);
 
+	/*
+	 * Alternatively, the CPU might be running in the kernel
+	 * for an extended period of time without a quiescent state.
+	 * Attempt to force the CPU through the scheduler to gain the
+	 * needed quiescent state, but only if the grace period has gone
+	 * on for an uncommonly long time.  If there are many stuck CPUs,
+	 * we will beat on the first one until it gets unstuck, then move
+	 * to the next.  Only do this for the primary flavor of RCU.
+	 */
+	if (rdp->rsp == rcu_state &&
+	    ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+		rdp->rsp->jiffies_resched += 5;
+		resched_cpu(rdp->cpu);
+	}
+
 	return 0;
 }
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	unsigned long j = ACCESS_ONCE(jiffies);
+	unsigned long j1;
 
 	rsp->gp_start = j;
 	smp_wmb(); /* Record start time before stall time. */
-	rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
+	j1 = rcu_jiffies_till_stall_check();
+	rsp->jiffies_stall = j + j1;
+	rsp->jiffies_resched = j + j1 / 2;
 }
 
 /*
@@ -1133,8 +1166,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root)
+	if (rnp != rnp_root) {
 		raw_spin_lock(&rnp_root->lock);
+		smp_mb__after_unlock_lock();
+	}
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1354,6 +1389,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		local_irq_restore(flags);
 		return;
 	}
+	smp_mb__after_unlock_lock();
 	__note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1368,6 +1404,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	if (rsp->gp_flags == 0) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1409,6 +1446,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1501,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
@@ -1480,6 +1519,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1505,16 +1545,19 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			__note_gp_changes(rsp, rnp, rdp);
+		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1553,6 +1596,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			wait_event_interruptible(rsp->gp_wq,
 						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
+			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
 			cond_resched();
@@ -1582,6 +1626,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					(!ACCESS_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
+			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
 			if (!ACCESS_ONCE(rnp->qsmask) &&
 			    !rcu_preempt_blocked_readers_cgp(rnp))
@@ -1749,6 +1794,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
@@ -1778,6 +1824,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
 	    rnp->completed == rnp->gpnum) {
 
@@ -1901,13 +1948,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
  * Adopt the RCU callbacks from the specified rcu_state structure's
  * orphanage.  The caller must hold the ->orphan_lock.
  */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 {
 	int i;
 	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -1986,12 +2033,13 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
-	rcu_adopt_orphan_cbs(rsp);
+	rcu_adopt_orphan_cbs(rsp, flags);
 
 	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
 		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
 			if (rnp != rdp->mynode)
@@ -2202,6 +2250,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		cond_resched();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		if (!rcu_gp_in_progress(rsp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
@@ -2231,6 +2280,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rnp = rcu_get_root(rsp);
 	if (rnp->qsmask == 0) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 	}
 }
@@ -2263,6 +2313,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
+	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2303,6 +2354,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	/* If there are callbacks ready, invoke them. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
 		invoke_rcu_callbacks(rsp, rdp);
+
+	/* Do any needed deferred wakeups of rcuo kthreads. */
+	do_nocb_deferred_wakeup(rdp);
 }
 
 /*
@@ -2378,6 +2432,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
 			raw_spin_lock(&rnp_root->lock);
+			smp_mb__after_unlock_lock();
 			rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 		} else {
@@ -2437,7 +2492,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 
 		if (cpu != -1)
 			rdp = per_cpu_ptr(rsp->rda, cpu);
-		offline = !__call_rcu_nocb(rdp, head, lazy);
+		offline = !__call_rcu_nocb(rdp, head, lazy, flags);
 		WARN_ON_ONCE(offline);
 		/* _call_rcu() is illegal on offline CPU; leak the callback. */
 		local_irq_restore(flags);
@@ -2757,6 +2812,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* Check for CPU stalls, if enabled. */
 	check_cpu_stall(rsp, rdp);
 
+	/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
+	if (rcu_nohz_full_cpu(rsp))
+		return 0;
+
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
 	    rdp->qs_pending && !rdp->passed_quiesce) {
@@ -2790,6 +2849,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;
 	}
 
+	/* Does this CPU need a deferred NOCB wakeup? */
+	if (rcu_nocb_need_deferred_wakeup(rdp)) {
+		rdp->n_rp_nocb_defer_wakeup++;
+		return 1;
+	}
+
 	/* nothing to do */
 	rdp->n_rp_need_nothing++;
 	return 0;
@@ -3214,9 +3279,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
 	int i;
 
-	for (i = rcu_num_lvls - 1; i > 0; i--)
+	rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+	for (i = rcu_num_lvls - 2; i >= 0; i--)
 		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
-	rsp->levelspread[0] = rcu_fanout_leaf;
 }
 #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)
@@ -3346,6 +3411,8 @@ static void __init rcu_init_geometry(void)
 	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
+	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
+		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
 	 * Compute number of nodes that can be handled an rcu_node tree
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 52be957c9fe2..8c19873f1ac9 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -317,6 +317,7 @@ struct rcu_data {
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
 	unsigned long n_rp_gp_started;
+	unsigned long n_rp_nocb_defer_wakeup;
 	unsigned long n_rp_need_nothing;
 
 	/* 6) _rcu_barrier() and OOM callbacks. */
@@ -335,6 +336,7 @@ struct rcu_data {
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
+	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
@@ -453,6 +455,8 @@ struct rcu_state {
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
+	unsigned long jiffies_resched;		/* Time at which to resched */
+						/*  a reluctant CPU. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	const char *name;			/* Name of structure. */
@@ -548,9 +552,12 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy);
+			    bool lazy, unsigned long flags);
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-				      struct rcu_data *rdp);
+				      struct rcu_data *rdp,
+				      unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
 static void rcu_kick_nohz_cpu(int cpu);
@@ -564,6 +571,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 				  unsigned long maxj);
 static void rcu_bind_gp_kthread(void);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 08a765232432..6e2ef4b2b920 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
 		t->rcu_blocked_node = rnp;
 
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
 	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
 }
 
@@ -361,10 +363,14 @@ void rcu_read_unlock_special(struct task_struct *t)
 	special = t->rcu_read_unlock_special;
 	if (special & RCU_READ_UNLOCK_NEED_QS) {
 		rcu_preempt_qs(smp_processor_id());
+		if (!t->rcu_read_unlock_special) {
+			local_irq_restore(flags);
+			return;
+		}
 	}
 
-	/* Hardware IRQ handlers cannot block. */
-	if (in_irq() || in_serving_softirq()) {
+	/* Hardware IRQ handlers cannot block, complain if they get here. */
+	if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -381,6 +387,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		for (;;) {
 			rnp = t->rcu_blocked_node;
 			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
+			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +612,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	while (!list_empty(lp)) {
 		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
 		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		list_del(&t->rcu_node_entry);
 		t->rcu_blocked_node = rnp_root;
 		list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +637,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	 * in this case.
 	 */
 	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+	smp_mb__after_unlock_lock();
 	if (rnp_root->boost_tasks != NULL &&
 	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
 	    rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +781,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 	unsigned long mask;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	for (;;) {
 		if (!sync_rcu_preempt_exp_done(rnp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -779,14 +789,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			if (wake)
+			if (wake) {
+				smp_mb(); /* EGP done before wake_up(). */
 				wake_up(&sync_rcu_preempt_exp_wq);
+			}
 			break;
 		}
 		mask = rnp->grpmask;
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		rnp->expmask &= ~mask;
 	}
 }
@@ -806,6 +819,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 	int must_wait = 0;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (list_empty(&rnp->blkd_tasks)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
@@ -886,6 +900,7 @@ void synchronize_rcu_expedited(void)
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rnp->expmask = rnp->qsmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
@@ -1191,6 +1206,7 @@ static int rcu_boost(struct rcu_node *rnp)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1393,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_BOOST_PRIO;
@@ -1769,6 +1786,7 @@ static void rcu_prepare_for_idle(int cpu)
 			continue;
 		rnp = rdp->mynode;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
@@ -1852,6 +1870,7 @@ static int rcu_oom_notify(struct notifier_block *self,
 
 	/* Wait for callbacks from earlier instance to complete. */
 	wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+	smp_mb(); /* Ensure callback reuse happens after callback invocation. */
 
 	/*
 	 * Prevent premature wakeup: ensure that all increments happen
@@ -2101,7 +2120,8 @@ bool rcu_is_nocb_cpu(int cpu)
 static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 				    struct rcu_head *rhp,
 				    struct rcu_head **rhtp,
-				    int rhcount, int rhcount_lazy)
+				    int rhcount, int rhcount_lazy,
+				    unsigned long flags)
 {
 	int len;
 	struct rcu_head **old_rhpp;
@@ -2122,9 +2142,16 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	}
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
-		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+		if (!irqs_disabled_flags(flags)) {
+			wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmpty"));
+		} else {
+			rdp->nocb_defer_wakeup = true;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmptyIsDeferred"));
+		}
 		rdp->qlen_last_fqs_check = 0;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		wake_up_process(t); /* ... or if many callbacks queued. */
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2145,12 +2172,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
  * "rcuo" kthread can find it.
  */
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return 0;
-	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
 		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
 					 (unsigned long)rhp->func,
@@ -2168,7 +2195,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
  * not a no-CBs CPU.
  */
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	long ql = rsp->qlen;
 	long qll = rsp->qlen_lazy;
@@ -2182,14 +2210,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
 	if (rsp->orphan_donelist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
-					rsp->orphan_donetail, ql, qll);
+					rsp->orphan_donetail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_donelist = NULL;
 		rsp->orphan_donetail = &rsp->orphan_donelist;
 	}
 	if (rsp->orphan_nxtlist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
-					rsp->orphan_nxttail, ql, qll);
+					rsp->orphan_nxttail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_nxtlist = NULL;
 		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2209,6 +2237,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	c = rcu_start_future_gp(rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
@@ -2250,6 +2279,7 @@ static int rcu_nocb_kthread(void *arg)
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("Sleep"));
 			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+			/* Memory barrier provide by xchg() below. */
 		} else if (firsttime) {
 			firsttime = 0;
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
@@ -2310,6 +2340,22 @@ static int rcu_nocb_kthread(void *arg)
 	return 0;
 }
 
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+	if (!rcu_nocb_need_deferred_wakeup(rdp))
+		return;
+	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+	wake_up(&rdp->nocb_wq);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
@@ -2365,13 +2411,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
 }
 
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 	return 0;
 }
 
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	return 0;
 }
@@ -2380,6 +2427,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
 static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 }
@@ -2829,3 +2885,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
 }
 
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+/*
+ * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
+ * grace-period kthread will do force_quiescent_state() processing?
+ * The idea is to avoid waking up RCU core processing on such a
+ * CPU unless the grace period has extended for too long.
+ *
+ * This code relies on the fact that all NO_HZ_FULL CPUs are also
+ * CONFIG_RCU_NOCB_CPUs.
+ */
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_cpu(smp_processor_id()) &&
+	    (!rcu_gp_in_progress(rsp) ||
+	     ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
+		return 1;
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+	return 0;
+}
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3596797b7e46..4def475336d4 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp);
-	seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+	seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
 		   rdp->n_rp_gp_completed,
 		   rdp->n_rp_gp_started,
+		   rdp->n_rp_nocb_defer_wakeup,
 		   rdp->n_rp_need_nothing);
 }
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6cb3dff89e2b..802365ccd591 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -128,6 +128,11 @@ struct lockdep_map rcu_sched_lock_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 
+static struct lock_class_key rcu_callback_key;
+struct lockdep_map rcu_callback_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
+EXPORT_SYMBOL_GPL(rcu_callback_map);
+
 int notrace debug_lockdep_rcu_enabled(void)
 {
 	return rcu_scheduler_active && debug_locks &&
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index abc9a1a84d25..096d65e2d89e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2003,6 +2003,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (unlikely(prev_state == TASK_DEAD)) {
 		task_numa_free(prev);
 
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
@@ -2414,10 +2417,10 @@ static inline void schedule_debug(struct task_struct *prev)
 {
 	/*
 	 * Test if we are atomic. Since do_exit() needs to call into
-	 * schedule() atomically, we ignore that path for now.
-	 * Otherwise, whine if we are scheduling when we should not be.
+	 * schedule() atomically, we ignore that path. Otherwise whine
+	 * if we are scheduling when we should not.
 	 */
-	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+	if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
 		__schedule_bug(prev);
 	rcu_sleep_check();
 
@@ -3653,7 +3656,7 @@ again:
 	}
 
 	double_rq_lock(rq, p_rq);
-	while (task_rq(p) != p_rq) {
+	if (task_rq(p) != p_rq) {
 		double_rq_unlock(rq, p_rq);
 		goto again;
 	}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 5c34d1817e8f..374fe04a5e6e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -139,7 +139,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+	SEQ_printf(m, " %d", task_node(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c7395d97e4cb..b4ba00f51fd1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -872,15 +872,6 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
-/*
- * Once a preferred node is selected the scheduler balancer will prefer moving
- * a task to that node for sysctl_numa_balancing_settle_count number of PTE
- * scans. This will give the process the chance to accumulate more faults on
- * the preferred node but still allow the scheduler to move the task again if
- * the nodes CPUs are overloaded.
- */
-unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
-
 static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 {
 	rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -930,7 +921,8 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 	if (!p->numa_group)
 		return 0;
 
-	return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1];
+	return p->numa_group->faults[task_faults_idx(nid, 0)] +
+		p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
 /*
@@ -1023,7 +1015,7 @@ struct task_numa_env {
 
 	struct numa_stats src_stats, dst_stats;
 
-	int imbalance_pct, idx;
+	int imbalance_pct;
 
 	struct task_struct *best_task;
 	long best_imp;
@@ -1211,7 +1203,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 * elsewhere, so there is no point in (re)trying.
 	 */
 	if (unlikely(!sd)) {
-		p->numa_preferred_nid = cpu_to_node(task_cpu(p));
+		p->numa_preferred_nid = task_node(p);
 		return -EINVAL;
 	}
 
@@ -1278,7 +1270,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 	p->numa_migrate_retry = jiffies + HZ;
 
 	/* Success if task is already running on preferred CPU */
-	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+	if (task_node(p) == p->numa_preferred_nid)
 		return;
 
 	/* Otherwise, try migrate to a CPU on the preferred node */
@@ -1350,7 +1342,6 @@ static void update_task_scan_period(struct task_struct *p,
 		 * scanning faster if shared accesses dominate as it may
 		 * simply bounce migrations uselessly
 		 */
-		period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
 		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
 		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
 	}
@@ -4101,12 +4092,16 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
  */
 static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int load_idx)
+		  int this_cpu, int sd_flag)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
 	unsigned long min_load = ULONG_MAX, this_load = 0;
+	int load_idx = sd->forkexec_idx;
 	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
+	if (sd_flag & SD_BALANCE_WAKE)
+		load_idx = sd->wake_idx;
+
 	do {
 		unsigned long load, avg_load;
 		int local_group;
@@ -4274,7 +4269,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	}
 
 	while (sd) {
-		int load_idx = sd->forkexec_idx;
 		struct sched_group *group;
 		int weight;
 
@@ -4283,10 +4277,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			continue;
 		}
 
-		if (sd_flag & SD_BALANCE_WAKE)
-			load_idx = sd->wake_idx;
-
-		group = find_idlest_group(sd, p, cpu, load_idx);
+		group = find_idlest_group(sd, p, cpu, sd_flag);
 		if (!group) {
 			sd = sd->child;
 			continue;
@@ -5512,7 +5503,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
 			int local_group, struct sg_lb_stats *sgs)
 {
-	unsigned long nr_running;
 	unsigned long load;
 	int i;
 
@@ -5521,8 +5511,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
-		nr_running = rq->nr_running;
-
 		/* Bias balancing toward cpus of our domain */
 		if (local_group)
 			load = target_load(i, load_idx);
@@ -5530,7 +5518,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
-		sgs->sum_nr_running += nr_running;
+		sgs->sum_nr_running += rq->nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
 		sgs->nr_preferred_running += rq->nr_preferred_running;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 88c85b21d633..b3b4a4953efc 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1023,6 +1023,7 @@ struct sched_class {
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork) (struct task_struct *p);
+	void (*task_dead) (struct task_struct *p);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025ccc06dd..937aa1f240c2 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -211,14 +211,48 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+	bool in_hardirq = false;
+
+	if (trace_hardirq_context(current)) {
+		in_hardirq = true;
+		trace_hardirq_exit();
+	}
+
+	lockdep_softirq_enter();
+
+	return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+	lockdep_softirq_exit();
+
+	if (in_hardirq)
+		trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
-	struct softirq_action *h;
-	__u32 pending;
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
-	int cpu;
 	unsigned long old_flags = current->flags;
 	int max_restart = MAX_SOFTIRQ_RESTART;
+	struct softirq_action *h;
+	bool in_hardirq;
+	__u32 pending;
+	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -231,7 +265,7 @@ asmlinkage void __do_softirq(void)
 	account_irq_enter_time(current);
 
 	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+	in_hardirq = lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -278,16 +312,13 @@ restart:
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_exit();
-
+	lockdep_softirq_end(in_hardirq);
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-
-
 asmlinkage void do_softirq(void)
 {
 	__u32 pending;
@@ -311,8 +342,6 @@ asmlinkage void do_softirq(void)
  */
 void irq_enter(void)
 {
-	int cpu = smp_processor_id();
-
 	rcu_irq_enter();
 	if (is_idle_task(current) && !in_interrupt()) {
 		/*
@@ -320,7 +349,7 @@ void irq_enter(void)
 		 * here, as softirq will be serviced on return from interrupt.
 		 */
 		local_bh_disable();
-		tick_check_idle(cpu);
+		tick_check_idle();
 		_local_bh_enable();
 	}
 
@@ -375,13 +404,13 @@ void irq_exit(void)
 #endif
 
 	account_irq_exit_time(current);
-	trace_hardirq_exit();
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
 	tick_irq_exit();
 	rcu_irq_exit();
+	trace_hardirq_exit(); /* must be last! */
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 34a604726d0b..c8da99f905cf 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -385,13 +385,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname       = "numa_balancing_settle_count",
-		.data           = &sysctl_numa_balancing_settle_count,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-	{
 		.procname       = "numa_balancing_migrate_deferred",
 		.data           = &sysctl_numa_balancing_migrate_deferred,
 		.maxlen         = sizeof(unsigned int),
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9532690daaa9..43780ab5e279 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -538,10 +538,10 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
  * Called from irq_enter() when idle was interrupted to reenable the
  * per cpu device.
  */
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
 {
-	if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
-		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+	if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+		struct tick_device *td = &__get_cpu_var(tick_cpu_device);
 
 		/*
 		 * We might be in the middle of switching over from
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 18e71f7fbc2a..e2bced59b6dd 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -51,7 +51,7 @@ extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
@@ -62,7 +62,7 @@ static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return true; }
 # endif /* !BROADCAST */
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index ea20f7d1ac2c..52cee12b3302 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -391,11 +391,9 @@ __setup("nohz=", setup_tick_nohz);
  */
 static void tick_nohz_update_jiffies(ktime_t now)
 {
-	int cpu = smp_processor_id();
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	unsigned long flags;
 
-	ts->idle_waketime = now;
+	__this_cpu_write(tick_cpu_sched.idle_waketime, now);
 
 	local_irq_save(flags);
 	tick_do_update_jiffies64(now);
@@ -426,17 +424,15 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
 
 }
 
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
-	update_ts_time_stats(cpu, ts, now, NULL);
+	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
 
 	sched_clock_idle_wakeup_event(0);
 }
 
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
 	ktime_t now = ktime_get();
 
@@ -754,7 +750,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 	ktime_t now, expires;
 	int cpu = smp_processor_id();
 
-	now = tick_nohz_start_idle(cpu, ts);
+	now = tick_nohz_start_idle(ts);
 
 	if (can_stop_idle_tick(cpu, ts)) {
 		int was_stopped = ts->tick_stopped;
@@ -911,8 +907,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
  */
 void tick_nohz_idle_exit(void)
 {
-	int cpu = smp_processor_id();
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t now;
 
 	local_irq_disable();
@@ -925,7 +920,7 @@ void tick_nohz_idle_exit(void)
 		now = ktime_get();
 
 	if (ts->idle_active)
-		tick_nohz_stop_idle(cpu, now);
+		tick_nohz_stop_idle(ts, now);
 
 	if (ts->tick_stopped) {
 		tick_nohz_restart_sched_tick(ts, now);
@@ -1009,12 +1004,10 @@ static void tick_nohz_switch_to_nohz(void)
  * timer and do not touch the other magic bits which need to be done
  * when idle is left.
  */
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
 {
 #if 0
 	/* Switch back to 2.6.27 behaviour */
-
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t delta;
 
 	/*
@@ -1029,36 +1022,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
 #endif
 }
 
-static inline void tick_check_nohz(int cpu)
+static inline void tick_check_nohz_this_cpu(void)
 {
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t now;
 
 	if (!ts->idle_active && !ts->tick_stopped)
 		return;
 	now = ktime_get();
 	if (ts->idle_active)
-		tick_nohz_stop_idle(cpu, now);
+		tick_nohz_stop_idle(ts, now);
 	if (ts->tick_stopped) {
 		tick_nohz_update_jiffies(now);
-		tick_nohz_kick_tick(cpu, now);
+		tick_nohz_kick_tick(ts, now);
 	}
 }
 
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_check_nohz_this_cpu(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
  * Called from irq_enter to notify about the possible interruption of idle()
  */
-void tick_check_idle(int cpu)
+void tick_check_idle(void)
 {
-	tick_check_oneshot_broadcast(cpu);
-	tick_check_nohz(cpu);
+	tick_check_oneshot_broadcast_this_cpu();
+	tick_check_nohz_this_cpu();
 }
 
 /*
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index db25707aa41b..6982094a7e74 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -761,6 +761,15 @@ config PANIC_ON_OOPS_VALUE
 	default 0 if !PANIC_ON_OOPS
 	default 1 if PANIC_ON_OOPS
 
+config PANIC_TIMEOUT
+	int "panic timeout"
+	default 0
+	help
+	  Set the timeout value (in seconds) until a reboot occurs when the
+	  the kernel panics. If n = 0, then we wait forever. A timeout
+	  value n > 0 will wait n seconds before rebooting, while a timeout
+	  value n < 0 will reboot immediately.
+
 config SCHED_DEBUG
 	bool "Collect scheduler debugging info"
 	depends on DEBUG_KERNEL && PROC_FS
diff --git a/tools/Makefile b/tools/Makefile
index a9b02008443c..927cd46d36dc 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -39,10 +39,10 @@ cpupower: FORCE
 cgroup firewire guest usb virtio vm net: FORCE
 	$(call descend,$@)
 
-liblk: FORCE
-	$(call descend,lib/lk)
+libapikfs: FORCE
+	$(call descend,lib/api)
 
-perf: liblk FORCE
+perf: libapikfs FORCE
 	$(call descend,$@)
 
 selftests: FORCE
@@ -80,10 +80,10 @@ cpupower_clean:
 cgroup_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean:
 	$(call descend,$(@:_clean=),clean)
 
-liblk_clean:
-	$(call descend,lib/lk,clean)
+libapikfs_clean:
+	$(call descend,lib/api,clean)
 
-perf_clean: liblk_clean
+perf_clean: libapikfs_clean
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
diff --git a/tools/lib/lk/Makefile b/tools/lib/api/Makefile
index 3dba0a4aebbf..ed2f51e11b80 100644
--- a/tools/lib/lk/Makefile
+++ b/tools/lib/api/Makefile
@@ -1,4 +1,5 @@
 include ../../scripts/Makefile.include
+include ../../perf/config/utilities.mak		# QUIET_CLEAN
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
@@ -7,11 +8,11 @@ AR = $(CROSS_COMPILE)ar
 LIB_H=
 LIB_OBJS=
 
-LIB_H += debugfs.h
+LIB_H += fs/debugfs.h
 
-LIB_OBJS += $(OUTPUT)debugfs.o
+LIB_OBJS += $(OUTPUT)fs/debugfs.o
 
-LIBFILE = liblk.a
+LIBFILE = libapikfs.a
 
 CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
 EXTLIBS = -lelf -lpthread -lrt -lm
@@ -25,14 +26,17 @@ $(LIBFILE): $(LIB_OBJS)
 
 $(LIB_OBJS): $(LIB_H)
 
-$(OUTPUT)%.o: %.c
+libapi_dirs:
+	$(QUIET_MKDIR)mkdir -p $(OUTPUT)fs/
+
+$(OUTPUT)%.o: %.c libapi_dirs
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-$(OUTPUT)%.s: %.c
+$(OUTPUT)%.s: %.c libapi_dirs
 	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-$(OUTPUT)%.o: %.S
+$(OUTPUT)%.o: %.S libapi_dirs
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
 
 clean:
-	$(RM) $(LIB_OBJS) $(LIBFILE)
+	$(call QUIET_CLEAN, libapi) $(RM) $(LIB_OBJS) $(LIBFILE)
 
 .PHONY: clean
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/api/fs/debugfs.c
index 7c4347962353..7c4347962353 100644
--- a/tools/lib/lk/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
diff --git a/tools/lib/lk/debugfs.h b/tools/lib/api/fs/debugfs.h
index 935c59bdb442..f19d3df9609d 100644
--- a/tools/lib/lk/debugfs.h
+++ b/tools/lib/api/fs/debugfs.h
@@ -1,5 +1,5 @@
-#ifndef __LK_DEBUGFS_H__
-#define __LK_DEBUGFS_H__
+#ifndef __API_DEBUGFS_H__
+#define __API_DEBUGFS_H__
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -26,4 +26,4 @@ char *debugfs_mount(const char *mountpoint);
 
 extern char debugfs_mountpoint[];
 
-#endif /* __LK_DEBUGFS_H__ */
+#endif /* __API_DEBUGFS_H__ */
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
new file mode 100644
index 000000000000..da8b7aa3d351
--- /dev/null
+++ b/tools/lib/lockdep/Makefile
@@ -0,0 +1,251 @@
+# liblockdep version
+LL_VERSION = 0
+LL_PATCHLEVEL = 0
+LL_EXTRAVERSION = 1
+
+# file format version
+FILE_VERSION = 1
+
+MAKEFLAGS += --no-print-directory
+
+
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+prefix ?= /usr/local
+libdir_relative = lib
+libdir = $(prefix)/$(libdir_relative)
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+
+export DESTDIR DESTDIR_SQ INSTALL
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+  VERBOSE = $(V)
+endif
+ifndef VERBOSE
+  VERBOSE = 0
+endif
+
+ifeq ("$(origin O)", "command line")
+  BUILD_OUTPUT := $(O)
+endif
+
+ifeq ($(BUILD_SRC),)
+ifneq ($(BUILD_OUTPUT),)
+
+define build_output
+	$(if $(VERBOSE:1=),@)$(MAKE) -C $(BUILD_OUTPUT)	\
+	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
+endef
+
+saved-output := $(BUILD_OUTPUT)
+BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
+$(if $(BUILD_OUTPUT),, \
+     $(error output directory "$(saved-output)" does not exist))
+
+all: sub-make
+
+gui: force
+	$(call build_output, all_cmd)
+
+$(filter-out gui,$(MAKECMDGOALS)): sub-make
+
+sub-make: force
+	$(call build_output, $(MAKECMDGOALS))
+
+
+# Leave processing to above invocation of make
+skip-makefile := 1
+
+endif # BUILD_OUTPUT
+endif # BUILD_SRC
+
+# We process the rest of the Makefile if this is the final invocation of make
+ifeq ($(skip-makefile),)
+
+srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
+objtree		:= $(CURDIR)
+src		:= $(srctree)
+obj		:= $(objtree)
+
+export prefix libdir bindir src obj
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+bindir_SQ = $(subst ','\'',$(bindir))
+
+LIB_FILE = liblockdep.a liblockdep.so
+BIN_FILE = lockdep
+
+CONFIG_INCLUDES =
+CONFIG_LIBS	=
+CONFIG_FLAGS	=
+
+OBJ		= $@
+N		=
+
+export Q VERBOSE
+
+LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION)
+
+INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES)
+
+# Set compile option CFLAGS if not set elsewhere
+CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
+
+override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
+
+ifeq ($(VERBOSE),1)
+  Q =
+  print_compile =
+  print_app_build =
+  print_fpic_compile =
+  print_shared_lib_compile =
+  print_install =
+else
+  Q = @
+  print_compile =		echo '  CC                 '$(OBJ);
+  print_app_build =		echo '  BUILD              '$(OBJ);
+  print_fpic_compile =		echo '  CC FPIC            '$(OBJ);
+  print_shared_lib_compile =	echo '  BUILD SHARED LIB   '$(OBJ);
+  print_static_lib_build =	echo '  BUILD STATIC LIB   '$(OBJ);
+  print_install =		echo '  INSTALL     '$1'	to	$(DESTDIR_SQ)$2';
+endif
+
+do_fpic_compile =					\
+	($(print_fpic_compile)				\
+	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
+
+do_app_build =						\
+	($(print_app_build)				\
+	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
+
+do_compile_shared_library =			\
+	($(print_shared_lib_compile)		\
+	$(CC) --shared $^ -o $@ -lpthread -ldl)
+
+do_build_static_lib =				\
+	($(print_static_lib_build)		\
+	$(RM) $@;  $(AR) rcs $@ $^)
+
+
+define do_compile
+	$(print_compile)						\
+	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
+endef
+
+$(obj)/%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+PEVENT_LIB_OBJS = common.o lockdep.o preload.o rbtree.o
+
+ALL_OBJS = $(PEVENT_LIB_OBJS)
+
+CMD_TARGETS = $(LIB_FILE)
+
+TARGETS = $(CMD_TARGETS)
+
+
+all: all_cmd
+
+all_cmd: $(CMD_TARGETS)
+
+liblockdep.so: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_compile_shared_library)
+
+liblockdep.a: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_build_static_lib)
+
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
+	$(Q)$(do_fpic_compile)
+
+## make deps
+
+all_objs := $(sort $(ALL_OBJS))
+all_deps := $(all_objs:%.o=.%.d)
+
+# let .d file also depends on the source and header files
+define check_deps
+		@set -e; $(RM) $@; \
+		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+		$(RM) $@.$$$$
+endef
+
+$(all_deps): .%.d: $(src)/%.c
+	$(Q)$(call check_deps)
+
+$(all_objs) : %.o : .%.d
+
+dep_includes := $(wildcard $(all_deps))
+
+ifneq ($(dep_includes),)
+ include $(dep_includes)
+endif
+
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+tags:	force
+	$(RM) tags
+	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
+
+TAGS:	force
+	$(RM) TAGS
+	find . -name '*.[ch]' | xargs etags \
+	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+
+define do_install
+	$(print_install)				\
+	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
+	fi;						\
+	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: all_cmd
+	$(Q)$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(Q)$(call do_install,$(BIN_FILE),$(bindir_SQ))
+
+install: install_lib
+
+clean:
+	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) tags TAGS
+
+endif # skip-makefile
+
+PHONY += force
+force:
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
new file mode 100644
index 000000000000..8ef602f18a32
--- /dev/null
+++ b/tools/lib/lockdep/common.c
@@ -0,0 +1,33 @@
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/compiler.h>
+#include <linux/lockdep.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+static __thread struct task_struct current_obj;
+
+/* lockdep wants these */
+bool debug_locks = true;
+bool debug_locks_silent;
+
+__attribute__((constructor)) static void liblockdep_init(void)
+{
+	lockdep_init();
+}
+
+__attribute__((destructor)) static void liblockdep_exit(void)
+{
+	debug_check_no_locks_held(&current_obj);
+}
+
+struct task_struct *__curr(void)
+{
+	if (current_obj.pid == 0) {
+		/* Makes lockdep output pretty */
+		prctl(PR_GET_NAME, current_obj.comm);
+		current_obj.pid = syscall(__NR_gettid);
+	}
+
+	return &current_obj;
+}
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
new file mode 100644
index 000000000000..0bda630027c3
--- /dev/null
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -0,0 +1,50 @@
+#ifndef _LIBLOCKDEP_COMMON_H
+#define _LIBLOCKDEP_COMMON_H
+
+#include <pthread.h>
+
+#define NR_LOCKDEP_CACHING_CLASSES 2
+#define MAX_LOCKDEP_SUBCLASSES 8UL
+
+#ifndef CALLER_ADDR0
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#endif
+
+#ifndef _RET_IP_
+#define _RET_IP_ CALLER_ADDR0
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
+
+struct lockdep_subclass_key {
+	char __one_byte;
+};
+
+struct lock_class_key {
+	struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES];
+};
+
+struct lockdep_map {
+	struct lock_class_key	*key;
+	struct lock_class	*class_cache[NR_LOCKDEP_CACHING_CLASSES];
+	const char		*name;
+#ifdef CONFIG_LOCK_STAT
+	int			cpu;
+	unsigned long		ip;
+#endif
+};
+
+void lockdep_init_map(struct lockdep_map *lock, const char *name,
+			struct lock_class_key *key, int subclass);
+void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
+			int trylock, int read, int check,
+			struct lockdep_map *nest_lock, unsigned long ip);
+void lock_release(struct lockdep_map *lock, int nested,
+			unsigned long ip);
+
+#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .name = (_name), .key = (void *)(_key), }
+
+#endif
diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
new file mode 100644
index 000000000000..c342f7087147
--- /dev/null
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -0,0 +1,70 @@
+#ifndef _LIBLOCKDEP_MUTEX_H
+#define _LIBLOCKDEP_MUTEX_H
+
+#include <pthread.h>
+#include "common.h"
+
+struct liblockdep_pthread_mutex {
+	pthread_mutex_t mutex;
+	struct lockdep_map dep_map;
+};
+
+typedef struct liblockdep_pthread_mutex liblockdep_pthread_mutex_t;
+
+#define LIBLOCKDEP_PTHREAD_MUTEX_INITIALIZER(mtx)			\
+		(const struct liblockdep_pthread_mutex) {		\
+	.mutex = PTHREAD_MUTEX_INITIALIZER,				\
+	.dep_map = STATIC_LOCKDEP_MAP_INIT(#mtx, &((&(mtx))->dep_map)),	\
+}
+
+static inline int __mutex_init(liblockdep_pthread_mutex_t *lock,
+				const char *name,
+				struct lock_class_key *key,
+				const pthread_mutexattr_t *__mutexattr)
+{
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+	return pthread_mutex_init(&lock->mutex, __mutexattr);
+}
+
+#define liblockdep_pthread_mutex_init(mutex, mutexattr)		\
+({								\
+	static struct lock_class_key __key;			\
+								\
+	__mutex_init((mutex), #mutex, &__key, (mutexattr));	\
+})
+
+static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_mutex_lock(&lock->mutex);
+}
+
+static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	return pthread_mutex_unlock(&lock->mutex);
+}
+
+static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_pthread_mutex_destroy(liblockdep_pthread_mutex_t *lock)
+{
+	return pthread_mutex_destroy(&lock->mutex);
+}
+
+#ifdef __USE_LIBLOCKDEP
+
+#define pthread_mutex_t         liblockdep_pthread_mutex_t
+#define pthread_mutex_init      liblockdep_pthread_mutex_init
+#define pthread_mutex_lock      liblockdep_pthread_mutex_lock
+#define pthread_mutex_unlock    liblockdep_pthread_mutex_unlock
+#define pthread_mutex_trylock   liblockdep_pthread_mutex_trylock
+#define pthread_mutex_destroy   liblockdep_pthread_mutex_destroy
+
+#endif
+
+#endif
diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
new file mode 100644
index 000000000000..a680ab8c2e36
--- /dev/null
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -0,0 +1,86 @@
+#ifndef _LIBLOCKDEP_RWLOCK_H
+#define _LIBLOCKDEP_RWLOCK_H
+
+#include <pthread.h>
+#include "common.h"
+
+struct liblockdep_pthread_rwlock {
+	pthread_rwlock_t rwlock;
+	struct lockdep_map dep_map;
+};
+
+typedef struct liblockdep_pthread_rwlock liblockdep_pthread_rwlock_t;
+
+#define LIBLOCKDEP_PTHREAD_RWLOCK_INITIALIZER(rwl)			\
+		(struct liblockdep_pthread_rwlock) {			\
+	.rwlock = PTHREAD_RWLOCK_INITIALIZER,				\
+	.dep_map = STATIC_LOCKDEP_MAP_INIT(#rwl, &((&(rwl))->dep_map)),	\
+}
+
+static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock,
+				const char *name,
+				struct lock_class_key *key,
+				const pthread_rwlockattr_t *attr)
+{
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+
+	return pthread_rwlock_init(&lock->rwlock, attr);
+}
+
+#define liblockdep_pthread_rwlock_init(lock, attr)		\
+({							\
+	static struct lock_class_key __key;		\
+							\
+	__rwlock_init((lock), #lock, &__key, (attr));	\
+})
+
+static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_rdlock(&lock->rwlock);
+
+}
+
+static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	return pthread_rwlock_unlock(&lock->rwlock);
+}
+
+static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_wrlock(&lock->rwlock);
+}
+
+static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_rwlock_destroy(liblockdep_pthread_rwlock_t *lock)
+{
+	return pthread_rwlock_destroy(&lock->rwlock);
+}
+
+#ifdef __USE_LIBLOCKDEP
+
+#define pthread_rwlock_t		liblockdep_pthread_rwlock_t
+#define pthread_rwlock_init		liblockdep_pthread_rwlock_init
+#define pthread_rwlock_rdlock		liblockdep_pthread_rwlock_rdlock
+#define pthread_rwlock_unlock		liblockdep_pthread_rwlock_unlock
+#define pthread_rwlock_wrlock		liblockdep_pthread_rwlock_wrlock
+#define pthread_rwlock_tryrdlock	liblockdep_pthread_rwlock_tryrdlock
+#define pthread_rwlock_trywlock		liblockdep_pthread_rwlock_trywlock
+#define pthread_rwlock_destroy		liblockdep_rwlock_destroy
+
+#endif
+
+#endif
diff --git a/tools/lib/lockdep/lockdep b/tools/lib/lockdep/lockdep
new file mode 100755
index 000000000000..49af9fe19f5b
--- /dev/null
+++ b/tools/lib/lockdep/lockdep
@@ -0,0 +1,3 @@
+#!/bin/bash
+
+LD_PRELOAD="./liblockdep.so $LD_PRELOAD" "$@"
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
new file mode 100644
index 000000000000..f42b7e9aa48f
--- /dev/null
+++ b/tools/lib/lockdep/lockdep.c
@@ -0,0 +1,2 @@
+#include <linux/lockdep.h>
+#include "../../../kernel/locking/lockdep.c"
diff --git a/tools/lib/lockdep/lockdep_internals.h b/tools/lib/lockdep/lockdep_internals.h
new file mode 100644
index 000000000000..29d0c954cc24
--- /dev/null
+++ b/tools/lib/lockdep/lockdep_internals.h
@@ -0,0 +1 @@
+#include "../../../kernel/locking/lockdep_internals.h"
diff --git a/tools/lib/lockdep/lockdep_states.h b/tools/lib/lockdep/lockdep_states.h
new file mode 100644
index 000000000000..248d235efda9
--- /dev/null
+++ b/tools/lib/lockdep/lockdep_states.h
@@ -0,0 +1 @@
+#include "../../../kernel/locking/lockdep_states.h"
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
new file mode 100644
index 000000000000..f8465a811aa5
--- /dev/null
+++ b/tools/lib/lockdep/preload.c
@@ -0,0 +1,447 @@
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <stdio.h>
+#include <dlfcn.h>
+#include <stdlib.h>
+#include <sysexits.h>
+#include "include/liblockdep/mutex.h"
+#include "../../../include/linux/rbtree.h"
+
+/**
+ * struct lock_lookup - liblockdep's view of a single unique lock
+ * @orig: pointer to the original pthread lock, used for lookups
+ * @dep_map: lockdep's dep_map structure
+ * @key: lockdep's key structure
+ * @node: rb-tree node used to store the lock in a global tree
+ * @name: a unique name for the lock
+ */
+struct lock_lookup {
+	void *orig; /* Original pthread lock, used for lookups */
+	struct lockdep_map dep_map; /* Since all locks are dynamic, we need
+				     * a dep_map and a key for each lock */
+	/*
+	 * Wait, there's no support for key classes? Yup :(
+	 * Most big projects wrap the pthread api with their own calls to
+	 * be compatible with different locking methods. This means that
+	 * "classes" will be brokes since the function that creates all
+	 * locks will point to a generic locking function instead of the
+	 * actual code that wants to do the locking.
+	 */
+	struct lock_class_key key;
+	struct rb_node node;
+#define LIBLOCKDEP_MAX_LOCK_NAME 22
+	char name[LIBLOCKDEP_MAX_LOCK_NAME];
+};
+
+/* This is where we store our locks */
+static struct rb_root locks = RB_ROOT;
+static pthread_rwlock_t locks_rwlock = PTHREAD_RWLOCK_INITIALIZER;
+
+/* pthread mutex API */
+
+#ifdef __GLIBC__
+extern int __pthread_mutex_init(pthread_mutex_t *mutex, const pthread_mutexattr_t *attr);
+extern int __pthread_mutex_lock(pthread_mutex_t *mutex);
+extern int __pthread_mutex_trylock(pthread_mutex_t *mutex);
+extern int __pthread_mutex_unlock(pthread_mutex_t *mutex);
+extern int __pthread_mutex_destroy(pthread_mutex_t *mutex);
+#else
+#define __pthread_mutex_init	NULL
+#define __pthread_mutex_lock	NULL
+#define __pthread_mutex_trylock	NULL
+#define __pthread_mutex_unlock	NULL
+#define __pthread_mutex_destroy	NULL
+#endif
+static int (*ll_pthread_mutex_init)(pthread_mutex_t *mutex,
+			const pthread_mutexattr_t *attr)	= __pthread_mutex_init;
+static int (*ll_pthread_mutex_lock)(pthread_mutex_t *mutex)	= __pthread_mutex_lock;
+static int (*ll_pthread_mutex_trylock)(pthread_mutex_t *mutex)	= __pthread_mutex_trylock;
+static int (*ll_pthread_mutex_unlock)(pthread_mutex_t *mutex)	= __pthread_mutex_unlock;
+static int (*ll_pthread_mutex_destroy)(pthread_mutex_t *mutex)	= __pthread_mutex_destroy;
+
+/* pthread rwlock API */
+
+#ifdef __GLIBC__
+extern int __pthread_rwlock_init(pthread_rwlock_t *rwlock, const pthread_rwlockattr_t *attr);
+extern int __pthread_rwlock_destroy(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_wrlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_rdlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_unlock(pthread_rwlock_t *rwlock);
+#else
+#define __pthread_rwlock_init		NULL
+#define __pthread_rwlock_destroy	NULL
+#define __pthread_rwlock_wrlock		NULL
+#define __pthread_rwlock_trywrlock	NULL
+#define __pthread_rwlock_rdlock		NULL
+#define __pthread_rwlock_tryrdlock	NULL
+#define __pthread_rwlock_unlock		NULL
+#endif
+
+static int (*ll_pthread_rwlock_init)(pthread_rwlock_t *rwlock,
+			const pthread_rwlockattr_t *attr)		= __pthread_rwlock_init;
+static int (*ll_pthread_rwlock_destroy)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_destroy;
+static int (*ll_pthread_rwlock_rdlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_rdlock;
+static int (*ll_pthread_rwlock_tryrdlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_tryrdlock;
+static int (*ll_pthread_rwlock_trywrlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_trywrlock;
+static int (*ll_pthread_rwlock_wrlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_wrlock;
+static int (*ll_pthread_rwlock_unlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_unlock;
+
+enum { none, prepare, done, } __init_state;
+static void init_preload(void);
+static void try_init_preload(void)
+{
+	if (!__init_state != done)
+		init_preload();
+}
+
+static struct rb_node **__get_lock_node(void *lock, struct rb_node **parent)
+{
+	struct rb_node **node = &locks.rb_node;
+	struct lock_lookup *l;
+
+	*parent = NULL;
+
+	while (*node) {
+		l = rb_entry(*node, struct lock_lookup, node);
+
+		*parent = *node;
+		if (lock < l->orig)
+			node = &l->node.rb_left;
+		else if (lock > l->orig)
+			node = &l->node.rb_right;
+		else
+			return node;
+	}
+
+	return node;
+}
+
+#ifndef LIBLOCKDEP_STATIC_ENTRIES
+#define LIBLOCKDEP_STATIC_ENTRIES	1024
+#endif
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static struct lock_lookup __locks[LIBLOCKDEP_STATIC_ENTRIES];
+static int __locks_nr;
+
+static inline bool is_static_lock(struct lock_lookup *lock)
+{
+	return lock >= __locks && lock < __locks + ARRAY_SIZE(__locks);
+}
+
+static struct lock_lookup *alloc_lock(void)
+{
+	if (__init_state != done) {
+		/*
+		 * Some programs attempt to initialize and use locks in their
+		 * allocation path. This means that a call to malloc() would
+		 * result in locks being initialized and locked.
+		 *
+		 * Why is it an issue for us? dlsym() below will try allocating
+		 * to give us the original function. Since this allocation will
+		 * result in a locking operations, we have to let pthread deal
+		 * with it, but we can't! we don't have the pointer to the
+		 * original API since we're inside dlsym() trying to get it
+		 */
+
+		int idx = __locks_nr++;
+		if (idx >= ARRAY_SIZE(__locks)) {
+			fprintf(stderr,
+		"LOCKDEP error: insufficient LIBLOCKDEP_STATIC_ENTRIES\n");
+			exit(EX_UNAVAILABLE);
+		}
+		return __locks + idx;
+	}
+
+	return malloc(sizeof(struct lock_lookup));
+}
+
+static inline void free_lock(struct lock_lookup *lock)
+{
+	if (likely(!is_static_lock(lock)))
+		free(lock);
+}
+
+/**
+ * __get_lock - find or create a lock instance
+ * @lock: pointer to a pthread lock function
+ *
+ * Try to find an existing lock in the rbtree using the provided pointer. If
+ * one wasn't found - create it.
+ */
+static struct lock_lookup *__get_lock(void *lock)
+{
+	struct rb_node **node, *parent;
+	struct lock_lookup *l;
+
+	ll_pthread_rwlock_rdlock(&locks_rwlock);
+	node = __get_lock_node(lock, &parent);
+	ll_pthread_rwlock_unlock(&locks_rwlock);
+	if (*node) {
+		return rb_entry(*node, struct lock_lookup, node);
+	}
+
+	/* We didn't find the lock, let's create it */
+	l = alloc_lock();
+	if (l == NULL)
+		return NULL;
+
+	l->orig = lock;
+	/*
+	 * Currently the name of the lock is the ptr value of the pthread lock,
+	 * while not optimal, it makes debugging a bit easier.
+	 *
+	 * TODO: Get the real name of the lock using libdwarf
+	 */
+	sprintf(l->name, "%p", lock);
+	lockdep_init_map(&l->dep_map, l->name, &l->key, 0);
+
+	ll_pthread_rwlock_wrlock(&locks_rwlock);
+	/* This might have changed since the last time we fetched it */
+	node = __get_lock_node(lock, &parent);
+	rb_link_node(&l->node, parent, node);
+	rb_insert_color(&l->node, &locks);
+	ll_pthread_rwlock_unlock(&locks_rwlock);
+
+	return l;
+}
+
+static void __del_lock(struct lock_lookup *lock)
+{
+	ll_pthread_rwlock_wrlock(&locks_rwlock);
+	rb_erase(&lock->node, &locks);
+	ll_pthread_rwlock_unlock(&locks_rwlock);
+	free_lock(lock);
+}
+
+int pthread_mutex_init(pthread_mutex_t *mutex,
+			const pthread_mutexattr_t *attr)
+{
+	int r;
+
+	/*
+	 * We keep trying to init our preload module because there might be
+	 * code in init sections that tries to touch locks before we are
+	 * initialized, in that case we'll need to manually call preload
+	 * to get us going.
+	 *
+	 * Funny enough, kernel's lockdep had the same issue, and used
+	 * (almost) the same solution. See look_up_lock_class() in
+	 * kernel/locking/lockdep.c for details.
+	 */
+	try_init_preload();
+
+	r = ll_pthread_mutex_init(mutex, attr);
+	if (r == 0)
+		/*
+		 * We do a dummy initialization here so that lockdep could
+		 * warn us if something fishy is going on - such as
+		 * initializing a held lock.
+		 */
+		__get_lock(mutex);
+
+	return r;
+}
+
+int pthread_mutex_lock(pthread_mutex_t *mutex)
+{
+	int r;
+
+	try_init_preload();
+
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL,
+			(unsigned long)_RET_IP_);
+	/*
+	 * Here's the thing with pthread mutexes: unlike the kernel variant,
+	 * they can fail.
+	 *
+	 * This means that the behaviour here is a bit different from what's
+	 * going on in the kernel: there we just tell lockdep that we took the
+	 * lock before actually taking it, but here we must deal with the case
+	 * that locking failed.
+	 *
+	 * To do that we'll "release" the lock if locking failed - this way
+	 * we'll get lockdep doing the correct checks when we try to take
+	 * the lock, and if that fails - we'll be back to the correct
+	 * state by releasing it.
+	 */
+	r = ll_pthread_mutex_lock(mutex);
+	if (r)
+		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_mutex_trylock(pthread_mutex_t *mutex)
+{
+	int r;
+
+	try_init_preload();
+
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_mutex_trylock(mutex);
+	if (r)
+		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_mutex_unlock(pthread_mutex_t *mutex)
+{
+	int r;
+
+	try_init_preload();
+
+	lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+	/*
+	 * Just like taking a lock, only in reverse!
+	 *
+	 * If we fail releasing the lock, tell lockdep we're holding it again.
+	 */
+	r = ll_pthread_mutex_unlock(mutex);
+	if (r)
+		lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_mutex_destroy(pthread_mutex_t *mutex)
+{
+	try_init_preload();
+
+	/*
+	 * Let's see if we're releasing a lock that's held.
+	 *
+	 * TODO: Hook into free() and add that check there as well.
+	 */
+	debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex));
+	__del_lock(__get_lock(mutex));
+	return ll_pthread_mutex_destroy(mutex);
+}
+
+/* This is the rwlock part, very similar to what happened with mutex above */
+int pthread_rwlock_init(pthread_rwlock_t *rwlock,
+			const pthread_rwlockattr_t *attr)
+{
+	int r;
+
+	try_init_preload();
+
+	r = ll_pthread_rwlock_init(rwlock, attr);
+	if (r == 0)
+		__get_lock(rwlock);
+
+	return r;
+}
+
+int pthread_rwlock_destroy(pthread_rwlock_t *rwlock)
+{
+	try_init_preload();
+
+	debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock));
+	__del_lock(__get_lock(rwlock));
+	return ll_pthread_rwlock_destroy(rwlock);
+}
+
+int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_rdlock(rwlock);
+	if (r)
+		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_tryrdlock(rwlock);
+	if (r)
+		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_trywrlock(rwlock);
+	if (r)
+                lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_wrlock(rwlock);
+	if (r)
+		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_unlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_unlock(rwlock);
+	if (r)
+		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+__attribute__((constructor)) static void init_preload(void)
+{
+	if (__init_state != done)
+		return;
+
+#ifndef __GLIBC__
+	__init_state = prepare;
+
+	ll_pthread_mutex_init = dlsym(RTLD_NEXT, "pthread_mutex_init");
+	ll_pthread_mutex_lock = dlsym(RTLD_NEXT, "pthread_mutex_lock");
+	ll_pthread_mutex_trylock = dlsym(RTLD_NEXT, "pthread_mutex_trylock");
+	ll_pthread_mutex_unlock = dlsym(RTLD_NEXT, "pthread_mutex_unlock");
+	ll_pthread_mutex_destroy = dlsym(RTLD_NEXT, "pthread_mutex_destroy");
+
+	ll_pthread_rwlock_init = dlsym(RTLD_NEXT, "pthread_rwlock_init");
+	ll_pthread_rwlock_destroy = dlsym(RTLD_NEXT, "pthread_rwlock_destroy");
+	ll_pthread_rwlock_rdlock = dlsym(RTLD_NEXT, "pthread_rwlock_rdlock");
+	ll_pthread_rwlock_tryrdlock = dlsym(RTLD_NEXT, "pthread_rwlock_tryrdlock");
+	ll_pthread_rwlock_wrlock = dlsym(RTLD_NEXT, "pthread_rwlock_wrlock");
+	ll_pthread_rwlock_trywrlock = dlsym(RTLD_NEXT, "pthread_rwlock_trywrlock");
+	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
+#endif
+
+	printf("%p\n", ll_pthread_mutex_trylock);fflush(stdout);
+
+	lockdep_init();
+
+	__init_state = done;
+}
diff --git a/tools/lib/lockdep/rbtree.c b/tools/lib/lockdep/rbtree.c
new file mode 100644
index 000000000000..f7f43033c8b7
--- /dev/null
+++ b/tools/lib/lockdep/rbtree.c
@@ -0,0 +1 @@
+#include "../../../lib/rbtree.c"
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
new file mode 100644
index 000000000000..5334ad9d39b7
--- /dev/null
+++ b/tools/lib/lockdep/run_tests.sh
@@ -0,0 +1,27 @@
+#! /bin/bash
+
+make &> /dev/null
+
+for i in `ls tests/*.c`; do
+	testname=$(basename -s .c "$i")
+	gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null
+	echo -ne "$testname... "
+	if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then
+		echo "PASSED!"
+	else
+		echo "FAILED!"
+	fi
+	rm tests/$testname
+done
+
+for i in `ls tests/*.c`; do
+	testname=$(basename -s .c "$i")
+	gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null
+	echo -ne "(PRELOAD) $testname... "
+	if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then
+		echo "PASSED!"
+	else
+		echo "FAILED!"
+	fi
+	rm tests/$testname
+done
diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c
new file mode 100644
index 000000000000..0f782ff404ac
--- /dev/null
+++ b/tools/lib/lockdep/tests/AA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_lock(&b);
+	pthread_mutex_lock(&a);
+}
diff --git a/tools/lib/lockdep/tests/ABBA.c b/tools/lib/lockdep/tests/ABBA.c
new file mode 100644
index 000000000000..07f0e29d5485
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, a);
+}
diff --git a/tools/lib/lockdep/tests/ABBCCA.c b/tools/lib/lockdep/tests/ABBCCA.c
new file mode 100644
index 000000000000..843db09ac666
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBCCA.c
@@ -0,0 +1,15 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(c, a);
+}
diff --git a/tools/lib/lockdep/tests/ABBCCDDA.c b/tools/lib/lockdep/tests/ABBCCDDA.c
new file mode 100644
index 000000000000..33620e268f85
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBCCDDA.c
@@ -0,0 +1,17 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(d, a);
+}
diff --git a/tools/lib/lockdep/tests/ABCABC.c b/tools/lib/lockdep/tests/ABCABC.c
new file mode 100644
index 000000000000..3fee51e3a68a
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCABC.c
@@ -0,0 +1,15 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, a);
+	LOCK_UNLOCK_2(b, c);
+}
diff --git a/tools/lib/lockdep/tests/ABCDBCDA.c b/tools/lib/lockdep/tests/ABCDBCDA.c
new file mode 100644
index 000000000000..427ba562c75b
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCDBCDA.c
@@ -0,0 +1,17 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(d, a);
+}
diff --git a/tools/lib/lockdep/tests/ABCDBDDA.c b/tools/lib/lockdep/tests/ABCDBDDA.c
new file mode 100644
index 000000000000..680c6cf3e919
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCDBDDA.c
@@ -0,0 +1,17 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(b, d);
+	LOCK_UNLOCK_2(d, a);
+}
diff --git a/tools/lib/lockdep/tests/WW.c b/tools/lib/lockdep/tests/WW.c
new file mode 100644
index 000000000000..d44f77d71029
--- /dev/null
+++ b/tools/lib/lockdep/tests/WW.c
@@ -0,0 +1,13 @@
+#include <liblockdep/rwlock.h>
+
+void main(void)
+{
+	pthread_rwlock_t a, b;
+
+	pthread_rwlock_init(&a, NULL);
+	pthread_rwlock_init(&b, NULL);
+
+	pthread_rwlock_wrlock(&a);
+	pthread_rwlock_rdlock(&b);
+	pthread_rwlock_wrlock(&a);
+}
diff --git a/tools/lib/lockdep/tests/common.h b/tools/lib/lockdep/tests/common.h
new file mode 100644
index 000000000000..d89e94d47d86
--- /dev/null
+++ b/tools/lib/lockdep/tests/common.h
@@ -0,0 +1,12 @@
+#ifndef _LIBLOCKDEP_TEST_COMMON_H
+#define _LIBLOCKDEP_TEST_COMMON_H
+
+#define LOCK_UNLOCK_2(a, b)			\
+	do {					\
+		pthread_mutex_lock(&(a));	\
+		pthread_mutex_lock(&(b));	\
+		pthread_mutex_unlock(&(b));	\
+		pthread_mutex_unlock(&(a));	\
+	} while(0)
+
+#endif
diff --git a/tools/lib/lockdep/tests/unlock_balance.c b/tools/lib/lockdep/tests/unlock_balance.c
new file mode 100644
index 000000000000..0bc62de686f7
--- /dev/null
+++ b/tools/lib/lockdep/tests/unlock_balance.c
@@ -0,0 +1,12 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a;
+
+	pthread_mutex_init(&a, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_unlock(&a);
+	pthread_mutex_unlock(&a);
+}
diff --git a/tools/lib/lockdep/uinclude/asm/hweight.h b/tools/lib/lockdep/uinclude/asm/hweight.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/hweight.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/asm/sections.h b/tools/lib/lockdep/uinclude/asm/sections.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/sections.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/bitops.h b/tools/lib/lockdep/uinclude/linux/bitops.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/bitops.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h
new file mode 100644
index 000000000000..7ac838a1f196
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/compiler.h
@@ -0,0 +1,7 @@
+#ifndef _LIBLOCKDEP_LINUX_COMPILER_H_
+#define _LIBLOCKDEP_LINUX_COMPILER_H_
+
+#define __used		__attribute__((__unused__))
+#define unlikely
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/debug_locks.h b/tools/lib/lockdep/uinclude/linux/debug_locks.h
new file mode 100644
index 000000000000..f38eb64df794
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/debug_locks.h
@@ -0,0 +1,12 @@
+#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
+#define _LIBLOCKDEP_DEBUG_LOCKS_H_
+
+#include <stddef.h>
+#include <linux/compiler.h>
+
+#define DEBUG_LOCKS_WARN_ON(x) (x)
+
+extern bool debug_locks;
+extern bool debug_locks_silent;
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/delay.h b/tools/lib/lockdep/uinclude/linux/delay.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/delay.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/export.h b/tools/lib/lockdep/uinclude/linux/export.h
new file mode 100644
index 000000000000..6bdf3492c535
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/export.h
@@ -0,0 +1,7 @@
+#ifndef _LIBLOCKDEP_LINUX_EXPORT_H_
+#define _LIBLOCKDEP_LINUX_EXPORT_H_
+
+#define EXPORT_SYMBOL(sym)
+#define EXPORT_SYMBOL_GPL(sym)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/ftrace.h b/tools/lib/lockdep/uinclude/linux/ftrace.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/ftrace.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/gfp.h b/tools/lib/lockdep/uinclude/linux/gfp.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/gfp.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/hardirq.h b/tools/lib/lockdep/uinclude/linux/hardirq.h
new file mode 100644
index 000000000000..c8f3f8f58729
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/hardirq.h
@@ -0,0 +1,11 @@
+#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
+#define _LIBLOCKDEP_LINUX_HARDIRQ_H_
+
+#define SOFTIRQ_BITS	0UL
+#define HARDIRQ_BITS	0UL
+#define SOFTIRQ_SHIFT	0UL
+#define HARDIRQ_SHIFT	0UL
+#define hardirq_count()	0UL
+#define softirq_count()	0UL
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/hash.h b/tools/lib/lockdep/uinclude/linux/hash.h
new file mode 100644
index 000000000000..0f8479858dc0
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/hash.h
@@ -0,0 +1 @@
+#include "../../../include/linux/hash.h"
diff --git a/tools/lib/lockdep/uinclude/linux/interrupt.h b/tools/lib/lockdep/uinclude/linux/interrupt.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/interrupt.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/irqflags.h b/tools/lib/lockdep/uinclude/linux/irqflags.h
new file mode 100644
index 000000000000..6cc296f0fad0
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/irqflags.h
@@ -0,0 +1,38 @@
+#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
+#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
+
+# define trace_hardirq_context(p)	0
+# define trace_softirq_context(p)	0
+# define trace_hardirqs_enabled(p)	0
+# define trace_softirqs_enabled(p)	0
+# define trace_hardirq_enter()		do { } while (0)
+# define trace_hardirq_exit()		do { } while (0)
+# define lockdep_softirq_enter()	do { } while (0)
+# define lockdep_softirq_exit()		do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+
+# define stop_critical_timings() do { } while (0)
+# define start_critical_timings() do { } while (0)
+
+#define raw_local_irq_disable() do { } while (0)
+#define raw_local_irq_enable() do { } while (0)
+#define raw_local_irq_save(flags) ((flags) = 0)
+#define raw_local_irq_restore(flags) do { } while (0)
+#define raw_local_save_flags(flags) ((flags) = 0)
+#define raw_irqs_disabled_flags(flags) do { } while (0)
+#define raw_irqs_disabled() 0
+#define raw_safe_halt()
+
+#define local_irq_enable() do { } while (0)
+#define local_irq_disable() do { } while (0)
+#define local_irq_save(flags) ((flags) = 0)
+#define local_irq_restore(flags) do { } while (0)
+#define local_save_flags(flags)	((flags) = 0)
+#define irqs_disabled() (1)
+#define irqs_disabled_flags(flags) (0)
+#define safe_halt() do { } while (0)
+
+#define trace_lock_release(x, y)
+#define trace_lock_acquire(a, b, c, d, e, f, g)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kallsyms.h b/tools/lib/lockdep/uinclude/linux/kallsyms.h
new file mode 100644
index 000000000000..b0f2dbdf1a15
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kallsyms.h
@@ -0,0 +1,32 @@
+#ifndef _LIBLOCKDEP_LINUX_KALLSYMS_H_
+#define _LIBLOCKDEP_LINUX_KALLSYMS_H_
+
+#include <linux/kernel.h>
+#include <stdio.h>
+
+#define KSYM_NAME_LEN 128
+
+struct module;
+
+static inline const char *kallsyms_lookup(unsigned long addr,
+					  unsigned long *symbolsize,
+					  unsigned long *offset,
+					  char **modname, char *namebuf)
+{
+	return NULL;
+}
+
+#include <execinfo.h>
+#include <stdlib.h>
+static inline void print_ip_sym(unsigned long ip)
+{
+	char **name;
+
+	name = backtrace_symbols((void **)&ip, 1);
+
+	printf("%s\n", *name);
+
+	free(name);
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kern_levels.h b/tools/lib/lockdep/uinclude/linux/kern_levels.h
new file mode 100644
index 000000000000..3b9bade28698
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kern_levels.h
@@ -0,0 +1,25 @@
+#ifndef __KERN_LEVELS_H__
+#define __KERN_LEVELS_H__
+
+#define KERN_SOH	""		/* ASCII Start Of Header */
+#define KERN_SOH_ASCII	''
+
+#define KERN_EMERG	KERN_SOH ""	/* system is unusable */
+#define KERN_ALERT	KERN_SOH ""	/* action must be taken immediately */
+#define KERN_CRIT	KERN_SOH ""	/* critical conditions */
+#define KERN_ERR	KERN_SOH ""	/* error conditions */
+#define KERN_WARNING	KERN_SOH ""	/* warning conditions */
+#define KERN_NOTICE	KERN_SOH ""	/* normal but significant condition */
+#define KERN_INFO	KERN_SOH ""	/* informational */
+#define KERN_DEBUG	KERN_SOH ""	/* debug-level messages */
+
+#define KERN_DEFAULT	KERN_SOH ""	/* the default kernel loglevel */
+
+/*
+ * Annotation for a "continued" line of log printout (only done after a
+ * line that had no enclosing \n). Only to be used by core/arch code
+ * during early bootup (a continued line is not SMP-safe otherwise).
+ */
+#define KERN_CONT	""
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kernel.h b/tools/lib/lockdep/uinclude/linux/kernel.h
new file mode 100644
index 000000000000..a11e3c357be7
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kernel.h
@@ -0,0 +1,44 @@
+#ifndef _LIBLOCKDEP_LINUX_KERNEL_H_
+#define _LIBLOCKDEP_LINUX_KERNEL_H_
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/rcu.h>
+#include <linux/hardirq.h>
+#include <linux/kern_levels.h>
+
+#ifndef container_of
+#define container_of(ptr, type, member) ({			\
+	const typeof(((type *)0)->member) * __mptr = (ptr);	\
+	(type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define max(x, y) ({				\
+	typeof(x) _max1 = (x);			\
+	typeof(y) _max2 = (y);			\
+	(void) (&_max1 == &_max2);		\
+	_max1 > _max2 ? _max1 : _max2; })
+
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+#define WARN_ON(x) (x)
+#define WARN_ON_ONCE(x) (x)
+#define likely(x) (x)
+#define WARN(x, y, z) (x)
+#define uninitialized_var(x) x
+#define __init
+#define noinline
+#define list_add_tail_rcu list_add_tail
+
+#ifndef CALLER_ADDR0
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#endif
+
+#ifndef _RET_IP_
+#define _RET_IP_ CALLER_ADDR0
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kmemcheck.h b/tools/lib/lockdep/uinclude/linux/kmemcheck.h
new file mode 100644
index 000000000000..94d598bc6abe
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kmemcheck.h
@@ -0,0 +1,8 @@
+#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_
+#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_
+
+static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
+{
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/linkage.h b/tools/lib/lockdep/uinclude/linux/linkage.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/linkage.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/list.h b/tools/lib/lockdep/uinclude/linux/list.h
new file mode 100644
index 000000000000..6e9ef31ed82e
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/list.h
@@ -0,0 +1 @@
+#include "../../../include/linux/list.h"
diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/lib/lockdep/uinclude/linux/lockdep.h
new file mode 100644
index 000000000000..d0f5d6e50214
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/lockdep.h
@@ -0,0 +1,55 @@
+#ifndef _LIBLOCKDEP_LOCKDEP_H_
+#define _LIBLOCKDEP_LOCKDEP_H_
+
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <string.h>
+#include <limits.h>
+#include <linux/utsname.h>
+
+
+#define MAX_LOCK_DEPTH 2000UL
+
+#include "../../../include/linux/lockdep.h"
+
+struct task_struct {
+	u64 curr_chain_key;
+	int lockdep_depth;
+	unsigned int lockdep_recursion;
+	struct held_lock held_locks[MAX_LOCK_DEPTH];
+	gfp_t lockdep_reclaim_gfp;
+	int pid;
+	char comm[17];
+};
+
+extern struct task_struct *__curr(void);
+
+#define current (__curr())
+
+#define debug_locks_off() 1
+#define task_pid_nr(tsk) ((tsk)->pid)
+
+#define KSYM_NAME_LEN 128
+#define printk printf
+
+#define list_del_rcu list_del
+
+#define atomic_t unsigned long
+#define atomic_inc(x) ((*(x))++)
+
+static struct new_utsname *init_utsname(void)
+{
+	static struct new_utsname n = (struct new_utsname) {
+		.release = "liblockdep",
+		.version = LIBLOCKDEP_VERSION,
+	};
+
+	return &n;
+}
+
+#define print_tainted() ""
+#define static_obj(x) 1
+
+#define debug_show_all_locks()
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/module.h b/tools/lib/lockdep/uinclude/linux/module.h
new file mode 100644
index 000000000000..09c7a7be8ccc
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/module.h
@@ -0,0 +1,6 @@
+#ifndef _LIBLOCKDEP_LINUX_MODULE_H_
+#define _LIBLOCKDEP_LINUX_MODULE_H_
+
+#define module_param(name, type, perm)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/mutex.h b/tools/lib/lockdep/uinclude/linux/mutex.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/mutex.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/poison.h b/tools/lib/lockdep/uinclude/linux/poison.h
new file mode 100644
index 000000000000..0c27bdf14233
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/poison.h
@@ -0,0 +1 @@
+#include "../../../include/linux/poison.h"
diff --git a/tools/lib/lockdep/uinclude/linux/prefetch.h b/tools/lib/lockdep/uinclude/linux/prefetch.h
new file mode 100644
index 000000000000..d73fe6f850ac
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/prefetch.h
@@ -0,0 +1,6 @@
+#ifndef _LIBLOCKDEP_LINUX_PREFETCH_H_
+#define _LIBLOCKDEP_LINUX_PREFETCH_H
+
+static inline void prefetch(void *a __attribute__((unused))) { }
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/proc_fs.h b/tools/lib/lockdep/uinclude/linux/proc_fs.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/proc_fs.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/rbtree.h b/tools/lib/lockdep/uinclude/linux/rbtree.h
new file mode 100644
index 000000000000..965901db4862
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/rbtree.h
@@ -0,0 +1 @@
+#include "../../../include/linux/rbtree.h"
diff --git a/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h b/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h
new file mode 100644
index 000000000000..c3759477379c
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h
@@ -0,0 +1,2 @@
+#define __always_inline
+#include "../../../include/linux/rbtree_augmented.h"
diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h
new file mode 100644
index 000000000000..4c99fcb5da27
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/rcu.h
@@ -0,0 +1,16 @@
+#ifndef _LIBLOCKDEP_RCU_H_
+#define _LIBLOCKDEP_RCU_H_
+
+int rcu_scheduler_active;
+
+static inline int rcu_lockdep_current_cpu_online(void)
+{
+	return 1;
+}
+
+static inline int rcu_is_cpu_idle(void)
+{
+	return 1;
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/seq_file.h b/tools/lib/lockdep/uinclude/linux/seq_file.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/seq_file.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/spinlock.h b/tools/lib/lockdep/uinclude/linux/spinlock.h
new file mode 100644
index 000000000000..68c1aa2bcba5
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/spinlock.h
@@ -0,0 +1,25 @@
+#ifndef _LIBLOCKDEP_SPINLOCK_H_
+#define _LIBLOCKDEP_SPINLOCK_H_
+
+#include <pthread.h>
+#include <stdbool.h>
+
+#define arch_spinlock_t pthread_mutex_t
+#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER
+
+static inline void arch_spin_lock(arch_spinlock_t *mutex)
+{
+	pthread_mutex_lock(mutex);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *mutex)
+{
+	pthread_mutex_unlock(mutex);
+}
+
+static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
+{
+	return true;
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/stacktrace.h b/tools/lib/lockdep/uinclude/linux/stacktrace.h
new file mode 100644
index 000000000000..39aecc6b19d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/stacktrace.h
@@ -0,0 +1,32 @@
+#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_
+#define _LIBLOCKDEP_LINUX_STACKTRACE_H_
+
+#include <execinfo.h>
+
+struct stack_trace {
+	unsigned int nr_entries, max_entries;
+	unsigned long *entries;
+	int skip;
+};
+
+static inline void print_stack_trace(struct stack_trace *trace, int spaces)
+{
+	backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1);
+}
+
+#define save_stack_trace(trace)	\
+	((trace)->nr_entries =	\
+		backtrace((void **)(trace)->entries, (trace)->max_entries))
+
+static inline int dump_stack(void)
+{
+	void *array[64];
+	size_t size;
+
+	size = backtrace(array, 64);
+	backtrace_symbols_fd(array, size, 1);
+
+	return 0;
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/stringify.h b/tools/lib/lockdep/uinclude/linux/stringify.h
new file mode 100644
index 000000000000..05dfcd1ac118
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/stringify.h
@@ -0,0 +1,7 @@
+#ifndef _LIBLOCKDEP_LINUX_STRINGIFY_H_
+#define _LIBLOCKDEP_LINUX_STRINGIFY_H_
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/types.h b/tools/lib/lockdep/uinclude/linux/types.h
new file mode 100644
index 000000000000..929938f426de
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/types.h
@@ -0,0 +1,58 @@
+#ifndef _LIBLOCKDEP_LINUX_TYPES_H_
+#define _LIBLOCKDEP_LINUX_TYPES_H_
+
+#include <stdbool.h>
+#include <stddef.h>
+
+#define __SANE_USERSPACE_TYPES__	/* For PPC64, to get LL64 types */
+#include <asm/types.h>
+
+struct page;
+struct kmem_cache;
+
+typedef unsigned gfp_t;
+
+typedef __u64 u64;
+typedef __s64 s64;
+
+typedef __u32 u32;
+typedef __s32 s32;
+
+typedef __u16 u16;
+typedef __s16 s16;
+
+typedef __u8  u8;
+typedef __s8  s8;
+
+#ifdef __CHECKER__
+#define __bitwise__ __attribute__((bitwise))
+#else
+#define __bitwise__
+#endif
+#ifdef __CHECK_ENDIAN__
+#define __bitwise __bitwise__
+#else
+#define __bitwise
+#endif
+
+
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+struct hlist_head {
+	struct hlist_node *first;
+};
+
+struct hlist_node {
+	struct hlist_node *next, **pprev;
+};
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/trace/events/lock.h b/tools/lib/lockdep/uinclude/trace/events/lock.h
new file mode 100644
index 000000000000..fab00ff936d1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/trace/events/lock.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
new file mode 100644
index 000000000000..18bc271a4bbc
--- /dev/null
+++ b/tools/lib/symbol/kallsyms.c
@@ -0,0 +1,58 @@
+#include "symbol/kallsyms.h"
+#include <stdio.h>
+#include <stdlib.h>
+
+int kallsyms__parse(const char *filename, void *arg,
+		    int (*process_symbol)(void *arg, const char *name,
+					  char type, u64 start))
+{
+	char *line = NULL;
+	size_t n;
+	int err = -1;
+	FILE *file = fopen(filename, "r");
+
+	if (file == NULL)
+		goto out_failure;
+
+	err = 0;
+
+	while (!feof(file)) {
+		u64 start;
+		int line_len, len;
+		char symbol_type;
+		char *symbol_name;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0 || !line)
+			break;
+
+		line[--line_len] = '\0'; /* \n */
+
+		len = hex2u64(line, &start);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		symbol_type = line[len];
+		len += 2;
+		symbol_name = line + len;
+		len = line_len - len;
+
+		if (len >= KSYM_NAME_LEN) {
+			err = -1;
+			break;
+		}
+
+		err = process_symbol(arg, symbol_name, symbol_type, start);
+		if (err)
+			break;
+	}
+
+	free(line);
+	fclose(file);
+	return err;
+
+out_failure:
+	return -1;
+}
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
new file mode 100644
index 000000000000..6084f5e18b3c
--- /dev/null
+++ b/tools/lib/symbol/kallsyms.h
@@ -0,0 +1,24 @@
+#ifndef __TOOLS_KALLSYMS_H_
+#define __TOOLS_KALLSYMS_H_ 1
+
+#include <elf.h>
+#include <linux/ctype.h>
+#include <linux/types.h>
+
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+static inline u8 kallsyms2elf_type(char type)
+{
+	if (type == 'W')
+		return STB_WEAK;
+
+	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
+}
+
+int kallsyms__parse(const char *filename, void *arg,
+		    int (*process_symbol)(void *arg, const char *name,
+					  char type, u64 start));
+
+#endif /* __TOOLS_KALLSYMS_H_ */
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index fc1502098595..0d9cbb426b44 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -43,6 +43,30 @@ man_dir_SQ = '$(subst ','\'',$(man_dir))'
 export man_dir man_dir_SQ INSTALL
 export DESTDIR DESTDIR_SQ
 
+set_plugin_dir := 1
+
+# Set plugin_dir to preffered global plugin location
+# If we install under $HOME directory we go under
+# $(HOME)/.traceevent/plugins
+#
+# We dont set PLUGIN_DIR in case we install under $HOME
+# directory, because by default the code looks under:
+# $(HOME)/.traceevent/plugins by default.
+#
+ifeq ($(plugin_dir),)
+ifeq ($(prefix),$(HOME))
+override plugin_dir = $(HOME)/.traceevent/plugins
+set_plugin_dir := 0
+else
+override plugin_dir = $(prefix)/lib/traceevent/plugins
+endif
+endif
+
+ifeq ($(set_plugin_dir),1)
+PLUGIN_DIR = -DPLUGIN_DIR="$(DESTDIR)/$(plugin_dir)"
+PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
+endif
+
 # copy a bit from Linux kbuild
 
 ifeq ("$(origin V)", "command line")
@@ -96,6 +120,7 @@ export prefix bindir src obj
 # Shell quotes
 bindir_SQ = $(subst ','\'',$(bindir))
 bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
 
@@ -138,10 +163,10 @@ else
   print_app_build =		echo '  BUILD    '$(OBJ);
   print_fpic_compile =		echo '  CC FPIC  '$(OBJ);
   print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
-  print_plugin_obj_compile =	echo '  BUILD    PLUGIN OBJ '$(OBJ);
-  print_plugin_build =		echo '  BUILD    PLUGIN     '$(OBJ);
+  print_plugin_obj_compile =	echo '  CC FPIC  '$(OBJ);
+  print_plugin_build =		echo '  BUILD    PLUGIN '$(OBJ);
   print_static_lib_build =	echo '  BUILD    STATIC LIB '$(OBJ);
-  print_install =		echo '  INSTALL  '$1'	to	$(DESTDIR_SQ)$2';
+  print_install =		echo '  INSTALL  '$1;
 endif
 
 do_fpic_compile =					\
@@ -180,12 +205,29 @@ $(obj)/%.o: $(src)/%.c
 %.o: $(src)/%.c
 	$(Q)$(call do_compile)
 
-PEVENT_LIB_OBJS = event-parse.o trace-seq.o parse-filter.o parse-utils.o
+PEVENT_LIB_OBJS  = event-parse.o
+PEVENT_LIB_OBJS += event-plugin.o
+PEVENT_LIB_OBJS += trace-seq.o
+PEVENT_LIB_OBJS += parse-filter.o
+PEVENT_LIB_OBJS += parse-utils.o
 PEVENT_LIB_OBJS += kbuffer-parse.o
 
-ALL_OBJS = $(PEVENT_LIB_OBJS)
+PLUGIN_OBJS  = plugin_jbd2.o
+PLUGIN_OBJS += plugin_hrtimer.o
+PLUGIN_OBJS += plugin_kmem.o
+PLUGIN_OBJS += plugin_kvm.o
+PLUGIN_OBJS += plugin_mac80211.o
+PLUGIN_OBJS += plugin_sched_switch.o
+PLUGIN_OBJS += plugin_function.o
+PLUGIN_OBJS += plugin_xen.o
+PLUGIN_OBJS += plugin_scsi.o
+PLUGIN_OBJS += plugin_cfg80211.o
+
+PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
-CMD_TARGETS = $(LIB_FILE)
+ALL_OBJS = $(PEVENT_LIB_OBJS) $(PLUGIN_OBJS)
+
+CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
 
 TARGETS = $(CMD_TARGETS)
 
@@ -200,9 +242,17 @@ libtraceevent.so: $(PEVENT_LIB_OBJS)
 libtraceevent.a: $(PEVENT_LIB_OBJS)
 	$(Q)$(do_build_static_lib)
 
+plugins: $(PLUGINS)
+
 $(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
 	$(Q)$(do_fpic_compile)
 
+$(PLUGIN_OBJS): %.o : $(src)/%.c
+	$(Q)$(do_compile_plugin_obj)
+
+$(PLUGINS): %.so: %.o
+	$(Q)$(do_plugin_build)
+
 define make_version.h
 	(echo '/* This file is automatically generated. Do not modify. */';		\
 	echo \#define VERSION_CODE $(shell						\
@@ -290,9 +340,16 @@ define do_install
 	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
 endef
 
-install_lib: all_cmd
+install_lib: all_cmd install_plugins
 	$(Q)$(call do_install,$(LIB_FILE),$(bindir_SQ))
 
+PLUGINS_INSTALL = $(subst .so,.install,$(PLUGINS))
+
+$(PLUGINS_INSTALL): %.install : %.so force
+	$(Q)$(call do_install,$<,$(plugin_dir_SQ))
+
+install_plugins: $(PLUGINS_INSTALL)
+
 install: install_lib
 
 clean:
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 217c82ee3665..22566c271275 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2710,7 +2710,6 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	struct print_arg *farg;
 	enum event_type type;
 	char *token;
-	const char *test;
 	int i;
 
 	arg->type = PRINT_FUNC;
@@ -2727,15 +2726,19 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 		}
 
 		type = process_arg(event, farg, &token);
-		if (i < (func->nr_args - 1))
-			test = ",";
-		else
-			test = ")";
-
-		if (test_type_token(type, token, EVENT_DELIM, test)) {
-			free_arg(farg);
-			free_token(token);
-			return EVENT_ERROR;
+		if (i < (func->nr_args - 1)) {
+			if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
+				warning("Error: function '%s()' expects %d arguments but event %s only uses %d",
+					func->name, func->nr_args,
+					event->name, i + 1);
+				goto err;
+			}
+		} else {
+			if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
+				warning("Error: function '%s()' only expects %d arguments but event %s has more",
+					func->name, func->nr_args, event->name);
+				goto err;
+			}
 		}
 
 		*next_arg = farg;
@@ -2747,6 +2750,11 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	*tok = token;
 
 	return type;
+
+err:
+	free_arg(farg);
+	free_token(token);
+	return EVENT_ERROR;
 }
 
 static enum event_type
@@ -4099,6 +4107,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 	unsigned long long val;
 	struct func_map *func;
 	const char *saveptr;
+	struct trace_seq p;
 	char *bprint_fmt = NULL;
 	char format[32];
 	int show_func;
@@ -4306,8 +4315,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				format[len] = 0;
 				if (!len_as_arg)
 					len_arg = -1;
-				print_str_arg(s, data, size, event,
+				/* Use helper trace_seq */
+				trace_seq_init(&p);
+				print_str_arg(&p, data, size, event,
 					      format, len_arg, arg);
+				trace_seq_terminate(&p);
+				trace_seq_puts(s, p.buffer);
 				arg = arg->next;
 				break;
 			default:
@@ -5116,8 +5129,38 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
 	return ret;
 }
 
+static enum pevent_errno
+__pevent_parse_event(struct pevent *pevent,
+		     struct event_format **eventp,
+		     const char *buf, unsigned long size,
+		     const char *sys)
+{
+	int ret = __pevent_parse_format(eventp, pevent, buf, size, sys);
+	struct event_format *event = *eventp;
+
+	if (event == NULL)
+		return ret;
+
+	if (pevent && add_event(pevent, event)) {
+		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		goto event_add_failed;
+	}
+
+#define PRINT_ARGS 0
+	if (PRINT_ARGS && event->print_fmt.args)
+		print_args(event->print_fmt.args);
+
+	return 0;
+
+event_add_failed:
+	pevent_free_format(event);
+	return ret;
+}
+
 /**
  * pevent_parse_format - parse the event format
+ * @pevent: the handle to the pevent
+ * @eventp: returned format
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
  * @sys: the system the event belongs to
@@ -5129,10 +5172,12 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+enum pevent_errno pevent_parse_format(struct pevent *pevent,
+				      struct event_format **eventp,
+				      const char *buf,
 				      unsigned long size, const char *sys)
 {
-	return __pevent_parse_format(eventp, NULL, buf, size, sys);
+	return __pevent_parse_event(pevent, eventp, buf, size, sys);
 }
 
 /**
@@ -5153,25 +5198,7 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys)
 {
 	struct event_format *event = NULL;
-	int ret = __pevent_parse_format(&event, pevent, buf, size, sys);
-
-	if (event == NULL)
-		return ret;
-
-	if (add_event(pevent, event)) {
-		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
-		goto event_add_failed;
-	}
-
-#define PRINT_ARGS 0
-	if (PRINT_ARGS && event->print_fmt.args)
-		print_args(event->print_fmt.args);
-
-	return 0;
-
-event_add_failed:
-	pevent_free_format(event);
-	return ret;
+	return __pevent_parse_event(pevent, &event, buf, size, sys);
 }
 
 #undef _PE
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 8d73d2594f65..3ad784f5f647 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -23,6 +23,7 @@
 #include <stdbool.h>
 #include <stdarg.h>
 #include <regex.h>
+#include <string.h>
 
 #ifndef __maybe_unused
 #define __maybe_unused __attribute__((unused))
@@ -355,12 +356,35 @@ enum pevent_flag {
 	_PE(READ_FORMAT_FAILED,	"failed to read event format"),		      \
 	_PE(READ_PRINT_FAILED,	"failed to read event print fmt"), 	      \
 	_PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\
-	_PE(INVALID_ARG_TYPE,	"invalid argument type")
+	_PE(INVALID_ARG_TYPE,	"invalid argument type"),		      \
+	_PE(INVALID_EXP_TYPE,	"invalid expression type"),		      \
+	_PE(INVALID_OP_TYPE,	"invalid operator type"),		      \
+	_PE(INVALID_EVENT_NAME,	"invalid event name"),			      \
+	_PE(EVENT_NOT_FOUND,	"no event found"),			      \
+	_PE(SYNTAX_ERROR,	"syntax error"),			      \
+	_PE(ILLEGAL_RVALUE,	"illegal rvalue"),			      \
+	_PE(ILLEGAL_LVALUE,	"illegal lvalue for string comparison"),      \
+	_PE(INVALID_REGEX,	"regex did not compute"),		      \
+	_PE(ILLEGAL_STRING_CMP,	"illegal comparison for string"), 	      \
+	_PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer"), 	      \
+	_PE(REPARENT_NOT_OP,	"cannot reparent other than OP"),	      \
+	_PE(REPARENT_FAILED,	"failed to reparent filter OP"),	      \
+	_PE(BAD_FILTER_ARG,	"bad arg in filter tree"),		      \
+	_PE(UNEXPECTED_TYPE,	"unexpected type (not a value)"),	      \
+	_PE(ILLEGAL_TOKEN,	"illegal token"),			      \
+	_PE(INVALID_PAREN,	"open parenthesis cannot come here"), 	      \
+	_PE(UNBALANCED_PAREN,	"unbalanced number of parenthesis"),	      \
+	_PE(UNKNOWN_TOKEN,	"unknown token"),			      \
+	_PE(FILTER_NOT_FOUND,	"no filter found"),			      \
+	_PE(NOT_A_NUMBER,	"must have number field"),		      \
+	_PE(NO_FILTER,		"no filters exists"),			      \
+	_PE(FILTER_MISS,	"record does not match to filter")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
 enum pevent_errno {
 	PEVENT_ERRNO__SUCCESS			= 0,
+	PEVENT_ERRNO__FILTER_MATCH		= PEVENT_ERRNO__SUCCESS,
 
 	/*
 	 * Choose an arbitrary negative big number not to clash with standard
@@ -377,6 +401,11 @@ enum pevent_errno {
 };
 #undef _PE
 
+struct plugin_list;
+
+struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
+void traceevent_unload_plugins(struct plugin_list *plugin_list);
+
 struct cmdline;
 struct cmdline_list;
 struct func_map;
@@ -522,6 +551,15 @@ __data2host8(struct pevent *pevent, unsigned long long data)
 	__data2host8(pevent, __val);				\
 })
 
+static inline int traceevent_host_bigendian(void)
+{
+	unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
+	unsigned int val;
+
+	memcpy(&val, str, 4);
+	return val == 0x01020304;
+}
+
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
@@ -547,7 +585,9 @@ int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long siz
 
 enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys);
-enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+enum pevent_errno pevent_parse_format(struct pevent *pevent,
+				      struct event_format **eventp,
+				      const char *buf,
 				      unsigned long size, const char *sys);
 void pevent_free_format(struct event_format *event);
 
@@ -819,10 +859,11 @@ struct event_filter {
 
 struct event_filter *pevent_filter_alloc(struct pevent *pevent);
 
-#define FILTER_NONE		-2
-#define FILTER_NOEXIST		-1
-#define FILTER_MISS		0
-#define FILTER_MATCH		1
+/* for backward compatibility */
+#define FILTER_NONE		PEVENT_ERRNO__FILTER_NOT_FOUND
+#define FILTER_NOEXIST		PEVENT_ERRNO__NO_FILTER
+#define FILTER_MISS		PEVENT_ERRNO__FILTER_MISS
+#define FILTER_MATCH		PEVENT_ERRNO__FILTER_MATCH
 
 enum filter_trivial_type {
 	FILTER_TRIVIAL_FALSE,
@@ -830,20 +871,19 @@ enum filter_trivial_type {
 	FILTER_TRIVIAL_BOTH,
 };
 
-int pevent_filter_add_filter_str(struct event_filter *filter,
-				 const char *filter_str,
-				 char **error_str);
+enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
+					       const char *filter_str);
 
 
-int pevent_filter_match(struct event_filter *filter,
-			struct pevent_record *record);
+enum pevent_errno pevent_filter_match(struct event_filter *filter,
+				      struct pevent_record *record);
 
 int pevent_event_filtered(struct event_filter *filter,
 			  int event_id);
 
 void pevent_filter_reset(struct event_filter *filter);
 
-void pevent_filter_clear_trivial(struct event_filter *filter,
+int pevent_filter_clear_trivial(struct event_filter *filter,
 				 enum filter_trivial_type type);
 
 void pevent_filter_free(struct event_filter *filter);
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
new file mode 100644
index 000000000000..125f5676bcb5
--- /dev/null
+++ b/tools/lib/traceevent/event-plugin.c
@@ -0,0 +1,215 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <string.h>
+#include <dlfcn.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <dirent.h>
+#include "event-parse.h"
+#include "event-utils.h"
+
+#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
+
+struct plugin_list {
+	struct plugin_list	*next;
+	char			*name;
+	void			*handle;
+};
+
+static void
+load_plugin(struct pevent *pevent, const char *path,
+	    const char *file, void *data)
+{
+	struct plugin_list **plugin_list = data;
+	pevent_plugin_load_func func;
+	struct plugin_list *list;
+	const char *alias;
+	char *plugin;
+	void *handle;
+
+	plugin = malloc(strlen(path) + strlen(file) + 2);
+	if (!plugin) {
+		warning("could not allocate plugin memory\n");
+		return;
+	}
+
+	strcpy(plugin, path);
+	strcat(plugin, "/");
+	strcat(plugin, file);
+
+	handle = dlopen(plugin, RTLD_NOW | RTLD_GLOBAL);
+	if (!handle) {
+		warning("could not load plugin '%s'\n%s\n",
+			plugin, dlerror());
+		goto out_free;
+	}
+
+	alias = dlsym(handle, PEVENT_PLUGIN_ALIAS_NAME);
+	if (!alias)
+		alias = file;
+
+	func = dlsym(handle, PEVENT_PLUGIN_LOADER_NAME);
+	if (!func) {
+		warning("could not find func '%s' in plugin '%s'\n%s\n",
+			PEVENT_PLUGIN_LOADER_NAME, plugin, dlerror());
+		goto out_free;
+	}
+
+	list = malloc(sizeof(*list));
+	if (!list) {
+		warning("could not allocate plugin memory\n");
+		goto out_free;
+	}
+
+	list->next = *plugin_list;
+	list->handle = handle;
+	list->name = plugin;
+	*plugin_list = list;
+
+	pr_stat("registering plugin: %s", plugin);
+	func(pevent);
+	return;
+
+ out_free:
+	free(plugin);
+}
+
+static void
+load_plugins_dir(struct pevent *pevent, const char *suffix,
+		 const char *path,
+		 void (*load_plugin)(struct pevent *pevent,
+				     const char *path,
+				     const char *name,
+				     void *data),
+		 void *data)
+{
+	struct dirent *dent;
+	struct stat st;
+	DIR *dir;
+	int ret;
+
+	ret = stat(path, &st);
+	if (ret < 0)
+		return;
+
+	if (!S_ISDIR(st.st_mode))
+		return;
+
+	dir = opendir(path);
+	if (!dir)
+		return;
+
+	while ((dent = readdir(dir))) {
+		const char *name = dent->d_name;
+
+		if (strcmp(name, ".") == 0 ||
+		    strcmp(name, "..") == 0)
+			continue;
+
+		/* Only load plugins that end in suffix */
+		if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
+			continue;
+
+		load_plugin(pevent, path, name, data);
+	}
+
+	closedir(dir);
+}
+
+static void
+load_plugins(struct pevent *pevent, const char *suffix,
+	     void (*load_plugin)(struct pevent *pevent,
+				 const char *path,
+				 const char *name,
+				 void *data),
+	     void *data)
+{
+	char *home;
+	char *path;
+	char *envdir;
+
+	/*
+	 * If a system plugin directory was defined,
+	 * check that first.
+	 */
+#ifdef PLUGIN_DIR
+	load_plugins_dir(pevent, suffix, PLUGIN_DIR, load_plugin, data);
+#endif
+
+	/*
+	 * Next let the environment-set plugin directory
+	 * override the system defaults.
+	 */
+	envdir = getenv("TRACEEVENT_PLUGIN_DIR");
+	if (envdir)
+		load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+
+	/*
+	 * Now let the home directory override the environment
+	 * or system defaults.
+	 */
+	home = getenv("HOME");
+	if (!home)
+		return;
+
+	path = malloc(strlen(home) + strlen(LOCAL_PLUGIN_DIR) + 2);
+	if (!path) {
+		warning("could not allocate plugin memory\n");
+		return;
+	}
+
+	strcpy(path, home);
+	strcat(path, "/");
+	strcat(path, LOCAL_PLUGIN_DIR);
+
+	load_plugins_dir(pevent, suffix, path, load_plugin, data);
+
+	free(path);
+}
+
+struct plugin_list*
+traceevent_load_plugins(struct pevent *pevent)
+{
+	struct plugin_list *list = NULL;
+
+	load_plugins(pevent, ".so", load_plugin, &list);
+	return list;
+}
+
+void
+traceevent_unload_plugins(struct plugin_list *plugin_list)
+{
+	pevent_plugin_unload_func func;
+	struct plugin_list *list;
+
+	while (plugin_list) {
+		list = plugin_list;
+		plugin_list = list->next;
+		func = dlsym(list->handle, PEVENT_PLUGIN_UNLOADER_NAME);
+		if (func)
+			func();
+		dlclose(list->handle);
+		free(list->name);
+		free(list);
+	}
+}
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 2500e75583fc..e2842b926759 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -56,7 +56,21 @@ static void show_error(char **error_str, const char *fmt, ...)
 	index = pevent_get_input_buf_ptr();
 	len = input ? strlen(input) : 0;
 
-	error = malloc_or_die(MAX_ERR_STR_SIZE + (len*2) + 3);
+	error = malloc(MAX_ERR_STR_SIZE + (len*2) + 3);
+	if (error == NULL) {
+		/*
+		 * Maybe it's due to len is too long.
+		 * Retry without the input buffer part.
+		 */
+		len = 0;
+
+		error = malloc(MAX_ERR_STR_SIZE);
+		if (error == NULL) {
+			/* no memory */
+			*error_str = NULL;
+			return;
+		}
+	}
 
 	if (len) {
 		strcpy(error, input);
@@ -95,7 +109,11 @@ static enum event_type read_token(char **tok)
 	    (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) &&
 	    pevent_peek_char() == '~') {
 		/* append it */
-		*tok = malloc_or_die(3);
+		*tok = malloc(3);
+		if (*tok == NULL) {
+			free_token(token);
+			return EVENT_ERROR;
+		}
 		sprintf(*tok, "%c%c", *token, '~');
 		free_token(token);
 		/* Now remove the '~' from the buffer */
@@ -147,11 +165,13 @@ add_filter_type(struct event_filter *filter, int id)
 	if (filter_type)
 		return filter_type;
 
-	filter->event_filters =	realloc(filter->event_filters,
-					sizeof(*filter->event_filters) *
-					(filter->filters + 1));
-	if (!filter->event_filters)
-		die("Could not allocate filter");
+	filter_type = realloc(filter->event_filters,
+			      sizeof(*filter->event_filters) *
+			      (filter->filters + 1));
+	if (!filter_type)
+		return NULL;
+
+	filter->event_filters = filter_type;
 
 	for (i = 0; i < filter->filters; i++) {
 		if (filter->event_filters[i].event_id > id)
@@ -182,7 +202,10 @@ struct event_filter *pevent_filter_alloc(struct pevent *pevent)
 {
 	struct event_filter *filter;
 
-	filter = malloc_or_die(sizeof(*filter));
+	filter = malloc(sizeof(*filter));
+	if (filter == NULL)
+		return NULL;
+
 	memset(filter, 0, sizeof(*filter));
 	filter->pevent = pevent;
 	pevent_ref(pevent);
@@ -192,12 +215,7 @@ struct event_filter *pevent_filter_alloc(struct pevent *pevent)
 
 static struct filter_arg *allocate_arg(void)
 {
-	struct filter_arg *arg;
-
-	arg = malloc_or_die(sizeof(*arg));
-	memset(arg, 0, sizeof(*arg));
-
-	return arg;
+	return calloc(1, sizeof(struct filter_arg));
 }
 
 static void free_arg(struct filter_arg *arg)
@@ -242,15 +260,19 @@ static void free_arg(struct filter_arg *arg)
 	free(arg);
 }
 
-static void add_event(struct event_list **events,
+static int add_event(struct event_list **events,
 		      struct event_format *event)
 {
 	struct event_list *list;
 
-	list = malloc_or_die(sizeof(*list));
+	list = malloc(sizeof(*list));
+	if (list == NULL)
+		return -1;
+
 	list->next = *events;
 	*events = list;
 	list->event = event;
+	return 0;
 }
 
 static int event_match(struct event_format *event,
@@ -265,7 +287,7 @@ static int event_match(struct event_format *event,
 		!regexec(ereg, event->name, 0, NULL, 0);
 }
 
-static int
+static enum pevent_errno
 find_event(struct pevent *pevent, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
@@ -273,6 +295,7 @@ find_event(struct pevent *pevent, struct event_list **events,
 	regex_t ereg;
 	regex_t sreg;
 	int match = 0;
+	int fail = 0;
 	char *reg;
 	int ret;
 	int i;
@@ -283,23 +306,31 @@ find_event(struct pevent *pevent, struct event_list **events,
 		sys_name = NULL;
 	}
 
-	reg = malloc_or_die(strlen(event_name) + 3);
+	reg = malloc(strlen(event_name) + 3);
+	if (reg == NULL)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 	sprintf(reg, "^%s$", event_name);
 
 	ret = regcomp(&ereg, reg, REG_ICASE|REG_NOSUB);
 	free(reg);
 
 	if (ret)
-		return -1;
+		return PEVENT_ERRNO__INVALID_EVENT_NAME;
 
 	if (sys_name) {
-		reg = malloc_or_die(strlen(sys_name) + 3);
+		reg = malloc(strlen(sys_name) + 3);
+		if (reg == NULL) {
+			regfree(&ereg);
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
+
 		sprintf(reg, "^%s$", sys_name);
 		ret = regcomp(&sreg, reg, REG_ICASE|REG_NOSUB);
 		free(reg);
 		if (ret) {
 			regfree(&ereg);
-			return -1;
+			return PEVENT_ERRNO__INVALID_EVENT_NAME;
 		}
 	}
 
@@ -307,7 +338,10 @@ find_event(struct pevent *pevent, struct event_list **events,
 		event = pevent->events[i];
 		if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
 			match = 1;
-			add_event(events, event);
+			if (add_event(events, event) < 0) {
+				fail = 1;
+				break;
+			}
 		}
 	}
 
@@ -316,7 +350,9 @@ find_event(struct pevent *pevent, struct event_list **events,
 		regfree(&sreg);
 
 	if (!match)
-		return -1;
+		return PEVENT_ERRNO__EVENT_NOT_FOUND;
+	if (fail)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 
 	return 0;
 }
@@ -332,14 +368,18 @@ static void free_events(struct event_list *events)
 	}
 }
 
-static struct filter_arg *
+static enum pevent_errno
 create_arg_item(struct event_format *event, const char *token,
-		enum event_type type, char **error_str)
+		enum event_type type, struct filter_arg **parg, char **error_str)
 {
 	struct format_field *field;
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (arg == NULL) {
+		show_error(error_str, "failed to allocate filter arg");
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+	}
 
 	switch (type) {
 
@@ -349,8 +389,11 @@ create_arg_item(struct event_format *event, const char *token,
 		arg->value.type =
 			type == EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
 		arg->value.str = strdup(token);
-		if (!arg->value.str)
-			die("malloc string");
+		if (!arg->value.str) {
+			free_arg(arg);
+			show_error(error_str, "failed to allocate string filter arg");
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
 		break;
 	case EVENT_ITEM:
 		/* if it is a number, then convert it */
@@ -377,11 +420,11 @@ create_arg_item(struct event_format *event, const char *token,
 		break;
 	default:
 		free_arg(arg);
-		show_error(error_str, "expected a value but found %s",
-			   token);
-		return NULL;
+		show_error(error_str, "expected a value but found %s", token);
+		return PEVENT_ERRNO__UNEXPECTED_TYPE;
 	}
-	return arg;
+	*parg = arg;
+	return 0;
 }
 
 static struct filter_arg *
@@ -390,6 +433,9 @@ create_arg_op(enum filter_op_type btype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	arg->type = FILTER_ARG_OP;
 	arg->op.type = btype;
 
@@ -402,6 +448,9 @@ create_arg_exp(enum filter_exp_type etype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	arg->type = FILTER_ARG_EXP;
 	arg->op.type = etype;
 
@@ -414,6 +463,9 @@ create_arg_cmp(enum filter_exp_type etype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	/* Use NUM and change if necessary */
 	arg->type = FILTER_ARG_NUM;
 	arg->op.type = etype;
@@ -421,8 +473,8 @@ create_arg_cmp(enum filter_exp_type etype)
 	return arg;
 }
 
-static int add_right(struct filter_arg *op, struct filter_arg *arg,
-		     char **error_str)
+static enum pevent_errno
+add_right(struct filter_arg *op, struct filter_arg *arg, char **error_str)
 {
 	struct filter_arg *left;
 	char *str;
@@ -453,9 +505,8 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 		case FILTER_ARG_FIELD:
 			break;
 		default:
-			show_error(error_str,
-				   "Illegal rvalue");
-			return -1;
+			show_error(error_str, "Illegal rvalue");
+			return PEVENT_ERRNO__ILLEGAL_RVALUE;
 		}
 
 		/*
@@ -502,7 +553,7 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 			if (left->type != FILTER_ARG_FIELD) {
 				show_error(error_str,
 					   "Illegal lvalue for string comparison");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_LVALUE;
 			}
 
 			/* Make sure this is a valid string compare */
@@ -521,25 +572,31 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 					show_error(error_str,
 						   "RegEx '%s' did not compute",
 						   str);
-					return -1;
+					return PEVENT_ERRNO__INVALID_REGEX;
 				}
 				break;
 			default:
 				show_error(error_str,
 					   "Illegal comparison for string");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_STRING_CMP;
 			}
 
 			op->type = FILTER_ARG_STR;
 			op->str.type = op_type;
 			op->str.field = left->field.field;
 			op->str.val = strdup(str);
-			if (!op->str.val)
-				die("malloc string");
+			if (!op->str.val) {
+				show_error(error_str, "Failed to allocate string filter");
+				return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+			}
 			/*
 			 * Need a buffer to copy data for tests
 			 */
-			op->str.buffer = malloc_or_die(op->str.field->size + 1);
+			op->str.buffer = malloc(op->str.field->size + 1);
+			if (!op->str.buffer) {
+				show_error(error_str, "Failed to allocate string filter");
+				return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+			}
 			/* Null terminate this buffer */
 			op->str.buffer[op->str.field->size] = 0;
 
@@ -557,7 +614,7 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 			case FILTER_CMP_NOT_REGEX:
 				show_error(error_str,
 					   "Op not allowed with integers");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_INTEGER_CMP;
 
 			default:
 				break;
@@ -577,9 +634,8 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 	return 0;
 
  out_fail:
-	show_error(error_str,
-		   "Syntax error");
-	return -1;
+	show_error(error_str, "Syntax error");
+	return PEVENT_ERRNO__SYNTAX_ERROR;
 }
 
 static struct filter_arg *
@@ -592,7 +648,7 @@ rotate_op_right(struct filter_arg *a, struct filter_arg *b)
 	return arg;
 }
 
-static int add_left(struct filter_arg *op, struct filter_arg *arg)
+static enum pevent_errno add_left(struct filter_arg *op, struct filter_arg *arg)
 {
 	switch (op->type) {
 	case FILTER_ARG_EXP:
@@ -611,11 +667,11 @@ static int add_left(struct filter_arg *op, struct filter_arg *arg)
 		/* left arg of compares must be a field */
 		if (arg->type != FILTER_ARG_FIELD &&
 		    arg->type != FILTER_ARG_BOOLEAN)
-			return -1;
+			return PEVENT_ERRNO__INVALID_ARG_TYPE;
 		op->num.left = arg;
 		break;
 	default:
-		return -1;
+		return PEVENT_ERRNO__INVALID_ARG_TYPE;
 	}
 	return 0;
 }
@@ -728,15 +784,18 @@ enum filter_vals {
 	FILTER_VAL_TRUE,
 };
 
-void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
-		  struct filter_arg *arg)
+static enum pevent_errno
+reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
+		struct filter_arg *arg, char **error_str)
 {
 	struct filter_arg *other_child;
 	struct filter_arg **ptr;
 
 	if (parent->type != FILTER_ARG_OP &&
-	    arg->type != FILTER_ARG_OP)
-		die("can not reparent other than OP");
+	    arg->type != FILTER_ARG_OP) {
+		show_error(error_str, "can not reparent other than OP");
+		return PEVENT_ERRNO__REPARENT_NOT_OP;
+	}
 
 	/* Get the sibling */
 	if (old_child->op.right == arg) {
@@ -745,8 +804,10 @@ void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 	} else if (old_child->op.left == arg) {
 		ptr = &old_child->op.left;
 		other_child = old_child->op.right;
-	} else
-		die("Error in reparent op, find other child");
+	} else {
+		show_error(error_str, "Error in reparent op, find other child");
+		return PEVENT_ERRNO__REPARENT_FAILED;
+	}
 
 	/* Detach arg from old_child */
 	*ptr = NULL;
@@ -757,23 +818,29 @@ void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 		*parent = *arg;
 		/* Free arg without recussion */
 		free(arg);
-		return;
+		return 0;
 	}
 
 	if (parent->op.right == old_child)
 		ptr = &parent->op.right;
 	else if (parent->op.left == old_child)
 		ptr = &parent->op.left;
-	else
-		die("Error in reparent op");
+	else {
+		show_error(error_str, "Error in reparent op");
+		return PEVENT_ERRNO__REPARENT_FAILED;
+	}
+
 	*ptr = arg;
 
 	free_arg(old_child);
+	return 0;
 }
 
-enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
+/* Returns either filter_vals (success) or pevent_errno (failfure) */
+static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
+		    char **error_str)
 {
-	enum filter_vals lval, rval;
+	int lval, rval;
 
 	switch (arg->type) {
 
@@ -788,63 +855,68 @@ enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_EXP:
-		lval = test_arg(arg, arg->exp.left);
+		lval = test_arg(arg, arg->exp.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
-		rval = test_arg(arg, arg->exp.right);
+		rval = test_arg(arg, arg->exp.right, error_str);
 		if (rval != FILTER_VAL_NORM)
 			return rval;
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_NUM:
-		lval = test_arg(arg, arg->num.left);
+		lval = test_arg(arg, arg->num.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
-		rval = test_arg(arg, arg->num.right);
+		rval = test_arg(arg, arg->num.right, error_str);
 		if (rval != FILTER_VAL_NORM)
 			return rval;
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_OP:
 		if (arg->op.type != FILTER_OP_NOT) {
-			lval = test_arg(arg, arg->op.left);
+			lval = test_arg(arg, arg->op.left, error_str);
 			switch (lval) {
 			case FILTER_VAL_NORM:
 				break;
 			case FILTER_VAL_TRUE:
 				if (arg->op.type == FILTER_OP_OR)
 					return FILTER_VAL_TRUE;
-				rval = test_arg(arg, arg->op.right);
+				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
 					return rval;
 
-				reparent_op_arg(parent, arg, arg->op.right);
-				return FILTER_VAL_NORM;
+				return reparent_op_arg(parent, arg, arg->op.right,
+						       error_str);
 
 			case FILTER_VAL_FALSE:
 				if (arg->op.type == FILTER_OP_AND)
 					return FILTER_VAL_FALSE;
-				rval = test_arg(arg, arg->op.right);
+				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
 					return rval;
 
-				reparent_op_arg(parent, arg, arg->op.right);
-				return FILTER_VAL_NORM;
+				return reparent_op_arg(parent, arg, arg->op.right,
+						       error_str);
+
+			default:
+				return lval;
 			}
 		}
 
-		rval = test_arg(arg, arg->op.right);
+		rval = test_arg(arg, arg->op.right, error_str);
 		switch (rval) {
 		case FILTER_VAL_NORM:
+		default:
 			break;
+
 		case FILTER_VAL_TRUE:
 			if (arg->op.type == FILTER_OP_OR)
 				return FILTER_VAL_TRUE;
 			if (arg->op.type == FILTER_OP_NOT)
 				return FILTER_VAL_FALSE;
 
-			reparent_op_arg(parent, arg, arg->op.left);
-			return FILTER_VAL_NORM;
+			return reparent_op_arg(parent, arg, arg->op.left,
+					       error_str);
 
 		case FILTER_VAL_FALSE:
 			if (arg->op.type == FILTER_OP_AND)
@@ -852,39 +924,54 @@ enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
 			if (arg->op.type == FILTER_OP_NOT)
 				return FILTER_VAL_TRUE;
 
-			reparent_op_arg(parent, arg, arg->op.left);
-			return FILTER_VAL_NORM;
+			return reparent_op_arg(parent, arg, arg->op.left,
+					       error_str);
 		}
 
-		return FILTER_VAL_NORM;
+		return rval;
 	default:
-		die("bad arg in filter tree");
+		show_error(error_str, "bad arg in filter tree");
+		return PEVENT_ERRNO__BAD_FILTER_ARG;
 	}
 	return FILTER_VAL_NORM;
 }
 
 /* Remove any unknown event fields */
-static struct filter_arg *collapse_tree(struct filter_arg *arg)
+static int collapse_tree(struct filter_arg *arg,
+			 struct filter_arg **arg_collapsed, char **error_str)
 {
-	enum filter_vals ret;
+	int ret;
 
-	ret = test_arg(arg, arg);
+	ret = test_arg(arg, arg, error_str);
 	switch (ret) {
 	case FILTER_VAL_NORM:
-		return arg;
+		break;
 
 	case FILTER_VAL_TRUE:
 	case FILTER_VAL_FALSE:
 		free_arg(arg);
 		arg = allocate_arg();
-		arg->type = FILTER_ARG_BOOLEAN;
-		arg->boolean.value = ret == FILTER_VAL_TRUE;
+		if (arg) {
+			arg->type = FILTER_ARG_BOOLEAN;
+			arg->boolean.value = ret == FILTER_VAL_TRUE;
+		} else {
+			show_error(error_str, "Failed to allocate filter arg");
+			ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
+		break;
+
+	default:
+		/* test_arg() already set the error_str */
+		free_arg(arg);
+		arg = NULL;
+		break;
 	}
 
-	return arg;
+	*arg_collapsed = arg;
+	return ret;
 }
 
-static int
+static enum pevent_errno
 process_filter(struct event_format *event, struct filter_arg **parg,
 	       char **error_str, int not)
 {
@@ -898,7 +985,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 	enum filter_op_type btype;
 	enum filter_exp_type etype;
 	enum filter_cmp_type ctype;
-	int ret;
+	enum pevent_errno ret;
 
 	*parg = NULL;
 
@@ -909,8 +996,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		case EVENT_SQUOTE:
 		case EVENT_DQUOTE:
 		case EVENT_ITEM:
-			arg = create_arg_item(event, token, type, error_str);
-			if (!arg)
+			ret = create_arg_item(event, token, type, &arg, error_str);
+			if (ret < 0)
 				goto fail;
 			if (!left_item)
 				left_item = arg;
@@ -923,20 +1010,20 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				if (not) {
 					arg = NULL;
 					if (current_op)
-						goto fail_print;
+						goto fail_syntax;
 					free(token);
 					*parg = current_exp;
 					return 0;
 				}
 			} else
-				goto fail_print;
+				goto fail_syntax;
 			arg = NULL;
 			break;
 
 		case EVENT_DELIM:
 			if (*token == ',') {
-				show_error(error_str,
-					   "Illegal token ','");
+				show_error(error_str, "Illegal token ','");
+				ret = PEVENT_ERRNO__ILLEGAL_TOKEN;
 				goto fail;
 			}
 
@@ -944,19 +1031,23 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				if (left_item) {
 					show_error(error_str,
 						   "Open paren can not come after item");
+					ret = PEVENT_ERRNO__INVALID_PAREN;
 					goto fail;
 				}
 				if (current_exp) {
 					show_error(error_str,
 						   "Open paren can not come after expression");
+					ret = PEVENT_ERRNO__INVALID_PAREN;
 					goto fail;
 				}
 
 				ret = process_filter(event, &arg, error_str, 0);
-				if (ret != 1) {
-					if (ret == 0)
+				if (ret != PEVENT_ERRNO__UNBALANCED_PAREN) {
+					if (ret == 0) {
 						show_error(error_str,
 							   "Unbalanced number of '('");
+						ret = PEVENT_ERRNO__UNBALANCED_PAREN;
+					}
 					goto fail;
 				}
 				ret = 0;
@@ -964,7 +1055,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				/* A not wants just one expression */
 				if (not) {
 					if (current_op)
-						goto fail_print;
+						goto fail_syntax;
 					*parg = arg;
 					return 0;
 				}
@@ -979,19 +1070,19 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 			} else { /* ')' */
 				if (!current_op && !current_exp)
-					goto fail_print;
+					goto fail_syntax;
 
 				/* Make sure everything is finished at this level */
 				if (current_exp && !check_op_done(current_exp))
-					goto fail_print;
+					goto fail_syntax;
 				if (current_op && !check_op_done(current_op))
-					goto fail_print;
+					goto fail_syntax;
 
 				if (current_op)
 					*parg = current_op;
 				else
 					*parg = current_exp;
-				return 1;
+				return PEVENT_ERRNO__UNBALANCED_PAREN;
 			}
 			break;
 
@@ -1003,21 +1094,22 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			case OP_BOOL:
 				/* Logic ops need a left expression */
 				if (!current_exp && !current_op)
-					goto fail_print;
+					goto fail_syntax;
 				/* fall through */
 			case OP_NOT:
 				/* logic only processes ops and exp */
 				if (left_item)
-					goto fail_print;
+					goto fail_syntax;
 				break;
 			case OP_EXP:
 			case OP_CMP:
 				if (!left_item)
-					goto fail_print;
+					goto fail_syntax;
 				break;
 			case OP_NONE:
 				show_error(error_str,
 					   "Unknown op token %s", token);
+				ret = PEVENT_ERRNO__UNKNOWN_TOKEN;
 				goto fail;
 			}
 
@@ -1025,6 +1117,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			switch (op_type) {
 			case OP_BOOL:
 				arg = create_arg_op(btype);
+				if (arg == NULL)
+					goto fail_alloc;
 				if (current_op)
 					ret = add_left(arg, current_op);
 				else
@@ -1035,6 +1129,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 			case OP_NOT:
 				arg = create_arg_op(btype);
+				if (arg == NULL)
+					goto fail_alloc;
 				if (current_op)
 					ret = add_right(current_op, arg, error_str);
 				if (ret < 0)
@@ -1054,6 +1150,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 					arg = create_arg_exp(etype);
 				else
 					arg = create_arg_cmp(ctype);
+				if (arg == NULL)
+					goto fail_alloc;
 
 				if (current_op)
 					ret = add_right(current_op, arg, error_str);
@@ -1062,7 +1160,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				ret = add_left(arg, left_item);
 				if (ret < 0) {
 					arg = NULL;
-					goto fail_print;
+					goto fail_syntax;
 				}
 				current_exp = arg;
 				break;
@@ -1071,38 +1169,47 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			}
 			arg = NULL;
 			if (ret < 0)
-				goto fail_print;
+				goto fail_syntax;
 			break;
 		case EVENT_NONE:
 			break;
+		case EVENT_ERROR:
+			goto fail_alloc;
 		default:
-			goto fail_print;
+			goto fail_syntax;
 		}
 	} while (type != EVENT_NONE);
 
 	if (!current_op && !current_exp)
-		goto fail_print;
+		goto fail_syntax;
 
 	if (!current_op)
 		current_op = current_exp;
 
-	current_op = collapse_tree(current_op);
+	ret = collapse_tree(current_op, parg, error_str);
+	if (ret < 0)
+		goto fail;
 
 	*parg = current_op;
 
 	return 0;
 
- fail_print:
+ fail_alloc:
+	show_error(error_str, "failed to allocate filter arg");
+	ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+	goto fail;
+ fail_syntax:
 	show_error(error_str, "Syntax error");
+	ret = PEVENT_ERRNO__SYNTAX_ERROR;
  fail:
 	free_arg(current_op);
 	free_arg(current_exp);
 	free_arg(arg);
 	free(token);
-	return -1;
+	return ret;
 }
 
-static int
+static enum pevent_errno
 process_event(struct event_format *event, const char *filter_str,
 	      struct filter_arg **parg, char **error_str)
 {
@@ -1111,17 +1218,15 @@ process_event(struct event_format *event, const char *filter_str,
 	pevent_buffer_init(filter_str, strlen(filter_str));
 
 	ret = process_filter(event, parg, error_str, 0);
-	if (ret == 1) {
-		show_error(error_str,
-			   "Unbalanced number of ')'");
-		return -1;
-	}
 	if (ret < 0)
 		return ret;
 
 	/* If parg is NULL, then make it into FALSE */
 	if (!*parg) {
 		*parg = allocate_arg();
+		if (*parg == NULL)
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 		(*parg)->type = FILTER_ARG_BOOLEAN;
 		(*parg)->boolean.value = FILTER_FALSE;
 	}
@@ -1129,13 +1234,13 @@ process_event(struct event_format *event, const char *filter_str,
 	return 0;
 }
 
-static int filter_event(struct event_filter *filter,
-			struct event_format *event,
-			const char *filter_str, char **error_str)
+static enum pevent_errno
+filter_event(struct event_filter *filter, struct event_format *event,
+	     const char *filter_str, char **error_str)
 {
 	struct filter_type *filter_type;
 	struct filter_arg *arg;
-	int ret;
+	enum pevent_errno ret;
 
 	if (filter_str) {
 		ret = process_event(event, filter_str, &arg, error_str);
@@ -1145,11 +1250,17 @@ static int filter_event(struct event_filter *filter,
 	} else {
 		/* just add a TRUE arg */
 		arg = allocate_arg();
+		if (arg == NULL)
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 		arg->type = FILTER_ARG_BOOLEAN;
 		arg->boolean.value = FILTER_TRUE;
 	}
 
 	filter_type = add_filter_type(filter, event->id);
+	if (filter_type == NULL)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
 	filter_type->filter = arg;
@@ -1161,18 +1272,12 @@ static int filter_event(struct event_filter *filter,
  * pevent_filter_add_filter_str - add a new filter
  * @filter: the event filter to add to
  * @filter_str: the filter string that contains the filter
- * @error_str: string containing reason for failed filter
  *
- * Returns 0 if the filter was successfully added
- *   -1 if there was an error.
- *
- * On error, if @error_str points to a string pointer,
- * it is set to the reason that the filter failed.
- * This string must be freed with "free".
+ * Returns 0 if the filter was successfully added or a
+ * negative error code.
  */
-int pevent_filter_add_filter_str(struct event_filter *filter,
-				 const char *filter_str,
-				 char **error_str)
+enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
+					       const char *filter_str)
 {
 	struct pevent *pevent = filter->pevent;
 	struct event_list *event;
@@ -1183,23 +1288,20 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	char *event_name = NULL;
 	char *sys_name = NULL;
 	char *sp;
-	int rtn = 0;
+	enum pevent_errno rtn = 0; /* PEVENT_ERRNO__SUCCESS */
 	int len;
 	int ret;
+	char *error_str = NULL;
 
 	/* clear buffer to reset show error */
 	pevent_buffer_init("", 0);
 
-	if (error_str)
-		*error_str = NULL;
-
 	filter_start = strchr(filter_str, ':');
 	if (filter_start)
 		len = filter_start - filter_str;
 	else
 		len = strlen(filter_str);
 
-
 	do {
 		next_event = strchr(filter_str, ',');
 		if (next_event &&
@@ -1210,7 +1312,12 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		else
 			len = strlen(filter_str);
 
-		this_event = malloc_or_die(len + 1);
+		this_event = malloc(len + 1);
+		if (this_event == NULL) {
+			/* This can only happen when events is NULL, but still */
+			free_events(events);
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
 		memcpy(this_event, filter_str, len);
 		this_event[len] = 0;
 
@@ -1223,27 +1330,18 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		event_name = strtok_r(NULL, "/", &sp);
 
 		if (!sys_name) {
-			show_error(error_str, "No filter found");
 			/* This can only happen when events is NULL, but still */
 			free_events(events);
 			free(this_event);
-			return -1;
+			return PEVENT_ERRNO__FILTER_NOT_FOUND;
 		}
 
 		/* Find this event */
 		ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
 		if (ret < 0) {
-			if (event_name)
-				show_error(error_str,
-					   "No event found under '%s.%s'",
-					   sys_name, event_name);
-			else
-				show_error(error_str,
-					   "No event found under '%s'",
-					   sys_name);
 			free_events(events);
 			free(this_event);
-			return -1;
+			return ret;
 		}
 		free(this_event);
 	} while (filter_str);
@@ -1255,7 +1353,7 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	/* filter starts here */
 	for (event = events; event; event = event->next) {
 		ret = filter_event(filter, event->event, filter_start,
-				   error_str);
+				   &error_str);
 		/* Failures are returned if a parse error happened */
 		if (ret < 0)
 			rtn = ret;
@@ -1263,8 +1361,10 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		if (ret >= 0 && pevent->test_filters) {
 			char *test;
 			test = pevent_filter_make_string(filter, event->event->id);
-			printf(" '%s: %s'\n", event->event->name, test);
-			free(test);
+			if (test) {
+				printf(" '%s: %s'\n", event->event->name, test);
+				free(test);
+			}
 		}
 	}
 
@@ -1374,6 +1474,9 @@ static int copy_filter_type(struct event_filter *filter,
 	if (strcmp(str, "TRUE") == 0 || strcmp(str, "FALSE") == 0) {
 		/* Add trivial event */
 		arg = allocate_arg();
+		if (arg == NULL)
+			return -1;
+
 		arg->type = FILTER_ARG_BOOLEAN;
 		if (strcmp(str, "TRUE") == 0)
 			arg->boolean.value = 1;
@@ -1381,6 +1484,9 @@ static int copy_filter_type(struct event_filter *filter,
 			arg->boolean.value = 0;
 
 		filter_type = add_filter_type(filter, event->id);
+		if (filter_type == NULL)
+			return -1;
+
 		filter_type->filter = arg;
 
 		free(str);
@@ -1482,8 +1588,10 @@ int pevent_update_trivial(struct event_filter *dest, struct event_filter *source
  * @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.
  */
-void pevent_filter_clear_trivial(struct event_filter *filter,
+int pevent_filter_clear_trivial(struct event_filter *filter,
 				 enum filter_trivial_type type)
 {
 	struct filter_type *filter_type;
@@ -1492,13 +1600,15 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 	int i;
 
 	if (!filter->filters)
-		return;
+		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 != FILTER_ARG_BOOLEAN)
 			continue;
@@ -1513,19 +1623,24 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 			break;
 		}
 
-		ids = realloc(ids, sizeof(*ids) * (count + 1));
-		if (!ids)
-			die("Can't allocate ids");
+		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;
+		return 0;
 
 	for (i = 0; i < count; i++)
 		pevent_filter_remove_event(filter, ids[i]);
 
 	free(ids);
+	return 0;
 }
 
 /**
@@ -1565,8 +1680,8 @@ int pevent_filter_event_has_trivial(struct event_filter *filter,
 	}
 }
 
-static int test_filter(struct event_format *event,
-		       struct filter_arg *arg, struct pevent_record *record);
+static int test_filter(struct event_format *event, struct filter_arg *arg,
+		       struct pevent_record *record, enum pevent_errno *err);
 
 static const char *
 get_comm(struct event_format *event, struct pevent_record *record)
@@ -1612,15 +1727,24 @@ get_value(struct event_format *event,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record);
+get_arg_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err);
 
 static unsigned long long
-get_exp_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record)
+get_exp_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err)
 {
 	unsigned long long lval, rval;
 
-	lval = get_arg_value(event, arg->exp.left, record);
-	rval = get_arg_value(event, arg->exp.right, record);
+	lval = get_arg_value(event, arg->exp.left, record, err);
+	rval = get_arg_value(event, arg->exp.right, record, err);
+
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
 
 	switch (arg->exp.type) {
 	case FILTER_EXP_ADD:
@@ -1655,39 +1779,51 @@ get_exp_value(struct event_format *event, struct filter_arg *arg, struct pevent_
 
 	case FILTER_EXP_NOT:
 	default:
-		die("error in exp");
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_EXP_TYPE;
 	}
 	return 0;
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record)
+get_arg_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err)
 {
 	switch (arg->type) {
 	case FILTER_ARG_FIELD:
 		return get_value(event, arg->field.field, record);
 
 	case FILTER_ARG_VALUE:
-		if (arg->value.type != FILTER_NUMBER)
-			die("must have number field!");
+		if (arg->value.type != FILTER_NUMBER) {
+			if (!*err)
+				*err = PEVENT_ERRNO__NOT_A_NUMBER;
+		}
 		return arg->value.val;
 
 	case FILTER_ARG_EXP:
-		return get_exp_value(event, arg, record);
+		return get_exp_value(event, arg, record, err);
 
 	default:
-		die("oops in filter");
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_ARG_TYPE;
 	}
 	return 0;
 }
 
-static int test_num(struct event_format *event,
-		    struct filter_arg *arg, struct pevent_record *record)
+static int test_num(struct event_format *event, struct filter_arg *arg,
+		    struct pevent_record *record, enum pevent_errno *err)
 {
 	unsigned long long lval, rval;
 
-	lval = get_arg_value(event, arg->num.left, record);
-	rval = get_arg_value(event, arg->num.right, record);
+	lval = get_arg_value(event, arg->num.left, record, err);
+	rval = get_arg_value(event, arg->num.right, record, err);
+
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
 
 	switch (arg->num.type) {
 	case FILTER_CMP_EQ:
@@ -1709,7 +1845,8 @@ static int test_num(struct event_format *event,
 		return lval <= rval;
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__ILLEGAL_INTEGER_CMP;
 		return 0;
 	}
 }
@@ -1756,8 +1893,8 @@ static const char *get_field_str(struct filter_arg *arg, struct pevent_record *r
 	return val;
 }
 
-static int test_str(struct event_format *event,
-		    struct filter_arg *arg, struct pevent_record *record)
+static int test_str(struct event_format *event, struct filter_arg *arg,
+		    struct pevent_record *record, enum pevent_errno *err)
 {
 	const char *val;
 
@@ -1781,48 +1918,57 @@ static int test_str(struct event_format *event,
 		return regexec(&arg->str.reg, val, 0, NULL, 0);
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__ILLEGAL_STRING_CMP;
 		return 0;
 	}
 }
 
-static int test_op(struct event_format *event,
-		   struct filter_arg *arg, struct pevent_record *record)
+static int test_op(struct event_format *event, struct filter_arg *arg,
+		   struct pevent_record *record, enum pevent_errno *err)
 {
 	switch (arg->op.type) {
 	case FILTER_OP_AND:
-		return test_filter(event, arg->op.left, record) &&
-			test_filter(event, arg->op.right, record);
+		return test_filter(event, arg->op.left, record, err) &&
+			test_filter(event, arg->op.right, record, err);
 
 	case FILTER_OP_OR:
-		return test_filter(event, arg->op.left, record) ||
-			test_filter(event, arg->op.right, record);
+		return test_filter(event, arg->op.left, record, err) ||
+			test_filter(event, arg->op.right, record, err);
 
 	case FILTER_OP_NOT:
-		return !test_filter(event, arg->op.right, record);
+		return !test_filter(event, arg->op.right, record, err);
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_OP_TYPE;
 		return 0;
 	}
 }
 
-static int test_filter(struct event_format *event,
-		       struct filter_arg *arg, struct pevent_record *record)
+static int test_filter(struct event_format *event, struct filter_arg *arg,
+		       struct pevent_record *record, enum pevent_errno *err)
 {
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
+
 	switch (arg->type) {
 	case FILTER_ARG_BOOLEAN:
 		/* easy case */
 		return arg->boolean.value;
 
 	case FILTER_ARG_OP:
-		return test_op(event, arg, record);
+		return test_op(event, arg, record, err);
 
 	case FILTER_ARG_NUM:
-		return test_num(event, arg, record);
+		return test_num(event, arg, record, err);
 
 	case FILTER_ARG_STR:
-		return test_str(event, arg, record);
+		return test_str(event, arg, record, err);
 
 	case FILTER_ARG_EXP:
 	case FILTER_ARG_VALUE:
@@ -1831,11 +1977,11 @@ static int test_filter(struct event_format *event,
 		 * Expressions, fields and values evaluate
 		 * to true if they return non zero
 		 */
-		return !!get_arg_value(event, arg, record);
+		return !!get_arg_value(event, arg, record, err);
 
 	default:
-		die("oops!");
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_ARG_TYPE;
 		return 0;
 	}
 }
@@ -1848,8 +1994,7 @@ static int test_filter(struct event_format *event,
  * Returns 1 if filter found for @event_id
  *   otherwise 0;
  */
-int pevent_event_filtered(struct event_filter *filter,
-			  int event_id)
+int pevent_event_filtered(struct event_filter *filter, int event_id)
 {
 	struct filter_type *filter_type;
 
@@ -1866,31 +2011,36 @@ int pevent_event_filtered(struct event_filter *filter,
  * @filter: filter struct with filter information
  * @record: the record to test against the filter
  *
- * Returns:
- *  1 - filter found for event and @record matches
- *  0 - filter found for event and @record does not match
- * -1 - no filter found for @record's event
- * -2 - if no filters exist
+ * Returns: match result or error code (prefixed with PEVENT_ERRNO__)
+ * FILTER_MATCH - filter found for event and @record matches
+ * FILTER_MISS  - filter found for event and @record does not match
+ * FILTER_NOT_FOUND - no filter found for @record's event
+ * NO_FILTER - if no filters exist
+ * otherwise - error occurred during test
  */
-int pevent_filter_match(struct event_filter *filter,
-			struct pevent_record *record)
+enum pevent_errno pevent_filter_match(struct event_filter *filter,
+				      struct pevent_record *record)
 {
 	struct pevent *pevent = filter->pevent;
 	struct filter_type *filter_type;
 	int event_id;
+	int ret;
+	enum pevent_errno err = 0;
 
 	if (!filter->filters)
-		return FILTER_NONE;
+		return PEVENT_ERRNO__NO_FILTER;
 
 	event_id = pevent_data_type(pevent, record);
 
 	filter_type = find_filter_type(filter, event_id);
-
 	if (!filter_type)
-		return FILTER_NOEXIST;
+		return PEVENT_ERRNO__FILTER_NOT_FOUND;
 
-	return test_filter(filter_type->event, filter_type->filter, record) ?
-		FILTER_MATCH : FILTER_MISS;
+	ret = test_filter(filter_type->event, filter_type->filter, record, &err);
+	if (err)
+		return err;
+
+	return ret ? PEVENT_ERRNO__FILTER_MATCH : PEVENT_ERRNO__FILTER_MISS;
 }
 
 static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
@@ -1902,7 +2052,6 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	int left_val = -1;
 	int right_val = -1;
 	int val;
-	int len;
 
 	switch (arg->op.type) {
 	case FILTER_OP_AND:
@@ -1949,11 +2098,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 				default:
 					break;
 				}
-				str = malloc_or_die(6);
-				if (val)
-					strcpy(str, "TRUE");
-				else
-					strcpy(str, "FALSE");
+				asprintf(&str, val ? "TRUE" : "FALSE");
 				break;
 			}
 		}
@@ -1971,10 +2116,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			break;
 		}
 
-		len = strlen(left) + strlen(right) + strlen(op) + 10;
-		str = malloc_or_die(len);
-		snprintf(str, len, "(%s) %s (%s)",
-			 left, op, right);
+		asprintf(&str, "(%s) %s (%s)", left, op, right);
 		break;
 
 	case FILTER_OP_NOT:
@@ -1990,16 +2132,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			right_val = 0;
 		if (right_val >= 0) {
 			/* just return the opposite */
-			str = malloc_or_die(6);
-			if (right_val)
-				strcpy(str, "FALSE");
-			else
-				strcpy(str, "TRUE");
+			asprintf(&str, right_val ? "FALSE" : "TRUE");
 			break;
 		}
-		len = strlen(right) + strlen(op) + 3;
-		str = malloc_or_die(len);
-		snprintf(str, len, "%s(%s)", op, right);
+		asprintf(&str, "%s(%s)", op, right);
 		break;
 
 	default:
@@ -2013,11 +2149,9 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
-	char *str;
-
-	str = malloc_or_die(30);
+	char *str = NULL;
 
-	snprintf(str, 30, "%lld", arg->value.val);
+	asprintf(&str, "%lld", arg->value.val);
 
 	return str;
 }
@@ -2033,7 +2167,6 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *rstr;
 	char *op;
 	char *str = NULL;
-	int len;
 
 	lstr = arg_to_str(filter, arg->exp.left);
 	rstr = arg_to_str(filter, arg->exp.right);
@@ -2072,12 +2205,11 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 		op = "^";
 		break;
 	default:
-		die("oops in exp");
+		op = "[ERROR IN EXPRESSION TYPE]";
+		break;
 	}
 
-	len = strlen(op) + strlen(lstr) + strlen(rstr) + 4;
-	str = malloc_or_die(len);
-	snprintf(str, len, "%s %s %s", lstr, op, rstr);
+	asprintf(&str, "%s %s %s", lstr, op, rstr);
 out:
 	free(lstr);
 	free(rstr);
@@ -2091,7 +2223,6 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *rstr;
 	char *str = NULL;
 	char *op = NULL;
-	int len;
 
 	lstr = arg_to_str(filter, arg->num.left);
 	rstr = arg_to_str(filter, arg->num.right);
@@ -2122,10 +2253,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 		if (!op)
 			op = "<=";
 
-		len = strlen(lstr) + strlen(op) + strlen(rstr) + 4;
-		str = malloc_or_die(len);
-		sprintf(str, "%s %s %s", lstr, op, rstr);
-
+		asprintf(&str, "%s %s %s", lstr, op, rstr);
 		break;
 
 	default:
@@ -2143,7 +2271,6 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
 	char *str = NULL;
 	char *op = NULL;
-	int len;
 
 	switch (arg->str.type) {
 	case FILTER_CMP_MATCH:
@@ -2161,12 +2288,8 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 		if (!op)
 			op = "!~";
 
-		len = strlen(arg->str.field->name) + strlen(op) +
-			strlen(arg->str.val) + 6;
-		str = malloc_or_die(len);
-		snprintf(str, len, "%s %s \"%s\"",
-			 arg->str.field->name,
-			 op, arg->str.val);
+		asprintf(&str, "%s %s \"%s\"",
+			 arg->str.field->name, op, arg->str.val);
 		break;
 
 	default:
@@ -2178,15 +2301,11 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
-	char *str;
+	char *str = NULL;
 
 	switch (arg->type) {
 	case FILTER_ARG_BOOLEAN:
-		str = malloc_or_die(6);
-		if (arg->boolean.value)
-			strcpy(str, "TRUE");
-		else
-			strcpy(str, "FALSE");
+		asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
 		return str;
 
 	case FILTER_ARG_OP:
@@ -2221,7 +2340,7 @@ static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
  *
  * Returns a string that displays the filter contents.
  *  This string must be freed with free(str).
- *  NULL is returned if no filter is found.
+ *  NULL is returned if no filter is found or allocation failed.
  */
 char *
 pevent_filter_make_string(struct event_filter *filter, int event_id)
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
new file mode 100644
index 000000000000..dcab8e873c21
--- /dev/null
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -0,0 +1,24 @@
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <endian.h>
+#include "event-parse.h"
+
+static unsigned long long
+process___le16_to_cpup(struct trace_seq *s,
+		       unsigned long long *args)
+{
+	uint16_t *val = (uint16_t *) args[0];
+	return val ? (long long) le16toh(*val) : 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process___le16_to_cpup,
+				       PEVENT_FUNC_ARG_INT,
+				       "__le16_to_cpup",
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
new file mode 100644
index 000000000000..aad92ad5e96f
--- /dev/null
+++ b/tools/lib/traceevent/plugin_function.c
@@ -0,0 +1,160 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+#include "event-utils.h"
+
+static struct func_stack {
+	int size;
+	char **stack;
+} *fstack;
+
+static int cpus = -1;
+
+#define STK_BLK 10
+
+static void add_child(struct func_stack *stack, const char *child, int pos)
+{
+	int i;
+
+	if (!child)
+		return;
+
+	if (pos < stack->size)
+		free(stack->stack[pos]);
+	else {
+		char **ptr;
+
+		ptr = realloc(stack->stack, sizeof(char *) *
+			      (stack->size + STK_BLK));
+		if (!ptr) {
+			warning("could not allocate plugin memory\n");
+			return;
+		}
+
+		stack->stack = ptr;
+
+		for (i = stack->size; i < stack->size + STK_BLK; i++)
+			stack->stack[i] = NULL;
+		stack->size += STK_BLK;
+	}
+
+	stack->stack[pos] = strdup(child);
+}
+
+static int add_and_get_index(const char *parent, const char *child, int cpu)
+{
+	int i;
+
+	if (cpu < 0)
+		return 0;
+
+	if (cpu > cpus) {
+		struct func_stack *ptr;
+
+		ptr = realloc(fstack, sizeof(*fstack) * (cpu + 1));
+		if (!ptr) {
+			warning("could not allocate plugin memory\n");
+			return 0;
+		}
+
+		fstack = ptr;
+
+		/* Account for holes in the cpu count */
+		for (i = cpus + 1; i <= cpu; i++)
+			memset(&fstack[i], 0, sizeof(fstack[i]));
+		cpus = cpu;
+	}
+
+	for (i = 0; i < fstack[cpu].size && fstack[cpu].stack[i]; i++) {
+		if (strcmp(parent, fstack[cpu].stack[i]) == 0) {
+			add_child(&fstack[cpu], child, i+1);
+			return i;
+		}
+	}
+
+	/* Not found */
+	add_child(&fstack[cpu], parent, 0);
+	add_child(&fstack[cpu], child, 1);
+	return 0;
+}
+
+static int function_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	struct pevent *pevent = event->pevent;
+	unsigned long long function;
+	unsigned long long pfunction;
+	const char *func;
+	const char *parent;
+	int index;
+
+	if (pevent_get_field_val(s, event, "ip", record, &function, 1))
+		return trace_seq_putc(s, '!');
+
+	func = pevent_find_function(pevent, function);
+
+	if (pevent_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
+		return trace_seq_putc(s, '!');
+
+	parent = pevent_find_function(pevent, pfunction);
+
+	index = add_and_get_index(parent, func, record->cpu);
+
+	trace_seq_printf(s, "%*s", index*3, "");
+
+	if (func)
+		trace_seq_printf(s, "%s", func);
+	else
+		trace_seq_printf(s, "0x%llx", function);
+
+	trace_seq_printf(s, " <-- ");
+	if (parent)
+		trace_seq_printf(s, "%s", parent);
+	else
+		trace_seq_printf(s, "0x%llx", pfunction);
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "ftrace", "function",
+				      function_handler, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(void)
+{
+	int i, x;
+
+	for (i = 0; i <= cpus; i++) {
+		for (x = 0; x < fstack[i].size && fstack[i].stack[x]; x++)
+			free(fstack[i].stack[x]);
+		free(fstack[i].stack);
+	}
+
+	free(fstack);
+	fstack = NULL;
+	cpus = -1;
+}
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
new file mode 100644
index 000000000000..0b0ebf30aa44
--- /dev/null
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static int timer_expire_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	trace_seq_printf(s, "hrtimer=");
+
+	if (pevent_print_num_field(s, "0x%llx", event, "timer",
+				   record, 0) == -1)
+		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
+				       record, 1);
+
+	trace_seq_printf(s, " now=");
+
+	pevent_print_num_field(s, "%llu", event, "now", record, 1);
+
+	pevent_print_func_field(s, " function=%s", event, "function",
+				record, 0);
+	return 0;
+}
+
+static int timer_start_handler(struct trace_seq *s,
+			       struct pevent_record *record,
+			       struct event_format *event, void *context)
+{
+	trace_seq_printf(s, "hrtimer=");
+
+	if (pevent_print_num_field(s, "0x%llx", event, "timer",
+				   record, 0) == -1)
+		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
+				       record, 1);
+
+	pevent_print_func_field(s, " function=%s", event, "function",
+				record, 0);
+
+	trace_seq_printf(s, " expires=");
+	pevent_print_num_field(s, "%llu", event, "expires", record, 1);
+
+	trace_seq_printf(s, " softexpires=");
+	pevent_print_num_field(s, "%llu", event, "softexpires", record, 1);
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1,
+				      "timer", "hrtimer_expire_entry",
+				      timer_expire_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+				      timer_start_handler, NULL);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
new file mode 100644
index 000000000000..2f93f81f0bac
--- /dev/null
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+#define MINORBITS	20
+#define MINORMASK	((1U << MINORBITS) - 1)
+
+#define MAJOR(dev)	((unsigned int) ((dev) >> MINORBITS))
+#define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
+
+static unsigned long long
+process_jbd2_dev_to_name(struct trace_seq *s,
+			 unsigned long long *args)
+{
+	unsigned int dev = args[0];
+
+	trace_seq_printf(s, "%d:%d", MAJOR(dev), MINOR(dev));
+	return 0;
+}
+
+static unsigned long long
+process_jiffies_to_msecs(struct trace_seq *s,
+			 unsigned long long *args)
+{
+	unsigned long long jiffies = args[0];
+
+	trace_seq_printf(s, "%lld", jiffies);
+	return jiffies;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_jbd2_dev_to_name,
+				       PEVENT_FUNC_ARG_STRING,
+				       "jbd2_dev_to_name",
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+
+	pevent_register_print_function(pevent,
+				       process_jiffies_to_msecs,
+				       PEVENT_FUNC_ARG_LONG,
+				       "jiffies_to_msecs",
+				       PEVENT_FUNC_ARG_LONG,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
new file mode 100644
index 000000000000..7115c8037ea8
--- /dev/null
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static int call_site_handler(struct trace_seq *s, struct pevent_record *record,
+			     struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val, addr;
+	void *data = record->data;
+	const char *func;
+
+	field = pevent_find_field(event, "call_site");
+	if (!field)
+		return 1;
+
+	if (pevent_read_number_field(field, data, &val))
+		return 1;
+
+	func = pevent_find_function(event->pevent, val);
+	if (!func)
+		return 1;
+
+	addr = pevent_find_function_address(event->pevent, val);
+
+	trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
+	return 1;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "kmem", "kfree",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmalloc",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem",
+				      "kmem_cache_alloc_node",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+				      call_site_handler, NULL);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
new file mode 100644
index 000000000000..a0e282c6b967
--- /dev/null
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -0,0 +1,436 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+
+#include "event-parse.h"
+
+#ifdef HAVE_UDIS86
+
+#include <udis86.h>
+
+static ud_t ud;
+
+static void init_disassembler(void)
+{
+	ud_init(&ud);
+	ud_set_syntax(&ud, UD_SYN_ATT);
+}
+
+static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
+			       int cr0_pe, int eflags_vm,
+			       int cs_d, int cs_l)
+{
+	int mode;
+
+	if (!cr0_pe)
+		mode = 16;
+	else if (eflags_vm)
+		mode = 16;
+	else if (cs_l)
+		mode = 64;
+	else if (cs_d)
+		mode = 32;
+	else
+		mode = 16;
+
+	ud_set_pc(&ud, rip);
+	ud_set_mode(&ud, mode);
+	ud_set_input_buffer(&ud, insn, len);
+	ud_disassemble(&ud);
+	return ud_insn_asm(&ud);
+}
+
+#else
+
+static void init_disassembler(void)
+{
+}
+
+static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
+			       int cr0_pe, int eflags_vm,
+			       int cs_d, int cs_l)
+{
+	static char out[15*3+1];
+	int i;
+
+	for (i = 0; i < len; ++i)
+		sprintf(out + i * 3, "%02x ", insn[i]);
+	out[len*3-1] = '\0';
+	return out;
+}
+
+#endif
+
+
+#define VMX_EXIT_REASONS			\
+	_ER(EXCEPTION_NMI,	 0)		\
+	_ER(EXTERNAL_INTERRUPT,	 1)		\
+	_ER(TRIPLE_FAULT,	 2)		\
+	_ER(PENDING_INTERRUPT,	 7)		\
+	_ER(NMI_WINDOW,		 8)		\
+	_ER(TASK_SWITCH,	 9)		\
+	_ER(CPUID,		 10)		\
+	_ER(HLT,		 12)		\
+	_ER(INVD,		 13)		\
+	_ER(INVLPG,		 14)		\
+	_ER(RDPMC,		 15)		\
+	_ER(RDTSC,		 16)		\
+	_ER(VMCALL,		 18)		\
+	_ER(VMCLEAR,		 19)		\
+	_ER(VMLAUNCH,		 20)		\
+	_ER(VMPTRLD,		 21)		\
+	_ER(VMPTRST,		 22)		\
+	_ER(VMREAD,		 23)		\
+	_ER(VMRESUME,		 24)		\
+	_ER(VMWRITE,		 25)		\
+	_ER(VMOFF,		 26)		\
+	_ER(VMON,		 27)		\
+	_ER(CR_ACCESS,		 28)		\
+	_ER(DR_ACCESS,		 29)		\
+	_ER(IO_INSTRUCTION,	 30)		\
+	_ER(MSR_READ,		 31)		\
+	_ER(MSR_WRITE,		 32)		\
+	_ER(MWAIT_INSTRUCTION,	 36)		\
+	_ER(MONITOR_INSTRUCTION, 39)		\
+	_ER(PAUSE_INSTRUCTION,	 40)		\
+	_ER(MCE_DURING_VMENTRY,	 41)		\
+	_ER(TPR_BELOW_THRESHOLD, 43)		\
+	_ER(APIC_ACCESS,	 44)		\
+	_ER(EOI_INDUCED,	 45)		\
+	_ER(EPT_VIOLATION,	 48)		\
+	_ER(EPT_MISCONFIG,	 49)		\
+	_ER(INVEPT,		 50)		\
+	_ER(PREEMPTION_TIMER,	 52)		\
+	_ER(WBINVD,		 54)		\
+	_ER(XSETBV,		 55)		\
+	_ER(APIC_WRITE,		 56)		\
+	_ER(INVPCID,		 58)
+
+#define SVM_EXIT_REASONS \
+	_ER(EXIT_READ_CR0,	0x000)		\
+	_ER(EXIT_READ_CR3,	0x003)		\
+	_ER(EXIT_READ_CR4,	0x004)		\
+	_ER(EXIT_READ_CR8,	0x008)		\
+	_ER(EXIT_WRITE_CR0,	0x010)		\
+	_ER(EXIT_WRITE_CR3,	0x013)		\
+	_ER(EXIT_WRITE_CR4,	0x014)		\
+	_ER(EXIT_WRITE_CR8,	0x018)		\
+	_ER(EXIT_READ_DR0,	0x020)		\
+	_ER(EXIT_READ_DR1,	0x021)		\
+	_ER(EXIT_READ_DR2,	0x022)		\
+	_ER(EXIT_READ_DR3,	0x023)		\
+	_ER(EXIT_READ_DR4,	0x024)		\
+	_ER(EXIT_READ_DR5,	0x025)		\
+	_ER(EXIT_READ_DR6,	0x026)		\
+	_ER(EXIT_READ_DR7,	0x027)		\
+	_ER(EXIT_WRITE_DR0,	0x030)		\
+	_ER(EXIT_WRITE_DR1,	0x031)		\
+	_ER(EXIT_WRITE_DR2,	0x032)		\
+	_ER(EXIT_WRITE_DR3,	0x033)		\
+	_ER(EXIT_WRITE_DR4,	0x034)		\
+	_ER(EXIT_WRITE_DR5,	0x035)		\
+	_ER(EXIT_WRITE_DR6,	0x036)		\
+	_ER(EXIT_WRITE_DR7,	0x037)		\
+	_ER(EXIT_EXCP_BASE,     0x040)		\
+	_ER(EXIT_INTR,		0x060)		\
+	_ER(EXIT_NMI,		0x061)		\
+	_ER(EXIT_SMI,		0x062)		\
+	_ER(EXIT_INIT,		0x063)		\
+	_ER(EXIT_VINTR,		0x064)		\
+	_ER(EXIT_CR0_SEL_WRITE,	0x065)		\
+	_ER(EXIT_IDTR_READ,	0x066)		\
+	_ER(EXIT_GDTR_READ,	0x067)		\
+	_ER(EXIT_LDTR_READ,	0x068)		\
+	_ER(EXIT_TR_READ,	0x069)		\
+	_ER(EXIT_IDTR_WRITE,	0x06a)		\
+	_ER(EXIT_GDTR_WRITE,	0x06b)		\
+	_ER(EXIT_LDTR_WRITE,	0x06c)		\
+	_ER(EXIT_TR_WRITE,	0x06d)		\
+	_ER(EXIT_RDTSC,		0x06e)		\
+	_ER(EXIT_RDPMC,		0x06f)		\
+	_ER(EXIT_PUSHF,		0x070)		\
+	_ER(EXIT_POPF,		0x071)		\
+	_ER(EXIT_CPUID,		0x072)		\
+	_ER(EXIT_RSM,		0x073)		\
+	_ER(EXIT_IRET,		0x074)		\
+	_ER(EXIT_SWINT,		0x075)		\
+	_ER(EXIT_INVD,		0x076)		\
+	_ER(EXIT_PAUSE,		0x077)		\
+	_ER(EXIT_HLT,		0x078)		\
+	_ER(EXIT_INVLPG,	0x079)		\
+	_ER(EXIT_INVLPGA,	0x07a)		\
+	_ER(EXIT_IOIO,		0x07b)		\
+	_ER(EXIT_MSR,		0x07c)		\
+	_ER(EXIT_TASK_SWITCH,	0x07d)		\
+	_ER(EXIT_FERR_FREEZE,	0x07e)		\
+	_ER(EXIT_SHUTDOWN,	0x07f)		\
+	_ER(EXIT_VMRUN,		0x080)		\
+	_ER(EXIT_VMMCALL,	0x081)		\
+	_ER(EXIT_VMLOAD,	0x082)		\
+	_ER(EXIT_VMSAVE,	0x083)		\
+	_ER(EXIT_STGI,		0x084)		\
+	_ER(EXIT_CLGI,		0x085)		\
+	_ER(EXIT_SKINIT,	0x086)		\
+	_ER(EXIT_RDTSCP,	0x087)		\
+	_ER(EXIT_ICEBP,		0x088)		\
+	_ER(EXIT_WBINVD,	0x089)		\
+	_ER(EXIT_MONITOR,	0x08a)		\
+	_ER(EXIT_MWAIT,		0x08b)		\
+	_ER(EXIT_MWAIT_COND,	0x08c)		\
+	_ER(EXIT_NPF,		0x400)		\
+	_ER(EXIT_ERR,		-1)
+
+#define _ER(reason, val)	{ #reason, val },
+struct str_values {
+	const char	*str;
+	int		val;
+};
+
+static struct str_values vmx_exit_reasons[] = {
+	VMX_EXIT_REASONS
+	{ NULL, -1}
+};
+
+static struct str_values svm_exit_reasons[] = {
+	SVM_EXIT_REASONS
+	{ NULL, -1}
+};
+
+static struct isa_exit_reasons {
+	unsigned isa;
+	struct str_values *strings;
+} isa_exit_reasons[] = {
+	{ .isa = 1, .strings = vmx_exit_reasons },
+	{ .isa = 2, .strings = svm_exit_reasons },
+	{ }
+};
+
+static const char *find_exit_reason(unsigned isa, int val)
+{
+	struct str_values *strings = NULL;
+	int i;
+
+	for (i = 0; isa_exit_reasons[i].strings; ++i)
+		if (isa_exit_reasons[i].isa == isa) {
+			strings = isa_exit_reasons[i].strings;
+			break;
+		}
+	if (!strings)
+		return "UNKNOWN-ISA";
+	for (i = 0; strings[i].val >= 0; i++)
+		if (strings[i].val == val)
+			break;
+	if (strings[i].str)
+		return strings[i].str;
+	return "UNKNOWN";
+}
+
+static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	unsigned long long isa;
+	unsigned long long val;
+	unsigned long long info1 = 0, info2 = 0;
+
+	if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0)
+		isa = 1;
+
+	trace_seq_printf(s, "reason %s", find_exit_reason(isa, val));
+
+	pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1);
+
+	if (pevent_get_field_val(s, event, "info1", record, &info1, 0) >= 0
+	    && pevent_get_field_val(s, event, "info2", record, &info2, 0) >= 0)
+		trace_seq_printf(s, " info %llx %llx", info1, info2);
+
+	return 0;
+}
+
+#define KVM_EMUL_INSN_F_CR0_PE (1 << 0)
+#define KVM_EMUL_INSN_F_EFL_VM (1 << 1)
+#define KVM_EMUL_INSN_F_CS_D   (1 << 2)
+#define KVM_EMUL_INSN_F_CS_L   (1 << 3)
+
+static int kvm_emulate_insn_handler(struct trace_seq *s,
+				    struct pevent_record *record,
+				    struct event_format *event, void *context)
+{
+	unsigned long long rip, csbase, len, flags, failed;
+	int llen;
+	uint8_t *insn;
+	const char *disasm;
+
+	if (pevent_get_field_val(s, event, "rip", record, &rip, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "csbase", record, &csbase, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "len", record, &len, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "flags", record, &flags, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "failed", record, &failed, 1) < 0)
+		return -1;
+
+	insn = pevent_get_field_raw(s, event, "insn", record, &llen, 1);
+	if (!insn)
+		return -1;
+
+	disasm = disassemble(insn, len, rip,
+			     flags & KVM_EMUL_INSN_F_CR0_PE,
+			     flags & KVM_EMUL_INSN_F_EFL_VM,
+			     flags & KVM_EMUL_INSN_F_CS_D,
+			     flags & KVM_EMUL_INSN_F_CS_L);
+
+	trace_seq_printf(s, "%llx:%llx: %s%s", csbase, rip, disasm,
+			 failed ? " FAIL" : "");
+	return 0;
+}
+
+union kvm_mmu_page_role {
+	unsigned word;
+	struct {
+		unsigned glevels:4;
+		unsigned level:4;
+		unsigned quadrant:2;
+		unsigned pad_for_nice_hex_output:6;
+		unsigned direct:1;
+		unsigned access:3;
+		unsigned invalid:1;
+		unsigned cr4_pge:1;
+		unsigned nxe:1;
+	};
+};
+
+static int kvm_mmu_print_role(struct trace_seq *s, struct pevent_record *record,
+			      struct event_format *event, void *context)
+{
+	unsigned long long val;
+	static const char *access_str[] = {
+		"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux"
+	};
+	union kvm_mmu_page_role role;
+
+	if (pevent_get_field_val(s, event, "role", record, &val, 1) < 0)
+		return -1;
+
+	role.word = (int)val;
+
+	/*
+	 * We can only use the structure if file is of the same
+	 * endianess.
+	 */
+	if (pevent_is_file_bigendian(event->pevent) ==
+	    pevent_is_host_bigendian(event->pevent)) {
+
+		trace_seq_printf(s, "%u/%u q%u%s %s%s %spge %snxe",
+				 role.level,
+				 role.glevels,
+				 role.quadrant,
+				 role.direct ? " direct" : "",
+				 access_str[role.access],
+				 role.invalid ? " invalid" : "",
+				 role.cr4_pge ? "" : "!",
+				 role.nxe ? "" : "!");
+	} else
+		trace_seq_printf(s, "WORD: %08x", role.word);
+
+	pevent_print_num_field(s, " root %u ",  event,
+			       "root_count", record, 1);
+
+	if (pevent_get_field_val(s, event, "unsync", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "%s%c",  val ? "unsync" : "sync", 0);
+	return 0;
+}
+
+static int kvm_mmu_get_page_handler(struct trace_seq *s,
+				    struct pevent_record *record,
+				    struct event_format *event, void *context)
+{
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "created", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "%s ", val ? "new" : "existing");
+
+	if (pevent_get_field_val(s, event, "gfn", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "sp gfn %llx ", val);
+	return kvm_mmu_print_role(s, record, event, context);
+}
+
+#define PT_WRITABLE_SHIFT 1
+#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
+
+static unsigned long long
+process_is_writable_pte(struct trace_seq *s, unsigned long long *args)
+{
+	unsigned long pte = args[0];
+	return pte & PT_WRITABLE_MASK;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	init_disassembler();
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+				      kvm_exit_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+				      kvm_emulate_insn_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+				      kvm_mmu_get_page_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1,
+				      "kvmmmu", "kvm_mmu_unsync_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu",
+			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
+			NULL);
+
+	pevent_register_print_function(pevent,
+				       process_is_writable_pte,
+				       PEVENT_FUNC_ARG_INT,
+				       "is_writable_pte",
+				       PEVENT_FUNC_ARG_LONG,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
new file mode 100644
index 000000000000..558a3b91c046
--- /dev/null
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+#define INDENT 65
+
+static void print_string(struct trace_seq *s, struct event_format *event,
+			 const char *name, const void *data)
+{
+	struct format_field *f = pevent_find_field(event, name);
+	int offset;
+	int length;
+
+	if (!f) {
+		trace_seq_printf(s, "NOTFOUND:%s", name);
+		return;
+	}
+
+	offset = f->offset;
+	length = f->size;
+
+	if (!strncmp(f->type, "__data_loc", 10)) {
+		unsigned long long v;
+		if (pevent_read_number_field(f, data, &v)) {
+			trace_seq_printf(s, "invalid_data_loc");
+			return;
+		}
+		offset = v & 0xffff;
+		length = v >> 16;
+	}
+
+	trace_seq_printf(s, "%.*s", length, (char *)data + offset);
+}
+
+#define SF(fn)	pevent_print_num_field(s, fn ":%d", event, fn, record, 0)
+#define SFX(fn)	pevent_print_num_field(s, fn ":%#x", event, fn, record, 0)
+#define SP()	trace_seq_putc(s, ' ')
+
+static int drv_bss_info_changed(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	void *data = record->data;
+
+	print_string(s, event, "wiphy_name", data);
+	trace_seq_printf(s, " vif:");
+	print_string(s, event, "vif_name", data);
+	pevent_print_num_field(s, "(%d)", event, "vif_type", record, 1);
+
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("assoc"); SP();
+	SF("aid"); SP();
+	SF("cts"); SP();
+	SF("shortpre"); SP();
+	SF("shortslot"); SP();
+	SF("dtimper"); SP();
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("bcnint"); SP();
+	SFX("assoc_cap"); SP();
+	SFX("basic_rates"); SP();
+	SF("enable_beacon");
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("ht_operation_mode");
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "mac80211",
+				      "drv_bss_info_changed",
+				      drv_bss_info_changed, NULL);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
new file mode 100644
index 000000000000..fea3724aa24f
--- /dev/null
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -0,0 +1,148 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static void write_state(struct trace_seq *s, int val)
+{
+	const char states[] = "SDTtZXxW";
+	int found = 0;
+	int i;
+
+	for (i = 0; i < (sizeof(states) - 1); i++) {
+		if (!(val & (1 << i)))
+			continue;
+
+		if (found)
+			trace_seq_putc(s, '|');
+
+		found = 1;
+		trace_seq_putc(s, states[i]);
+	}
+
+	if (!found)
+		trace_seq_putc(s, 'R');
+}
+
+static void write_and_save_comm(struct format_field *field,
+				struct pevent_record *record,
+				struct trace_seq *s, int pid)
+{
+	const char *comm;
+	int len;
+
+	comm = (char *)(record->data + field->offset);
+	len = s->len;
+	trace_seq_printf(s, "%.*s",
+			 field->size, comm);
+
+	/* make sure the comm has a \0 at the end. */
+	trace_seq_terminate(s);
+	comm = &s->buffer[len];
+
+	/* Help out the comm to ids. This will handle dups */
+	pevent_register_comm(field->event->pevent, comm, pid);
+}
+
+static int sched_wakeup_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld", val);
+
+	if (pevent_get_field_val(s, event, "prio", record, &val, 0) == 0)
+		trace_seq_printf(s, " [%lld]", val);
+
+	if (pevent_get_field_val(s, event, "success", record, &val, 1) == 0)
+		trace_seq_printf(s, " success=%lld", val);
+
+	if (pevent_get_field_val(s, event, "target_cpu", record, &val, 0) == 0)
+		trace_seq_printf(s, " CPU:%03llu", val);
+
+	return 0;
+}
+
+static int sched_switch_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "prev_pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "prev_comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld ", val);
+
+	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
+		trace_seq_printf(s, "[%lld] ", val);
+
+	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
+		write_state(s, val);
+
+	trace_seq_puts(s, " ==> ");
+
+	if (pevent_get_field_val(s, event, "next_pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "next_comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld", val);
+
+	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
+		trace_seq_printf(s, " [%lld]", val);
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "sched", "sched_switch",
+				      sched_switch_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+				      sched_wakeup_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+				      sched_wakeup_handler, NULL);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
new file mode 100644
index 000000000000..6fb8e3e3fcad
--- /dev/null
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -0,0 +1,423 @@
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include "event-parse.h"
+
+typedef unsigned long sector_t;
+typedef uint64_t u64;
+typedef unsigned int u32;
+
+/*
+ *      SCSI opcodes
+ */
+#define TEST_UNIT_READY			0x00
+#define REZERO_UNIT			0x01
+#define REQUEST_SENSE			0x03
+#define FORMAT_UNIT			0x04
+#define READ_BLOCK_LIMITS		0x05
+#define REASSIGN_BLOCKS			0x07
+#define INITIALIZE_ELEMENT_STATUS	0x07
+#define READ_6				0x08
+#define WRITE_6				0x0a
+#define SEEK_6				0x0b
+#define READ_REVERSE			0x0f
+#define WRITE_FILEMARKS			0x10
+#define SPACE				0x11
+#define INQUIRY				0x12
+#define RECOVER_BUFFERED_DATA		0x14
+#define MODE_SELECT			0x15
+#define RESERVE				0x16
+#define RELEASE				0x17
+#define COPY				0x18
+#define ERASE				0x19
+#define MODE_SENSE			0x1a
+#define START_STOP			0x1b
+#define RECEIVE_DIAGNOSTIC		0x1c
+#define SEND_DIAGNOSTIC			0x1d
+#define ALLOW_MEDIUM_REMOVAL		0x1e
+
+#define READ_FORMAT_CAPACITIES		0x23
+#define SET_WINDOW			0x24
+#define READ_CAPACITY			0x25
+#define READ_10				0x28
+#define WRITE_10			0x2a
+#define SEEK_10				0x2b
+#define POSITION_TO_ELEMENT		0x2b
+#define WRITE_VERIFY			0x2e
+#define VERIFY				0x2f
+#define SEARCH_HIGH			0x30
+#define SEARCH_EQUAL			0x31
+#define SEARCH_LOW			0x32
+#define SET_LIMITS			0x33
+#define PRE_FETCH			0x34
+#define READ_POSITION			0x34
+#define SYNCHRONIZE_CACHE		0x35
+#define LOCK_UNLOCK_CACHE		0x36
+#define READ_DEFECT_DATA		0x37
+#define MEDIUM_SCAN			0x38
+#define COMPARE				0x39
+#define COPY_VERIFY			0x3a
+#define WRITE_BUFFER			0x3b
+#define READ_BUFFER			0x3c
+#define UPDATE_BLOCK			0x3d
+#define READ_LONG			0x3e
+#define WRITE_LONG			0x3f
+#define CHANGE_DEFINITION		0x40
+#define WRITE_SAME			0x41
+#define UNMAP				0x42
+#define READ_TOC			0x43
+#define READ_HEADER			0x44
+#define GET_EVENT_STATUS_NOTIFICATION	0x4a
+#define LOG_SELECT			0x4c
+#define LOG_SENSE			0x4d
+#define XDWRITEREAD_10			0x53
+#define MODE_SELECT_10			0x55
+#define RESERVE_10			0x56
+#define RELEASE_10			0x57
+#define MODE_SENSE_10			0x5a
+#define PERSISTENT_RESERVE_IN		0x5e
+#define PERSISTENT_RESERVE_OUT		0x5f
+#define VARIABLE_LENGTH_CMD		0x7f
+#define REPORT_LUNS			0xa0
+#define SECURITY_PROTOCOL_IN		0xa2
+#define MAINTENANCE_IN			0xa3
+#define MAINTENANCE_OUT			0xa4
+#define MOVE_MEDIUM			0xa5
+#define EXCHANGE_MEDIUM			0xa6
+#define READ_12				0xa8
+#define WRITE_12			0xaa
+#define READ_MEDIA_SERIAL_NUMBER	0xab
+#define WRITE_VERIFY_12			0xae
+#define VERIFY_12			0xaf
+#define SEARCH_HIGH_12			0xb0
+#define SEARCH_EQUAL_12			0xb1
+#define SEARCH_LOW_12			0xb2
+#define SECURITY_PROTOCOL_OUT		0xb5
+#define READ_ELEMENT_STATUS		0xb8
+#define SEND_VOLUME_TAG			0xb6
+#define WRITE_LONG_2			0xea
+#define EXTENDED_COPY			0x83
+#define RECEIVE_COPY_RESULTS		0x84
+#define ACCESS_CONTROL_IN		0x86
+#define ACCESS_CONTROL_OUT		0x87
+#define READ_16				0x88
+#define WRITE_16			0x8a
+#define READ_ATTRIBUTE			0x8c
+#define WRITE_ATTRIBUTE			0x8d
+#define VERIFY_16			0x8f
+#define SYNCHRONIZE_CACHE_16		0x91
+#define WRITE_SAME_16			0x93
+#define SERVICE_ACTION_IN		0x9e
+/* values for service action in */
+#define	SAI_READ_CAPACITY_16		0x10
+#define SAI_GET_LBA_STATUS		0x12
+/* values for VARIABLE_LENGTH_CMD service action codes
+ * see spc4r17 Section D.3.5, table D.7 and D.8 */
+#define VLC_SA_RECEIVE_CREDENTIAL	0x1800
+/* values for maintenance in */
+#define MI_REPORT_IDENTIFYING_INFORMATION		0x05
+#define MI_REPORT_TARGET_PGS				0x0a
+#define MI_REPORT_ALIASES				0x0b
+#define MI_REPORT_SUPPORTED_OPERATION_CODES		0x0c
+#define MI_REPORT_SUPPORTED_TASK_MANAGEMENT_FUNCTIONS	0x0d
+#define MI_REPORT_PRIORITY				0x0e
+#define MI_REPORT_TIMESTAMP				0x0f
+#define MI_MANAGEMENT_PROTOCOL_IN			0x10
+/* value for MI_REPORT_TARGET_PGS ext header */
+#define MI_EXT_HDR_PARAM_FMT		0x20
+/* values for maintenance out */
+#define MO_SET_IDENTIFYING_INFORMATION	0x06
+#define MO_SET_TARGET_PGS		0x0a
+#define MO_CHANGE_ALIASES		0x0b
+#define MO_SET_PRIORITY			0x0e
+#define MO_SET_TIMESTAMP		0x0f
+#define MO_MANAGEMENT_PROTOCOL_OUT	0x10
+/* values for variable length command */
+#define XDREAD_32			0x03
+#define XDWRITE_32			0x04
+#define XPWRITE_32			0x06
+#define XDWRITEREAD_32			0x07
+#define READ_32				0x09
+#define VERIFY_32			0x0a
+#define WRITE_32			0x0b
+#define WRITE_SAME_32			0x0d
+
+#define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f)
+#define SERVICE_ACTION32(cdb) ((cdb[8] << 8) | cdb[9])
+
+static const char *
+scsi_trace_misc(struct trace_seq *, unsigned char *, int);
+
+static const char *
+scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= ((cdb[1] & 0x1F) << 16);
+	lba |=  (cdb[2] << 8);
+	lba |=   cdb[3];
+	txlen = cdb[4];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu",
+			 (unsigned long long)lba, (unsigned long long)txlen);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= (cdb[2] << 24);
+	lba |= (cdb[3] << 16);
+	lba |= (cdb[4] << 8);
+	lba |=  cdb[5];
+	txlen |= (cdb[7] << 8);
+	txlen |=  cdb[8];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= (cdb[2] << 24);
+	lba |= (cdb[3] << 16);
+	lba |= (cdb[4] << 8);
+	lba |=  cdb[5];
+	txlen |= (cdb[6] << 24);
+	txlen |= (cdb[7] << 16);
+	txlen |= (cdb[8] << 8);
+	txlen |=  cdb[9];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= ((u64)cdb[2] << 56);
+	lba |= ((u64)cdb[3] << 48);
+	lba |= ((u64)cdb[4] << 40);
+	lba |= ((u64)cdb[5] << 32);
+	lba |= (cdb[6] << 24);
+	lba |= (cdb[7] << 16);
+	lba |= (cdb[8] << 8);
+	lba |=  cdb[9];
+	txlen |= (cdb[10] << 24);
+	txlen |= (cdb[11] << 16);
+	txlen |= (cdb[12] << 8);
+	txlen |=  cdb[13];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME_16)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len, *cmd;
+	sector_t lba = 0, txlen = 0;
+	u32 ei_lbrt = 0;
+
+	switch (SERVICE_ACTION32(cdb)) {
+	case READ_32:
+		cmd = "READ";
+		break;
+	case VERIFY_32:
+		cmd = "VERIFY";
+		break;
+	case WRITE_32:
+		cmd = "WRITE";
+		break;
+	case WRITE_SAME_32:
+		cmd = "WRITE_SAME";
+		break;
+	default:
+		trace_seq_printf(p, "UNKNOWN");
+		goto out;
+	}
+
+	lba |= ((u64)cdb[12] << 56);
+	lba |= ((u64)cdb[13] << 48);
+	lba |= ((u64)cdb[14] << 40);
+	lba |= ((u64)cdb[15] << 32);
+	lba |= (cdb[16] << 24);
+	lba |= (cdb[17] << 16);
+	lba |= (cdb[18] << 8);
+	lba |=  cdb[19];
+	ei_lbrt |= (cdb[20] << 24);
+	ei_lbrt |= (cdb[21] << 16);
+	ei_lbrt |= (cdb[22] << 8);
+	ei_lbrt |=  cdb[23];
+	txlen |= (cdb[28] << 24);
+	txlen |= (cdb[29] << 16);
+	txlen |= (cdb[30] << 8);
+	txlen |=  cdb[31];
+
+	trace_seq_printf(p, "%s_32 lba=%llu txlen=%llu protect=%u ei_lbrt=%u",
+			 cmd, (unsigned long long)lba,
+			 (unsigned long long)txlen, cdb[10] >> 5, ei_lbrt);
+
+	if (SERVICE_ACTION32(cdb) == WRITE_SAME_32)
+		trace_seq_printf(p, " unmap=%u", cdb[10] >> 3 & 1);
+
+out:
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	unsigned int regions = cdb[7] << 8 | cdb[8];
+
+	trace_seq_printf(p, "regions=%u", (regions - 8) / 16);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len, *cmd;
+	sector_t lba = 0;
+	u32 alloc_len = 0;
+
+	switch (SERVICE_ACTION16(cdb)) {
+	case SAI_READ_CAPACITY_16:
+		cmd = "READ_CAPACITY_16";
+		break;
+	case SAI_GET_LBA_STATUS:
+		cmd = "GET_LBA_STATUS";
+		break;
+	default:
+		trace_seq_printf(p, "UNKNOWN");
+		goto out;
+	}
+
+	lba |= ((u64)cdb[2] << 56);
+	lba |= ((u64)cdb[3] << 48);
+	lba |= ((u64)cdb[4] << 40);
+	lba |= ((u64)cdb[5] << 32);
+	lba |= (cdb[6] << 24);
+	lba |= (cdb[7] << 16);
+	lba |= (cdb[8] << 8);
+	lba |=  cdb[9];
+	alloc_len |= (cdb[10] << 24);
+	alloc_len |= (cdb[11] << 16);
+	alloc_len |= (cdb[12] << 8);
+	alloc_len |=  cdb[13];
+
+	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd,
+			 (unsigned long long)lba, alloc_len);
+
+out:
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	switch (SERVICE_ACTION32(cdb)) {
+	case READ_32:
+	case VERIFY_32:
+	case WRITE_32:
+	case WRITE_SAME_32:
+		return scsi_trace_rw32(p, cdb, len);
+	default:
+		return scsi_trace_misc(p, cdb, len);
+	}
+}
+
+static const char *
+scsi_trace_misc(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+
+	trace_seq_printf(p, "-");
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+const char *
+scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	switch (cdb[0]) {
+	case READ_6:
+	case WRITE_6:
+		return scsi_trace_rw6(p, cdb, len);
+	case READ_10:
+	case VERIFY:
+	case WRITE_10:
+	case WRITE_SAME:
+		return scsi_trace_rw10(p, cdb, len);
+	case READ_12:
+	case VERIFY_12:
+	case WRITE_12:
+		return scsi_trace_rw12(p, cdb, len);
+	case READ_16:
+	case VERIFY_16:
+	case WRITE_16:
+	case WRITE_SAME_16:
+		return scsi_trace_rw16(p, cdb, len);
+	case UNMAP:
+		return scsi_trace_unmap(p, cdb, len);
+	case SERVICE_ACTION_IN:
+		return scsi_trace_service_action_in(p, cdb, len);
+	case VARIABLE_LENGTH_CMD:
+		return scsi_trace_varlen(p, cdb, len);
+	default:
+		return scsi_trace_misc(p, cdb, len);
+	}
+}
+
+unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
+						unsigned long long *args)
+{
+	scsi_trace_parse_cdb(s, (unsigned char *) args[1], args[2]);
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_scsi_trace_parse_cdb,
+				       PEVENT_FUNC_ARG_STRING,
+				       "scsi_trace_parse_cdb",
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
new file mode 100644
index 000000000000..e7794298f3a9
--- /dev/null
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -0,0 +1,130 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "event-parse.h"
+
+#define __HYPERVISOR_set_trap_table			0
+#define __HYPERVISOR_mmu_update				1
+#define __HYPERVISOR_set_gdt				2
+#define __HYPERVISOR_stack_switch			3
+#define __HYPERVISOR_set_callbacks			4
+#define __HYPERVISOR_fpu_taskswitch			5
+#define __HYPERVISOR_sched_op_compat			6
+#define __HYPERVISOR_dom0_op				7
+#define __HYPERVISOR_set_debugreg			8
+#define __HYPERVISOR_get_debugreg			9
+#define __HYPERVISOR_update_descriptor			10
+#define __HYPERVISOR_memory_op				12
+#define __HYPERVISOR_multicall				13
+#define __HYPERVISOR_update_va_mapping			14
+#define __HYPERVISOR_set_timer_op			15
+#define __HYPERVISOR_event_channel_op_compat		16
+#define __HYPERVISOR_xen_version			17
+#define __HYPERVISOR_console_io				18
+#define __HYPERVISOR_physdev_op_compat			19
+#define __HYPERVISOR_grant_table_op			20
+#define __HYPERVISOR_vm_assist				21
+#define __HYPERVISOR_update_va_mapping_otherdomain	22
+#define __HYPERVISOR_iret				23 /* x86 only */
+#define __HYPERVISOR_vcpu_op				24
+#define __HYPERVISOR_set_segment_base			25 /* x86/64 only */
+#define __HYPERVISOR_mmuext_op				26
+#define __HYPERVISOR_acm_op				27
+#define __HYPERVISOR_nmi_op				28
+#define __HYPERVISOR_sched_op				29
+#define __HYPERVISOR_callback_op			30
+#define __HYPERVISOR_xenoprof_op			31
+#define __HYPERVISOR_event_channel_op			32
+#define __HYPERVISOR_physdev_op				33
+#define __HYPERVISOR_hvm_op				34
+#define __HYPERVISOR_tmem_op				38
+
+/* Architecture-specific hypercall definitions. */
+#define __HYPERVISOR_arch_0				48
+#define __HYPERVISOR_arch_1				49
+#define __HYPERVISOR_arch_2				50
+#define __HYPERVISOR_arch_3				51
+#define __HYPERVISOR_arch_4				52
+#define __HYPERVISOR_arch_5				53
+#define __HYPERVISOR_arch_6				54
+#define __HYPERVISOR_arch_7				55
+
+#define N(x)	[__HYPERVISOR_##x] = "("#x")"
+static const char *xen_hypercall_names[] = {
+	N(set_trap_table),
+	N(mmu_update),
+	N(set_gdt),
+	N(stack_switch),
+	N(set_callbacks),
+	N(fpu_taskswitch),
+	N(sched_op_compat),
+	N(dom0_op),
+	N(set_debugreg),
+	N(get_debugreg),
+	N(update_descriptor),
+	N(memory_op),
+	N(multicall),
+	N(update_va_mapping),
+	N(set_timer_op),
+	N(event_channel_op_compat),
+	N(xen_version),
+	N(console_io),
+	N(physdev_op_compat),
+	N(grant_table_op),
+	N(vm_assist),
+	N(update_va_mapping_otherdomain),
+	N(iret),
+	N(vcpu_op),
+	N(set_segment_base),
+	N(mmuext_op),
+	N(acm_op),
+	N(nmi_op),
+	N(sched_op),
+	N(callback_op),
+	N(xenoprof_op),
+	N(event_channel_op),
+	N(physdev_op),
+	N(hvm_op),
+
+/* Architecture-specific hypercall definitions. */
+	N(arch_0),
+	N(arch_1),
+	N(arch_2),
+	N(arch_3),
+	N(arch_4),
+	N(arch_5),
+	N(arch_6),
+	N(arch_7),
+};
+#undef N
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static const char *xen_hypercall_name(unsigned op)
+{
+	if (op < ARRAY_SIZE(xen_hypercall_names) &&
+	    xen_hypercall_names[op] != NULL)
+		return xen_hypercall_names[op];
+
+	return "";
+}
+
+unsigned long long process_xen_hypercall_name(struct trace_seq *s,
+					      unsigned long long *args)
+{
+	unsigned int op = args[0];
+
+	trace_seq_printf(s, "%s", xen_hypercall_name(op));
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_xen_hypercall_name,
+				       PEVENT_FUNC_ARG_STRING,
+				       "xen_hypercall_name",
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index 5032a142853e..ac6ecbb3e669 100644
--- a/tools/perf/Documentation/perf-archive.txt
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -12,9 +12,9 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command runs runs perf-buildid-list --with-hits, and collects the files
-with the buildids found so that analysis of perf.data contents can be possible
-on another machine.
+This command runs perf-buildid-list --with-hits, and collects the files with the
+buildids found so that analysis of perf.data contents can be possible on another
+machine.
 
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6a06cefe9642..52276a6d2b75 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -10,9 +10,9 @@ SYNOPSIS
 [verse]
 'perf kvm' [--host] [--guest] [--guestmount=<path>
 	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
-	{top|record|report|diff|buildid-list}
+	{top|record|report|diff|buildid-list} [<options>]
 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
-	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} [<options>]
 'perf kvm stat [record|report|live] [<options>]
 
 DESCRIPTION
@@ -24,10 +24,17 @@ There are a couple of variants of perf kvm:
   of an arbitrary workload.
 
   'perf kvm record <command>' to record the performance counter profile
-  of an arbitrary workload and save it into a perf data file. If both
-  --host and --guest are input, the perf data file name is perf.data.kvm.
-  If there is  no --host but --guest, the file name is perf.data.guest.
-  If there is no --guest but --host, the file name is perf.data.host.
+  of an arbitrary workload and save it into a perf data file. We set the
+  default behavior of perf kvm as --guest, so if neither --host nor --guest
+  is input, the perf data file name is perf.data.guest. If --host is input,
+  the perf data file name is perf.data.kvm. If you want to record data into
+  perf.data.host, please input --host --no-guest. The behaviors are shown as
+  following:
+    Default('')         ->  perf.data.guest
+    --host              ->  perf.data.kvm
+    --guest             ->  perf.data.guest
+    --host --guest      ->  perf.data.kvm
+    --host --no-guest   ->  perf.data.host
 
   'perf kvm report' to display the performance counter profile information
   recorded via perf kvm record.
@@ -37,7 +44,9 @@ There are a couple of variants of perf kvm:
 
   'perf kvm buildid-list' to  display the buildids found in a perf data file,
   so that other tools can be used to fetch packages with matching symbol tables
-  for use by perf report.
+  for use by perf report. As buildid is read from /sys/kernel/notes in os, then
+  if you want to list the buildid for guest, please make sure your perf data file
+  was captured with --guestmount in perf kvm record.
 
   'perf kvm stat <command>' to run a command and gather performance counter
   statistics.
@@ -58,14 +67,14 @@ There are a couple of variants of perf kvm:
 OPTIONS
 -------
 -i::
---input=::
+--input=<path>::
         Input file name.
 -o::
---output::
+--output=<path>::
         Output file name.
---host=::
+--host::
         Collect host side performance profile.
---guest=::
+--guest::
         Collect guest side performance profile.
 --guestmount=<path>::
 	Guest os root file system mount directory. Users mounts guest os
@@ -84,6 +93,9 @@ OPTIONS
 	kernel module information. Users copy it out from guest os.
 --guestvmlinux=<path>::
 	Guest os kernel vmlinux.
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc).
 
 STAT REPORT OPTIONS
 -------------------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 43b42c4f4a91..c407897f0435 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -57,6 +57,8 @@ OPTIONS
 -t::
 --tid=::
         Record events on existing thread ID (comma separated list).
+        This option also disables inheritance by default.  Enable it by adding
+        --inherit.
 
 -u::
 --uid=::
@@ -201,11 +203,11 @@ abort events and some memory events in precise mode on modern Intel CPUs.
 --transaction::
 Record transaction flags for transaction related events.
 
---force-per-cpu::
-Force the use of per-cpu mmaps.  By default, when tasks are specified (i.e. -p,
--t or -u options) per-thread mmaps are created.  This option overrides that and
-forces per-cpu mmaps.  A side-effect of that is that inheritance is
-automatically enabled.  Add the -i option also to disable inheritance.
+--per-thread::
+Use per-thread mmaps.  By default per-cpu mmaps are created.  This option
+overrides that and uses per-thread mmaps.  A side-effect of that is that
+inheritance is automatically disabled.  --per-thread is ignored with a warning
+if combined with -a or -C options.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 10a279871251..8eab8a4bdeb8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -237,6 +237,15 @@ OPTIONS
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
 
+--header::
+	Show header information in the perf.data file.  This includes
+	various information like hostname, OS and perf version, cpu/mem
+	info, perf command line, event list and so on.  Currently only
+	--stdio output supports this feature.
+
+--header-only::
+	Show only perf.data header (forces --stdio).
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index e9cbfcddfa3f..05f9a0a6784c 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,7 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
@@ -203,6 +203,18 @@ OPTIONS
 --show-kernel-path::
 	Try to resolve the path of [kernel.kallsyms]
 
+--show-task-events
+	Display task related events (e.g. FORK, COMM, EXIT).
+
+--show-mmap-events
+	Display mmap related events (e.g. MMAP, MMAP2).
+
+--header
+	Show perf.data header.
+
+--header-only
+	Show only perf.data header.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 3ff8bd4f0b4d..bc5990c33dc0 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -8,8 +8,7 @@ perf-timechart - Tool to visualize total system behavior during a workload
 SYNOPSIS
 --------
 [verse]
-'perf timechart' record <command>
-'perf timechart' [<options>]
+'perf timechart' [<timechart options>] {record} [<record options>]
 
 DESCRIPTION
 -----------
@@ -21,8 +20,8 @@ There are two variants of perf timechart:
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
   that can be viewed with popular SVG viewers such as 'Inkscape'.
 
-OPTIONS
--------
+TIMECHART OPTIONS
+-----------------
 -o::
 --output=::
         Select the output file (default: output.svg)
@@ -35,6 +34,9 @@ OPTIONS
 -P::
 --power-only::
         Only output the CPU power section of the diagram
+-T::
+--tasks-only::
+        Don't output processor state transitions
 -p::
 --process::
         Select the processes to display, by name or PID
@@ -54,6 +56,38 @@ $ perf timechart
 
   Written 10.2 seconds of trace to output.svg.
 
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
+
+-n::
+--proc-num::
+        Print task info for at least given number of tasks.
+-t::
+--topology::
+        Sort CPUs according to topology.
+--highlight=<duration_nsecs|task_name>::
+	Highlight tasks (using different color) that run more than given
+	duration or tasks with given name. If number is given it's interpreted
+	as number of nanoseconds. If non-numeric string is given it's
+	interpreted as task name.
+
+RECORD OPTIONS
+--------------
+-P::
+--power-only::
+        Record only power-related events
+-T::
+--tasks-only::
+        Record only tasks-related events
+-g::
+--callchain::
+        Do call-graph (stack chain/backtrace) recording
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 7de01dd79688..cdd8d4946dba 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -50,7 +50,6 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
 	Only display functions with more events than this.
 
--g::
 --group::
         Put the counters into a counter group.
 
@@ -143,12 +142,12 @@ Default is to monitor all CPUS.
 --asm-raw::
 	Show raw instruction encoding of assembly instructions.
 
--G::
+-g::
 	Enables call-graph (stack chain/backtrace) recording.
 
 --call-graph::
 	Setup and enable call-graph (stack chain/backtrace) recording,
-	implies -G.
+	implies -g.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 025de796067c..3170a7ff5782 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -2,6 +2,8 @@ tools/perf
 tools/scripts
 tools/lib/traceevent
 tools/lib/lk
+tools/lib/symbol/kallsyms.c
+tools/lib/symbol/kallsyms.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4835618a5608..eefb9fb0c02f 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -60,8 +60,11 @@ endef
 
 #
 # Needed if no target specified:
+# (Except for tags and TAGS targets. The reason is that the
+# Makefile does not treat tags/TAGS as targets but as files
+# and thus won't rebuilt them once they are in place.)
 #
-all:
+all tags TAGS:
 	$(print_msg)
 	$(make)
 
@@ -77,3 +80,5 @@ clean:
 %:
 	$(print_msg)
 	$(make)
+
+.PHONY: tags TAGS
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7fc8f179cae7..97a2145e4cc6 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -86,7 +86,7 @@ FLEX    = flex
 BISON   = bison
 STRIP   = strip
 
-LK_DIR          = $(srctree)/tools/lib/lk/
+LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 
 # include config/Makefile by default and rule out
@@ -105,7 +105,7 @@ ifeq ($(config),1)
 include config/Makefile
 endif
 
-export prefix bindir sharedir sysconfdir
+export prefix bindir sharedir sysconfdir DESTDIR
 
 # sparse is architecture-neutral, which means that we need to tell it
 # explicitly what architecture to check for. Fix this up for yours..
@@ -127,20 +127,20 @@ strip-libs = $(filter-out -l%,$(1))
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LK_PATH=$(OUTPUT)/../lib/lk/
+  LIB_PATH=$(OUTPUT)/../lib/api/
 else
-  LK_PATH=$(OUTPUT)
+  LIB_PATH=$(OUTPUT)
 endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
-  LK_PATH=$(LK_DIR)
+  LIB_PATH=$(LIB_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
-LIBLK = $(LK_PATH)liblk.a
-export LIBLK
+LIBAPIKFS = $(LIB_PATH)libapikfs.a
+export LIBAPIKFS
 
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
@@ -151,7 +151,7 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
 python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
 
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
-PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPIKFS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
@@ -202,6 +202,7 @@ $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
 LIB_FILE=$(OUTPUT)libperf.a
 
+LIB_H += ../lib/symbol/kallsyms.h
 LIB_H += ../../include/uapi/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
@@ -312,6 +313,7 @@ LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
 LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/kallsyms.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
 LIB_OBJS += $(OUTPUT)util/parse-options.o
 LIB_OBJS += $(OUTPUT)util/parse-events.o
@@ -353,6 +355,7 @@ LIB_OBJS += $(OUTPUT)util/pmu-bison.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
 LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
+LIB_OBJS += $(OUTPUT)util/trace-event.o
 LIB_OBJS += $(OUTPUT)util/svghelper.o
 LIB_OBJS += $(OUTPUT)util/sort.o
 LIB_OBJS += $(OUTPUT)util/hist.o
@@ -438,7 +441,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
 BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
 
-PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
+PERFLIBS = $(LIB_FILE) $(LIBAPIKFS) $(LIBTRACEEVENT)
 
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
@@ -671,6 +674,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
+$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
@@ -710,26 +716,33 @@ $(LIB_FILE): $(LIB_OBJS)
 # libtraceevent.a
 TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch])
 
-$(LIBTRACEEVENT): $(TE_SOURCES)
-	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) CFLAGS="-g -Wall $(EXTRA_CFLAGS)" libtraceevent.a
+LIBTRACEEVENT_FLAGS  = $(QUIET_SUBDIR1) O=$(OUTPUT)
+LIBTRACEEVENT_FLAGS += CFLAGS="-g -Wall $(EXTRA_CFLAGS)"
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+
+$(LIBTRACEEVENT): $(TE_SOURCES) $(OUTPUT)PERF-CFLAGS
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) libtraceevent.a plugins
 
 $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
 	@$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
-LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch])
+install-traceevent-plugins: $(LIBTRACEEVENT)
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
+
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
 
 # if subdir is set, we've been called from above so target has been built
 # already
-$(LIBLK): $(LIBLK_SOURCES)
+$(LIBAPIKFS): $(LIBAPIKFS_SOURCES)
 ifeq ($(subdir),)
-	$(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a
+	$(QUIET_SUBDIR0)$(LIB_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libapikfs.a
 endif
 
-$(LIBLK)-clean:
+$(LIBAPIKFS)-clean:
 ifeq ($(subdir),)
-	$(call QUIET_CLEAN, liblk)
-	@$(MAKE) -C $(LK_DIR) O=$(OUTPUT) clean >/dev/null
+	$(call QUIET_CLEAN, libapikfs)
+	@$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 endif
 
 help:
@@ -785,7 +798,7 @@ cscope:
 
 ### Detect prefix changes
 TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
-             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
+             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ):$(plugindir_SQ)
 
 $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
 	@FLAGS='$(TRACK_CFLAGS)'; \
@@ -840,16 +853,16 @@ ifndef NO_LIBPYTHON
 		$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
 		$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 endif
-	$(call QUIET_INSTALL, bash_completion-script) \
+	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
-		$(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install: install-bin try-install-man
+install: install-bin try-install-man install-traceevent-plugins
 
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
@@ -868,12 +881,11 @@ config-clean:
 	$(call QUIET_CLEAN, config)
 	@$(MAKE) -C config/feature-checks clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean config-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
-	$(call QUIET_CLEAN, Documentation)
-	@$(MAKE) -C Documentation O=$(OUTPUT) clean >/dev/null
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
 #
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4087ab19823c..6fd52c8fa682 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -373,7 +373,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (argc) {
 		/*
-		 * Special case: if there's an argument left then assume tha
+		 * Special case: if there's an argument left then assume that
 		 * it's a symbol filter:
 		 */
 		if (argc > 1)
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 3b67ea2444bd..2a85cc9a2d09 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1000,8 +1000,7 @@ static int data_init(int argc, const char **argv)
 			data__files_cnt = argc;
 			use_default = false;
 		}
-	} else if (symbol_conf.default_guest_vmlinux_name ||
-		   symbol_conf.default_guest_kallsyms) {
+	} else if (perf_guest) {
 		defaults[0] = "perf.data.host";
 		defaults[1] = "perf.data.guest";
 	}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f8bf5f244d77..154b397a5d27 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -13,7 +13,7 @@
 #include "util/parse-options.h"
 #include "util/trace-event.h"
 #include "util/debug.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "util/tool.h"
 #include "util/stat.h"
 #include "util/top.h"
@@ -1232,7 +1232,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 		.ordered_samples	= true,
 	};
 	struct perf_data_file file = {
-		.path = input_name,
+		.path = kvm->file_name,
 		.mode = PERF_DATA_MODE_READ,
 	};
 
@@ -1690,6 +1690,8 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 			   "file", "file saving guest os /proc/kallsyms"),
 		OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
 			   "file", "file saving guest os /proc/modules"),
+		OPT_INCR('v', "verbose", &verbose,
+			    "be more verbose (show counter open errors, etc)"),
 		OPT_END()
 	};
 
@@ -1711,12 +1713,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 		perf_guest = 1;
 
 	if (!file_name) {
-		if (perf_host && !perf_guest)
-			file_name = strdup("perf.data.host");
-		else if (!perf_host && perf_guest)
-			file_name = strdup("perf.data.guest");
-		else
-			file_name = strdup("perf.data.kvm");
+		file_name = get_filename_for_perf_kvm();
 
 		if (!file_name) {
 			pr_err("Failed to allocate memory for filename\n");
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 6ea9e85bdc00..c98ccb570509 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -37,7 +37,7 @@
 #include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "util/parse-options.h"
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7c8020a32784..c1c1200d2f0a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -76,7 +76,7 @@ struct perf_record {
 	long			samples;
 };
 
-static int do_write_output(struct perf_record *rec, void *buf, size_t size)
+static int perf_record__write(struct perf_record *rec, void *buf, size_t size)
 {
 	struct perf_data_file *file = &rec->file;
 
@@ -97,21 +97,13 @@ static int do_write_output(struct perf_record *rec, void *buf, size_t size)
 	return 0;
 }
 
-static int write_output(struct perf_record *rec, void *buf, size_t size)
-{
-	return do_write_output(rec, buf, size);
-}
-
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
 				     struct machine *machine __maybe_unused)
 {
 	struct perf_record *rec = container_of(tool, struct perf_record, tool);
-	if (write_output(rec, event, event->header.size) < 0)
-		return -1;
-
-	return 0;
+	return perf_record__write(rec, event, event->header.size);
 }
 
 static int perf_record__mmap_read(struct perf_record *rec,
@@ -136,7 +128,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
 		size = md->mask + 1 - (old & md->mask);
 		old += size;
 
-		if (write_output(rec, buf, size) < 0) {
+		if (perf_record__write(rec, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -146,7 +138,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
 	size = head - old;
 	old += size;
 
-	if (write_output(rec, buf, size) < 0) {
+	if (perf_record__write(rec, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
@@ -232,7 +224,7 @@ try_again:
 			       "Consider increasing "
 			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
 			       "or try again with a smaller value of -m/--mmap_pages.\n"
-			       "(current value: %d)\n", opts->mmap_pages);
+			       "(current value: %u)\n", opts->mmap_pages);
 			rc = -errno;
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
@@ -335,8 +327,8 @@ static int perf_record__mmap_read_all(struct perf_record *rec)
 	}
 
 	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
-		rc = write_output(rec, &finished_round_event,
-				  sizeof(finished_round_event));
+		rc = perf_record__write(rec, &finished_round_event,
+					sizeof(finished_round_event));
 
 out:
 	return rc;
@@ -800,6 +792,7 @@ static struct perf_record record = {
 		.freq		     = 4000,
 		.target		     = {
 			.uses_mmap   = true,
+			.default_per_cpu = true,
 		},
 	},
 };
@@ -842,8 +835,9 @@ const struct option record_options[] = {
 	OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
 	OPT_STRING('o', "output", &record.file.path, "file",
 		    "output file name"),
-	OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
-		    "child tasks do not inherit counters"),
+	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
+			&record.opts.no_inherit_set,
+			"child tasks do not inherit counters"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
 	OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
 		     "number of mmap data pages",
@@ -888,8 +882,8 @@ const struct option record_options[] = {
 		    "sample by weight (on special events only)"),
 	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
 		    "sample transaction flags (special events only)"),
-	OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
-		    "force the use of per-cpu mmaps"),
+	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
+		    "use per-thread mmaps"),
 	OPT_END()
 };
 
@@ -938,6 +932,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_symbol_exit;
 	}
 
+	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
+		rec->opts.no_inherit = true;
+
 	err = target__validate(&rec->opts.target);
 	if (err) {
 		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8cf8e66ba594..3a14dbed387c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -49,6 +49,8 @@ struct perf_report {
 	bool			show_threads;
 	bool			inverted_callchain;
 	bool			mem_mode;
+	bool			header;
+	bool			header_only;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;
@@ -514,9 +516,6 @@ static int __cmd_report(struct perf_report *rep)
 			return ret;
 	}
 
-	if (use_browser <= 0)
-		perf_session__fprintf_info(session, stdout, rep->show_full_info);
-
 	if (rep->show_threads)
 		perf_read_values_init(&rep->show_threads_values);
 
@@ -820,6 +819,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
+	OPT_BOOLEAN(0, "header", &report.header, "Show data header."),
+	OPT_BOOLEAN(0, "header-only", &report.header_only,
+		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
 		   " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
@@ -963,6 +965,10 @@ repeat:
 			goto error;
 	}
 
+	/* Force tty output for header output. */
+	if (report.header || report.header_only)
+		use_browser = 0;
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else {
@@ -970,6 +976,16 @@ repeat:
 		perf_hpp__init();
 	}
 
+	if (report.header || report.header_only) {
+		perf_session__fprintf_info(session, stdout,
+					   report.show_full_info);
+		if (report.header_only)
+			return 0;
+	} else if (use_browser == 0) {
+		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
+		      stdout);
+	}
+
 	/*
 	 * Only in the TUI browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index baf17989a216..f8ab125aac48 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -43,6 +43,7 @@ enum perf_output_field {
 	PERF_OUTPUT_DSO             = 1U << 9,
 	PERF_OUTPUT_ADDR            = 1U << 10,
 	PERF_OUTPUT_SYMOFFSET       = 1U << 11,
+	PERF_OUTPUT_SRCLINE         = 1U << 12,
 };
 
 struct output_option {
@@ -61,6 +62,7 @@ struct output_option {
 	{.str = "dso",   .field = PERF_OUTPUT_DSO},
 	{.str = "addr",  .field = PERF_OUTPUT_ADDR},
 	{.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
+	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 };
 
 /* default set to maintain compatibility with current format */
@@ -210,6 +212,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "to DSO.\n");
 		return -EINVAL;
 	}
+	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
+		pr_err("Display of source line number requested but sample IP is not\n"
+		       "selected. Hence, no address to lookup the source line number.\n");
+		return -EINVAL;
+	}
 
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
@@ -245,6 +252,9 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
 
 	if (PRINT_FIELD(SYMOFFSET))
 		output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+
+	if (PRINT_FIELD(SRCLINE))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE;
 }
 
 /*
@@ -280,6 +290,30 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	/*
+	 * set default for tracepoints to print symbols only
+	 * if callchains are present
+	 */
+	if (symbol_conf.use_callchain &&
+	    !output[PERF_TYPE_TRACEPOINT].user_set) {
+		struct perf_event_attr *attr;
+
+		j = PERF_TYPE_TRACEPOINT;
+		evsel = perf_session__find_first_evtype(session, j);
+		if (evsel == NULL)
+			goto out;
+
+		attr = &evsel->attr;
+
+		if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+			output[j].fields |= PERF_OUTPUT_IP;
+			output[j].fields |= PERF_OUTPUT_SYM;
+			output[j].fields |= PERF_OUTPUT_DSO;
+			set_print_ip_opts(attr);
+		}
+	}
+
+out:
 	return 0;
 }
 
@@ -288,7 +322,6 @@ static void print_sample_start(struct perf_sample *sample,
 			       struct perf_evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	const char *evname = NULL;
 	unsigned long secs;
 	unsigned long usecs;
 	unsigned long long nsecs;
@@ -323,11 +356,6 @@ static void print_sample_start(struct perf_sample *sample,
 		usecs = nsecs / NSECS_PER_USEC;
 		printf("%5lu.%06lu: ", secs, usecs);
 	}
-
-	if (PRINT_FIELD(EVNAME)) {
-		evname = perf_evsel__name(evsel);
-		printf("%s: ", evname ? evname : "[unknown]");
-	}
 }
 
 static bool is_bts_event(struct perf_event_attr *attr)
@@ -396,7 +424,8 @@ static void print_sample_bts(union perf_event *event,
 			     struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct machine *machine,
-			     struct thread *thread)
+			     struct thread *thread,
+			     struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 
@@ -406,7 +435,7 @@ static void print_sample_bts(union perf_event *event,
 			printf(" ");
 		else
 			printf("\n");
-		perf_evsel__print_ip(evsel, event, sample, machine,
+		perf_evsel__print_ip(evsel, sample, machine, al,
 				     output[attr->type].print_ip_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
@@ -425,7 +454,7 @@ static void print_sample_bts(union perf_event *event,
 static void process_event(union perf_event *event, struct perf_sample *sample,
 			  struct perf_evsel *evsel, struct machine *machine,
 			  struct thread *thread,
-			  struct addr_location *al __maybe_unused)
+			  struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 
@@ -434,8 +463,13 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 
 	print_sample_start(sample, thread, evsel);
 
+	if (PRINT_FIELD(EVNAME)) {
+		const char *evname = perf_evsel__name(evsel);
+		printf("%s: ", evname ? evname : "[unknown]");
+	}
+
 	if (is_bts_event(attr)) {
-		print_sample_bts(event, sample, evsel, machine, thread);
+		print_sample_bts(event, sample, evsel, machine, thread, al);
 		return;
 	}
 
@@ -451,7 +485,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		else
 			printf("\n");
 
-		perf_evsel__print_ip(evsel, event, sample, machine,
+		perf_evsel__print_ip(evsel, sample, machine, al,
 				     output[attr->type].print_ip_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
@@ -549,6 +583,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
+	bool			show_task_events;
+	bool			show_mmap_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -579,6 +615,163 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	return perf_evsel__check_attr(evsel, scr->session);
 }
 
+static int process_comm_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing COMM event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_comm(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+
+out:
+	return ret;
+}
+
+static int process_fork_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_fork(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing FORK event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = event->fork.time;
+		sample->tid = event->fork.tid;
+		sample->pid = event->fork.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+static int process_exit_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing EXIT event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	if (perf_event__process_exit(tool, event, sample, machine) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int process_mmap_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap.tid;
+		sample->pid = event->mmap.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
+static int process_mmap2_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP2 event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap2.tid;
+		sample->pid = event->mmap2.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -590,6 +783,17 @@ static int __cmd_script(struct perf_script *script)
 
 	signal(SIGINT, sig_handler);
 
+	/* override event processing functions */
+	if (script->show_task_events) {
+		script->tool.comm = process_comm_event;
+		script->tool.fork = process_fork_event;
+		script->tool.exit = process_exit_event;
+	}
+	if (script->show_mmap_events) {
+		script->tool.mmap = process_mmap_event;
+		script->tool.mmap2 = process_mmap2_event;
+	}
+
 	ret = perf_session__process_events(script->session, &script->tool);
 
 	if (debug_mode)
@@ -1290,6 +1494,8 @@ static int have_cmd(int argc, const char **argv)
 int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	bool show_full_info = false;
+	bool header = false;
+	bool header_only = false;
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
@@ -1328,6 +1534,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_BOOLEAN('d', "debug-mode", &debug_mode,
 		   "do various checks like samples ordering and lost events"),
+	OPT_BOOLEAN(0, "header", &header, "Show data header."),
+	OPT_BOOLEAN(0, "header-only", &header_only, "Show only data header."),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
@@ -1352,6 +1560,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "display extended information from perf.data file"),
 	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
 		    "Show the path of [kernel.kallsyms]"),
+	OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
+		    "Show the fork/comm/exit events"),
+	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
+		    "Show the mmap events"),
 	OPT_END()
 	};
 	const char * const script_usage[] = {
@@ -1540,6 +1752,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (header || header_only) {
+		perf_session__fprintf_info(session, stdout, show_full_info);
+		if (header_only)
+			return 0;
+	}
+
 	script.session = session;
 
 	if (cpu_list) {
@@ -1547,9 +1765,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			return -1;
 	}
 
-	if (!script_name && !generate_script_lang)
-		perf_session__fprintf_info(session, stdout, show_full_info);
-
 	if (!no_callchain)
 		symbol_conf.use_callchain = true;
 	else
@@ -1588,7 +1803,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			return -1;
 		}
 
-		err = scripting_ops->generate_script(session->pevent,
+		err = scripting_ops->generate_script(session->tevent.pevent,
 						     "perf-script");
 		goto out;
 	}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ee0d565f83e3..dab98b50c9fe 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -138,6 +138,7 @@ static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
 static unsigned int		interval			= 0;
 static unsigned int		initial_delay			= 0;
+static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
@@ -461,17 +462,17 @@ static void print_interval(void)
 	if (num_print_interval == 0 && !csv_output) {
 		switch (aggr_mode) {
 		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus             counts events\n");
+			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus             counts events\n");
+			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_NONE:
-			fprintf(output, "#           time CPU                 counts events\n");
+			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_GLOBAL:
 		default:
-			fprintf(output, "#           time             counts events\n");
+			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
 		}
 	}
 
@@ -516,6 +517,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
 	struct timespec ts;
+	size_t l;
 	int status = 0;
 	const bool forks = (argc > 0);
 
@@ -565,6 +567,10 @@ static int __run_perf_stat(int argc, const char **argv)
 			return -1;
 		}
 		counter->supported = true;
+
+		l = strlen(counter->unit);
+		if (l > unit_width)
+			unit_width = l;
 	}
 
 	if (perf_evlist__apply_filters(evsel_list)) {
@@ -704,14 +710,25 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
-	const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s";
+	const char *fmt_v, *fmt_n;
 	char name[25];
 
+	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
+	fmt_n = csv_output ? "%s" : "%-25s";
+
 	aggr_printout(evsel, cpu, nr);
 
 	scnprintf(name, sizeof(name), "%s%s",
 		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-	fprintf(output, fmt, msecs, csv_sep, name);
+
+	fprintf(output, fmt_v, msecs, csv_sep);
+
+	if (csv_output)
+		fprintf(output, "%s%s", evsel->unit, csv_sep);
+	else
+		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
+
+	fprintf(output, fmt_n, name);
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -908,21 +925,31 @@ static void print_ll_cache_misses(int cpu,
 static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0, total2;
+	double sc =  evsel->scale;
 	const char *fmt;
 
-	if (csv_output)
-		fmt = "%.0f%s%s";
-	else if (big_num)
-		fmt = "%'18.0f%s%-25s";
-	else
-		fmt = "%18.0f%s%-25s";
+	if (csv_output) {
+		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (big_num)
+			fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+	}
 
 	aggr_printout(evsel, cpu, nr);
 
 	if (aggr_mode == AGGR_GLOBAL)
 		cpu = 0;
 
-	fprintf(output, fmt, avg, csv_sep, perf_evsel__name(evsel));
+	fprintf(output, fmt, avg, csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			evsel->unit, csv_sep);
+
+	fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -941,7 +968,10 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 
 		if (total && avg) {
 			ratio = total / avg;
-			fprintf(output, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+			fprintf(output, "\n");
+			if (aggr_mode == AGGR_NONE)
+				fprintf(output, "        ");
+			fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);
 		}
 
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
@@ -1061,6 +1091,7 @@ static void print_aggr(char *prefix)
 {
 	struct perf_evsel *counter;
 	int cpu, cpu2, s, s2, id, nr;
+	double uval;
 	u64 ena, run, val;
 
 	if (!(aggr_map || aggr_get_id))
@@ -1087,11 +1118,17 @@ static void print_aggr(char *prefix)
 			if (run == 0 || ena == 0) {
 				aggr_printout(counter, id, nr);
 
-				fprintf(output, "%*s%s%*s",
+				fprintf(output, "%*s%s",
 					csv_output ? 0 : 18,
 					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-					csv_sep,
-					csv_output ? 0 : -24,
+					csv_sep);
+
+				fprintf(output, "%-*s%s",
+					csv_output ? 0 : unit_width,
+					counter->unit, csv_sep);
+
+				fprintf(output, "%*s",
+					csv_output ? 0 : -25,
 					perf_evsel__name(counter));
 
 				if (counter->cgrp)
@@ -1101,11 +1138,12 @@ static void print_aggr(char *prefix)
 				fputc('\n', output);
 				continue;
 			}
+			uval = val * counter->scale;
 
 			if (nsec_counter(counter))
-				nsec_printout(id, nr, counter, val);
+				nsec_printout(id, nr, counter, uval);
 			else
-				abs_printout(id, nr, counter, val);
+				abs_printout(id, nr, counter, uval);
 
 			if (!csv_output) {
 				print_noise(counter, 1.0);
@@ -1128,16 +1166,21 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	struct perf_stat *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
 	int scaled = counter->counts->scaled;
+	double uval;
 
 	if (prefix)
 		fprintf(output, "%s", prefix);
 
 	if (scaled == -1) {
-		fprintf(output, "%*s%s%*s",
+		fprintf(output, "%*s%s",
 			csv_output ? 0 : 18,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep,
-			csv_output ? 0 : -24,
+			csv_sep);
+		fprintf(output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+		fprintf(output, "%*s",
+			csv_output ? 0 : -25,
 			perf_evsel__name(counter));
 
 		if (counter->cgrp)
@@ -1147,10 +1190,12 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 		return;
 	}
 
+	uval = avg * counter->scale;
+
 	if (nsec_counter(counter))
-		nsec_printout(-1, 0, counter, avg);
+		nsec_printout(-1, 0, counter, uval);
 	else
-		abs_printout(-1, 0, counter, avg);
+		abs_printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
@@ -1177,6 +1222,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 static void print_counter(struct perf_evsel *counter, char *prefix)
 {
 	u64 ena, run, val;
+	double uval;
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1188,14 +1234,20 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		if (run == 0 || ena == 0) {
-			fprintf(output, "CPU%*d%s%*s%s%*s",
+			fprintf(output, "CPU%*d%s%*s%s",
 				csv_output ? 0 : -4,
 				perf_evsel__cpus(counter)->map[cpu], csv_sep,
 				csv_output ? 0 : 18,
 				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-				csv_sep,
-				csv_output ? 0 : -24,
-				perf_evsel__name(counter));
+				csv_sep);
+
+				fprintf(output, "%-*s%s",
+					csv_output ? 0 : unit_width,
+					counter->unit, csv_sep);
+
+				fprintf(output, "%*s",
+					csv_output ? 0 : -25,
+					perf_evsel__name(counter));
 
 			if (counter->cgrp)
 				fprintf(output, "%s%s",
@@ -1205,10 +1257,12 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			continue;
 		}
 
+		uval = val * counter->scale;
+
 		if (nsec_counter(counter))
-			nsec_printout(cpu, 0, counter, val);
+			nsec_printout(cpu, 0, counter, uval);
 		else
-			abs_printout(cpu, 0, counter, val);
+			abs_printout(cpu, 0, counter, uval);
 
 		if (!csv_output) {
 			print_noise(counter, 1.0);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 41c9bde2fb67..20d4212fa337 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,25 +41,29 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
-
-static unsigned int	numcpus;
-static u64		min_freq;	/* Lowest CPU frequency seen */
-static u64		max_freq;	/* Highest CPU frequency seen */
-static u64		turbo_frequency;
-
-static u64		first_time, last_time;
-
-static bool		power_only;
-
-
 struct per_pid;
-struct per_pidcomm;
-
-struct cpu_sample;
 struct power_event;
 struct wake_event;
 
-struct sample_wrapper;
+struct timechart {
+	struct perf_tool	tool;
+	struct per_pid		*all_data;
+	struct power_event	*power_events;
+	struct wake_event	*wake_events;
+	int			proc_num;
+	unsigned int		numcpus;
+	u64			min_freq,	/* Lowest CPU frequency seen */
+				max_freq,	/* Highest CPU frequency seen */
+				turbo_frequency,
+				first_time, last_time;
+	bool			power_only,
+				tasks_only,
+				with_backtrace,
+				topology;
+};
+
+struct per_pidcomm;
+struct cpu_sample;
 
 /*
  * Datastructure layout:
@@ -124,10 +128,9 @@ struct cpu_sample {
 	u64 end_time;
 	int type;
 	int cpu;
+	const char *backtrace;
 };
 
-static struct per_pid *all_data;
-
 #define CSTATE 1
 #define PSTATE 2
 
@@ -145,12 +148,9 @@ struct wake_event {
 	int waker;
 	int wakee;
 	u64 time;
+	const char *backtrace;
 };
 
-static struct power_event    *power_events;
-static struct wake_event     *wake_events;
-
-struct process_filter;
 struct process_filter {
 	char			*name;
 	int			pid;
@@ -160,9 +160,9 @@ struct process_filter {
 static struct process_filter *process_filter;
 
 
-static struct per_pid *find_create_pid(int pid)
+static struct per_pid *find_create_pid(struct timechart *tchart, int pid)
 {
-	struct per_pid *cursor = all_data;
+	struct per_pid *cursor = tchart->all_data;
 
 	while (cursor) {
 		if (cursor->pid == pid)
@@ -172,16 +172,16 @@ static struct per_pid *find_create_pid(int pid)
 	cursor = zalloc(sizeof(*cursor));
 	assert(cursor != NULL);
 	cursor->pid = pid;
-	cursor->next = all_data;
-	all_data = cursor;
+	cursor->next = tchart->all_data;
+	tchart->all_data = cursor;
 	return cursor;
 }
 
-static void pid_set_comm(int pid, char *comm)
+static void pid_set_comm(struct timechart *tchart, int pid, char *comm)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->all;
 	while (c) {
 		if (c->comm && strcmp(c->comm, comm) == 0) {
@@ -203,14 +203,14 @@ static void pid_set_comm(int pid, char *comm)
 	p->all = c;
 }
 
-static void pid_fork(int pid, int ppid, u64 timestamp)
+static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 {
 	struct per_pid *p, *pp;
-	p = find_create_pid(pid);
-	pp = find_create_pid(ppid);
+	p = find_create_pid(tchart, pid);
+	pp = find_create_pid(tchart, ppid);
 	p->ppid = ppid;
 	if (pp->current && pp->current->comm && !p->current)
-		pid_set_comm(pid, pp->current->comm);
+		pid_set_comm(tchart, pid, pp->current->comm);
 
 	p->start_time = timestamp;
 	if (p->current) {
@@ -219,23 +219,24 @@ static void pid_fork(int pid, int ppid, u64 timestamp)
 	}
 }
 
-static void pid_exit(int pid, u64 timestamp)
+static void pid_exit(struct timechart *tchart, int pid, u64 timestamp)
 {
 	struct per_pid *p;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	p->end_time = timestamp;
 	if (p->current)
 		p->current->end_time = timestamp;
 }
 
-static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
+static void pid_put_sample(struct timechart *tchart, int pid, int type,
+			   unsigned int cpu, u64 start, u64 end,
+			   const char *backtrace)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->current;
 	if (!c) {
 		c = zalloc(sizeof(*c));
@@ -252,6 +253,7 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
 	sample->type = type;
 	sample->next = c->samples;
 	sample->cpu = cpu;
+	sample->backtrace = backtrace;
 	c->samples = sample;
 
 	if (sample->type == TYPE_RUNNING && end > start && start > 0) {
@@ -272,84 +274,47 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(struct perf_tool *tool __maybe_unused,
+static int process_comm_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_set_comm(event->comm.tid, event->comm.comm);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_set_comm(tchart, event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(struct perf_tool *tool __maybe_unused,
+static int process_fork_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_fork(tchart, event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(struct perf_tool *tool __maybe_unused,
+static int process_exit_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_exit(event->fork.pid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_exit(tchart, event->fork.pid, event->fork.time);
 	return 0;
 }
 
-struct trace_entry {
-	unsigned short		type;
-	unsigned char		flags;
-	unsigned char		preempt_count;
-	int			pid;
-	int			lock_depth;
-};
-
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int use_old_power_events;
-struct power_entry_old {
-	struct trace_entry te;
-	u64	type;
-	u64	value;
-	u64	cpu_id;
-};
 #endif
 
-struct power_processor_entry {
-	struct trace_entry te;
-	u32	state;
-	u32	cpu_id;
-};
-
-#define TASK_COMM_LEN 16
-struct wakeup_entry {
-	struct trace_entry te;
-	char comm[TASK_COMM_LEN];
-	int   pid;
-	int   prio;
-	int   success;
-};
-
-struct sched_switch {
-	struct trace_entry te;
-	char prev_comm[TASK_COMM_LEN];
-	int  prev_pid;
-	int  prev_prio;
-	long prev_state; /* Arjan weeps. */
-	char next_comm[TASK_COMM_LEN];
-	int  next_pid;
-	int  next_prio;
-};
-
 static void c_state_start(int cpu, u64 timestamp, int state)
 {
 	cpus_cstate_start_times[cpu] = timestamp;
 	cpus_cstate_state[cpu] = state;
 }
 
-static void c_state_end(int cpu, u64 timestamp)
+static void c_state_end(struct timechart *tchart, int cpu, u64 timestamp)
 {
 	struct power_event *pwr = zalloc(sizeof(*pwr));
 
@@ -361,12 +326,12 @@ static void c_state_end(int cpu, u64 timestamp)
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = CSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 }
 
-static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
+static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64 new_freq)
 {
 	struct power_event *pwr;
 
@@ -382,73 +347,78 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = PSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
 	if (!pwr->start_time)
-		pwr->start_time = first_time;
+		pwr->start_time = tchart->first_time;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 
 	cpus_pstate_state[cpu] = new_freq;
 	cpus_pstate_start_times[cpu] = timestamp;
 
-	if ((u64)new_freq > max_freq)
-		max_freq = new_freq;
+	if ((u64)new_freq > tchart->max_freq)
+		tchart->max_freq = new_freq;
 
-	if (new_freq < min_freq || min_freq == 0)
-		min_freq = new_freq;
+	if (new_freq < tchart->min_freq || tchart->min_freq == 0)
+		tchart->min_freq = new_freq;
 
-	if (new_freq == max_freq - 1000)
-			turbo_frequency = max_freq;
+	if (new_freq == tchart->max_freq - 1000)
+		tchart->turbo_frequency = tchart->max_freq;
 }
 
-static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
+static void sched_wakeup(struct timechart *tchart, int cpu, u64 timestamp,
+			 int waker, int wakee, u8 flags, const char *backtrace)
 {
 	struct per_pid *p;
-	struct wakeup_entry *wake = (void *)te;
 	struct wake_event *we = zalloc(sizeof(*we));
 
 	if (!we)
 		return;
 
 	we->time = timestamp;
-	we->waker = pid;
+	we->waker = waker;
+	we->backtrace = backtrace;
 
-	if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
+	if ((flags & TRACE_FLAG_HARDIRQ) || (flags & TRACE_FLAG_SOFTIRQ))
 		we->waker = -1;
 
-	we->wakee = wake->pid;
-	we->next = wake_events;
-	wake_events = we;
-	p = find_create_pid(we->wakee);
+	we->wakee = wakee;
+	we->next = tchart->wake_events;
+	tchart->wake_events = we;
+	p = find_create_pid(tchart, we->wakee);
 
 	if (p && p->current && p->current->state == TYPE_NONE) {
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 	if (p && p->current && p->current->state == TYPE_BLOCKED) {
-		pid_put_sample(p->pid, p->current->state, cpu, p->current->state_since, timestamp);
+		pid_put_sample(tchart, p->pid, p->current->state, cpu,
+			       p->current->state_since, timestamp, NULL);
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 }
 
-static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
+static void sched_switch(struct timechart *tchart, int cpu, u64 timestamp,
+			 int prev_pid, int next_pid, u64 prev_state,
+			 const char *backtrace)
 {
 	struct per_pid *p = NULL, *prev_p;
-	struct sched_switch *sw = (void *)te;
-
 
-	prev_p = find_create_pid(sw->prev_pid);
+	prev_p = find_create_pid(tchart, prev_pid);
 
-	p = find_create_pid(sw->next_pid);
+	p = find_create_pid(tchart, next_pid);
 
 	if (prev_p->current && prev_p->current->state != TYPE_NONE)
-		pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu, prev_p->current->state_since, timestamp);
+		pid_put_sample(tchart, prev_pid, TYPE_RUNNING, cpu,
+			       prev_p->current->state_since, timestamp,
+			       backtrace);
 	if (p && p->current) {
 		if (p->current->state != TYPE_NONE)
-			pid_put_sample(sw->next_pid, p->current->state, cpu, p->current->state_since, timestamp);
+			pid_put_sample(tchart, next_pid, p->current->state, cpu,
+				       p->current->state_since, timestamp,
+				       backtrace);
 
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_RUNNING;
@@ -457,109 +427,212 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 	if (prev_p->current) {
 		prev_p->current->state = TYPE_NONE;
 		prev_p->current->state_since = timestamp;
-		if (sw->prev_state & 2)
+		if (prev_state & 2)
 			prev_p->current->state = TYPE_BLOCKED;
-		if (sw->prev_state == 0)
+		if (prev_state == 0)
 			prev_p->current->state = TYPE_WAITING;
 	}
 }
 
-typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
-				  struct perf_sample *sample);
+static const char *cat_backtrace(union perf_event *event,
+				 struct perf_sample *sample,
+				 struct machine *machine)
+{
+	struct addr_location al;
+	unsigned int i;
+	char *p = NULL;
+	size_t p_len;
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	struct addr_location tal;
+	struct ip_callchain *chain = sample->callchain;
+	FILE *f = open_memstream(&p, &p_len);
+
+	if (!f) {
+		perror("open_memstream error");
+		return NULL;
+	}
+
+	if (!chain)
+		goto exit;
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+			event->header.type);
+		goto exit;
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip;
+
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				free(p);
+				p = NULL;
+				goto exit;
+			}
+			continue;
+		}
+
+		tal.filtered = false;
+		thread__find_addr_location(al.thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &tal);
+
+		if (tal.sym)
+			fprintf(f, "..... %016" PRIx64 " %s\n", ip,
+				tal.sym->name);
+		else
+			fprintf(f, "..... %016" PRIx64 "\n", ip);
+	}
+
+exit:
+	fclose(f);
+
+	return p;
+}
+
+typedef int (*tracepoint_handler)(struct timechart *tchart,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  const char *backtrace);
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
-				struct machine *machine __maybe_unused)
+				struct machine *machine)
 {
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+
 	if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
-		if (!first_time || first_time > sample->time)
-			first_time = sample->time;
-		if (last_time < sample->time)
-			last_time = sample->time;
+		if (!tchart->first_time || tchart->first_time > sample->time)
+			tchart->first_time = sample->time;
+		if (tchart->last_time < sample->time)
+			tchart->last_time = sample->time;
 	}
 
-	if (sample->cpu > numcpus)
-		numcpus = sample->cpu;
-
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		return f(tchart, evsel, sample,
+			 cat_backtrace(event, sample, machine));
 	}
 
 	return 0;
 }
 
 static int
-process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
-			struct perf_sample *sample)
+process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
+			struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			const char *backtrace __maybe_unused)
 {
-	struct power_processor_entry *ppe = sample->raw_data;
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	if (ppe->state == (u32) PWR_EVENT_EXIT)
-		c_state_end(ppe->cpu_id, sample->time);
+	if (state == (u32)PWR_EVENT_EXIT)
+		c_state_end(tchart, cpu_id, sample->time);
 	else
-		c_state_start(ppe->cpu_id, sample->time, ppe->state);
+		c_state_start(cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
-			     struct perf_sample *sample)
+process_sample_cpu_frequency(struct timechart *tchart,
+			     struct perf_evsel *evsel,
+			     struct perf_sample *sample,
+			     const char *backtrace __maybe_unused)
 {
-	struct power_processor_entry *ppe = sample->raw_data;
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	p_state_change(ppe->cpu_id, sample->time, ppe->state);
+	p_state_change(tchart, cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
-			    struct perf_sample *sample)
+process_sample_sched_wakeup(struct timechart *tchart,
+			    struct perf_evsel *evsel,
+			    struct perf_sample *sample,
+			    const char *backtrace)
 {
-	struct trace_entry *te = sample->raw_data;
+	u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
+	int waker = perf_evsel__intval(evsel, sample, "common_pid");
+	int wakee = perf_evsel__intval(evsel, sample, "pid");
 
-	sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+	sched_wakeup(tchart, sample->cpu, sample->time, waker, wakee, flags, backtrace);
 	return 0;
 }
 
 static int
-process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
-			    struct perf_sample *sample)
+process_sample_sched_switch(struct timechart *tchart,
+			    struct perf_evsel *evsel,
+			    struct perf_sample *sample,
+			    const char *backtrace)
 {
-	struct trace_entry *te = sample->raw_data;
+	int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
+	int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 
-	sched_switch(sample->cpu, sample->time, te);
+	sched_switch(tchart, sample->cpu, sample->time, prev_pid, next_pid,
+		     prev_state, backtrace);
 	return 0;
 }
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int
-process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
-			   struct perf_sample *sample)
+process_sample_power_start(struct timechart *tchart __maybe_unused,
+			   struct perf_evsel *evsel,
+			   struct perf_sample *sample,
+			   const char *backtrace __maybe_unused)
 {
-	struct power_entry_old *peo = sample->raw_data;
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	c_state_start(peo->cpu_id, sample->time, peo->value);
+	c_state_start(cpu_id, sample->time, value);
 	return 0;
 }
 
 static int
-process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
-			 struct perf_sample *sample)
+process_sample_power_end(struct timechart *tchart,
+			 struct perf_evsel *evsel __maybe_unused,
+			 struct perf_sample *sample,
+			 const char *backtrace __maybe_unused)
 {
-	c_state_end(sample->cpu, sample->time);
+	c_state_end(tchart, sample->cpu, sample->time);
 	return 0;
 }
 
 static int
-process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
-			       struct perf_sample *sample)
+process_sample_power_frequency(struct timechart *tchart,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       const char *backtrace __maybe_unused)
 {
-	struct power_entry_old *peo = sample->raw_data;
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	p_state_change(peo->cpu_id, sample->time, peo->value);
+	p_state_change(tchart, cpu_id, sample->time, value);
 	return 0;
 }
 #endif /* SUPPORT_OLD_POWER_EVENTS */
@@ -568,12 +641,12 @@ process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
  */
-static void end_sample_processing(void)
+static void end_sample_processing(struct timechart *tchart)
 {
 	u64 cpu;
 	struct power_event *pwr;
 
-	for (cpu = 0; cpu <= numcpus; cpu++) {
+	for (cpu = 0; cpu <= tchart->numcpus; cpu++) {
 		/* C state */
 #if 0
 		pwr = zalloc(sizeof(*pwr));
@@ -582,12 +655,12 @@ static void end_sample_processing(void)
 
 		pwr->state = cpus_cstate_state[cpu];
 		pwr->start_time = cpus_cstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = CSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
-		power_events = pwr;
+		tchart->power_events = pwr;
 #endif
 		/* P state */
 
@@ -597,32 +670,32 @@ static void end_sample_processing(void)
 
 		pwr->state = cpus_pstate_state[cpu];
 		pwr->start_time = cpus_pstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = PSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
 		if (!pwr->start_time)
-			pwr->start_time = first_time;
+			pwr->start_time = tchart->first_time;
 		if (!pwr->state)
-			pwr->state = min_freq;
-		power_events = pwr;
+			pwr->state = tchart->min_freq;
+		tchart->power_events = pwr;
 	}
 }
 
 /*
  * Sort the pid datastructure
  */
-static void sort_pids(void)
+static void sort_pids(struct timechart *tchart)
 {
 	struct per_pid *new_list, *p, *cursor, *prev;
 	/* sort by ppid first, then by pid, lowest to highest */
 
 	new_list = NULL;
 
-	while (all_data) {
-		p = all_data;
-		all_data = p->next;
+	while (tchart->all_data) {
+		p = tchart->all_data;
+		tchart->all_data = p->next;
 		p->next = NULL;
 
 		if (new_list == NULL) {
@@ -655,14 +728,14 @@ static void sort_pids(void)
 				prev->next = p;
 		}
 	}
-	all_data = new_list;
+	tchart->all_data = new_list;
 }
 
 
-static void draw_c_p_states(void)
+static void draw_c_p_states(struct timechart *tchart)
 {
 	struct power_event *pwr;
-	pwr = power_events;
+	pwr = tchart->power_events;
 
 	/*
 	 * two pass drawing so that the P state bars are on top of the C state blocks
@@ -673,30 +746,30 @@ static void draw_c_p_states(void)
 		pwr = pwr->next;
 	}
 
-	pwr = power_events;
+	pwr = tchart->power_events;
 	while (pwr) {
 		if (pwr->type == PSTATE) {
 			if (!pwr->state)
-				pwr->state = min_freq;
+				pwr->state = tchart->min_freq;
 			svg_pstate(pwr->cpu, pwr->start_time, pwr->end_time, pwr->state);
 		}
 		pwr = pwr->next;
 	}
 }
 
-static void draw_wakeups(void)
+static void draw_wakeups(struct timechart *tchart)
 {
 	struct wake_event *we;
 	struct per_pid *p;
 	struct per_pidcomm *c;
 
-	we = wake_events;
+	we = tchart->wake_events;
 	while (we) {
 		int from = 0, to = 0;
 		char *task_from = NULL, *task_to = NULL;
 
 		/* locate the column of the waker and wakee */
-		p = all_data;
+		p = tchart->all_data;
 		while (p) {
 			if (p->pid == we->waker || p->pid == we->wakee) {
 				c = p->all;
@@ -739,11 +812,12 @@ static void draw_wakeups(void)
 		}
 
 		if (we->waker == -1)
-			svg_interrupt(we->time, to);
+			svg_interrupt(we->time, to, we->backtrace);
 		else if (from && to && abs(from - to) == 1)
-			svg_wakeline(we->time, from, to);
+			svg_wakeline(we->time, from, to, we->backtrace);
 		else
-			svg_partial_wakeline(we->time, from, task_from, to, task_to);
+			svg_partial_wakeline(we->time, from, task_from, to,
+					     task_to, we->backtrace);
 		we = we->next;
 
 		free(task_from);
@@ -751,19 +825,25 @@ static void draw_wakeups(void)
 	}
 }
 
-static void draw_cpu_usage(void)
+static void draw_cpu_usage(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
 			sample = c->samples;
 			while (sample) {
-				if (sample->type == TYPE_RUNNING)
-					svg_process(sample->cpu, sample->start_time, sample->end_time, "sample", c->comm);
+				if (sample->type == TYPE_RUNNING) {
+					svg_process(sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    p->pid,
+						    c->comm,
+						    sample->backtrace);
+				}
 
 				sample = sample->next;
 			}
@@ -773,16 +853,16 @@ static void draw_cpu_usage(void)
 	}
 }
 
-static void draw_process_bars(void)
+static void draw_process_bars(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 	int Y = 0;
 
-	Y = 2 * numcpus + 2;
+	Y = 2 * tchart->numcpus + 2;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
@@ -796,11 +876,20 @@ static void draw_process_bars(void)
 			sample = c->samples;
 			while (sample) {
 				if (sample->type == TYPE_RUNNING)
-					svg_sample(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_running(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_BLOCKED)
-					svg_box(Y, sample->start_time, sample->end_time, "blocked");
+					svg_blocked(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_WAITING)
-					svg_waiting(Y, sample->start_time, sample->end_time);
+					svg_waiting(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				sample = sample->next;
 			}
 
@@ -853,21 +942,21 @@ static int passes_filter(struct per_pid *p, struct per_pidcomm *c)
 	return 0;
 }
 
-static int determine_display_tasks_filtered(void)
+static int determine_display_tasks_filtered(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
+			p->end_time = tchart->last_time;
 
 		c = p->all;
 
@@ -875,7 +964,7 @@ static int determine_display_tasks_filtered(void)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
 			if (passes_filter(p, c)) {
 				c->display = 1;
@@ -884,7 +973,7 @@ static int determine_display_tasks_filtered(void)
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -893,25 +982,25 @@ static int determine_display_tasks_filtered(void)
 	return count;
 }
 
-static int determine_display_tasks(u64 threshold)
+static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
 	if (process_filter)
-		return determine_display_tasks_filtered();
+		return determine_display_tasks_filtered(tchart);
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
-		if (p->total_time >= threshold && !power_only)
+			p->end_time = tchart->last_time;
+		if (p->total_time >= threshold)
 			p->display = 1;
 
 		c = p->all;
@@ -920,15 +1009,15 @@ static int determine_display_tasks(u64 threshold)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
-			if (c->total_time >= threshold && !power_only) {
+			if (c->total_time >= threshold) {
 				c->display = 1;
 				count++;
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -941,45 +1030,74 @@ static int determine_display_tasks(u64 threshold)
 
 #define TIME_THRESH 10000000
 
-static void write_svg_file(const char *filename)
+static void write_svg_file(struct timechart *tchart, const char *filename)
 {
 	u64 i;
 	int count;
+	int thresh = TIME_THRESH;
 
-	numcpus++;
-
+	if (tchart->power_only)
+		tchart->proc_num = 0;
 
-	count = determine_display_tasks(TIME_THRESH);
+	/* We'd like to show at least proc_num tasks;
+	 * be less picky if we have fewer */
+	do {
+		count = determine_display_tasks(tchart, thresh);
+		thresh /= 10;
+	} while (!process_filter && thresh && count < tchart->proc_num);
 
-	/* We'd like to show at least 15 tasks; be less picky if we have fewer */
-	if (count < 15)
-		count = determine_display_tasks(TIME_THRESH / 10);
-
-	open_svg(filename, numcpus, count, first_time, last_time);
+	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
 	svg_time_grid();
 	svg_legenda();
 
-	for (i = 0; i < numcpus; i++)
-		svg_cpu_box(i, max_freq, turbo_frequency);
+	for (i = 0; i < tchart->numcpus; i++)
+		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
 
-	draw_cpu_usage();
-	draw_process_bars();
-	draw_c_p_states();
-	draw_wakeups();
+	draw_cpu_usage(tchart);
+	if (tchart->proc_num)
+		draw_process_bars(tchart);
+	if (!tchart->tasks_only)
+		draw_c_p_states(tchart);
+	if (tchart->proc_num)
+		draw_wakeups(tchart);
 
 	svg_close();
 }
 
-static int __cmd_timechart(const char *output_name)
+static int process_header(struct perf_file_section *section __maybe_unused,
+			  struct perf_header *ph,
+			  int feat,
+			  int fd __maybe_unused,
+			  void *data)
+{
+	struct timechart *tchart = data;
+
+	switch (feat) {
+	case HEADER_NRCPUS:
+		tchart->numcpus = ph->env.nr_cpus_avail;
+		break;
+
+	case HEADER_CPU_TOPOLOGY:
+		if (!tchart->topology)
+			break;
+
+		if (svg_build_topology_map(ph->env.sibling_cores,
+					   ph->env.nr_sibling_cores,
+					   ph->env.sibling_threads,
+					   ph->env.nr_sibling_threads))
+			fprintf(stderr, "problem building topology\n");
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 {
-	struct perf_tool perf_timechart = {
-		.comm		 = process_comm_event,
-		.fork		 = process_fork_event,
-		.exit		 = process_exit_event,
-		.sample		 = process_sample_event,
-		.ordered_samples = true,
-	};
 	const struct perf_evsel_str_handler power_tracepoints[] = {
 		{ "power:cpu_idle",		process_sample_cpu_idle },
 		{ "power:cpu_frequency",	process_sample_cpu_frequency },
@@ -997,12 +1115,17 @@ static int __cmd_timechart(const char *output_name)
 	};
 
 	struct perf_session *session = perf_session__new(&file, false,
-							 &perf_timechart);
+							 &tchart->tool);
 	int ret = -EINVAL;
 
 	if (session == NULL)
 		return -ENOMEM;
 
+	(void)perf_header__process_sections(&session->header,
+					    perf_data_file__fd(session->file),
+					    tchart,
+					    process_header);
+
 	if (!perf_session__has_traces(session, "timechart record"))
 		goto out_delete;
 
@@ -1012,69 +1135,111 @@ static int __cmd_timechart(const char *output_name)
 		goto out_delete;
 	}
 
-	ret = perf_session__process_events(session, &perf_timechart);
+	ret = perf_session__process_events(session, &tchart->tool);
 	if (ret)
 		goto out_delete;
 
-	end_sample_processing();
+	end_sample_processing(tchart);
 
-	sort_pids();
+	sort_pids(tchart);
 
-	write_svg_file(output_name);
+	write_svg_file(tchart, output_name);
 
 	pr_info("Written %2.1f seconds of trace to %s.\n",
-		(last_time - first_time) / 1000000000.0, output_name);
+		(tchart->last_time - tchart->first_time) / 1000000000.0, output_name);
 out_delete:
 	perf_session__delete(session);
 	return ret;
 }
 
-static int __cmd_record(int argc, const char **argv)
+static int timechart__record(struct timechart *tchart, int argc, const char **argv)
 {
-#ifdef SUPPORT_OLD_POWER_EVENTS
-	const char * const record_old_args[] = {
+	unsigned int rec_argc, i, j;
+	const char **rec_argv;
+	const char **p;
+	unsigned int record_elems;
+
+	const char * const common_args[] = {
 		"record", "-a", "-R", "-c", "1",
+	};
+	unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+	const char * const backtrace_args[] = {
+		"-g",
+	};
+	unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
+
+	const char * const power_args[] = {
+		"-e", "power:cpu_frequency",
+		"-e", "power:cpu_idle",
+	};
+	unsigned int power_args_nr = ARRAY_SIZE(power_args);
+
+	const char * const old_power_args[] = {
+#ifdef SUPPORT_OLD_POWER_EVENTS
 		"-e", "power:power_start",
 		"-e", "power:power_end",
 		"-e", "power:power_frequency",
-		"-e", "sched:sched_wakeup",
-		"-e", "sched:sched_switch",
-	};
 #endif
-	const char * const record_new_args[] = {
-		"record", "-a", "-R", "-c", "1",
-		"-e", "power:cpu_frequency",
-		"-e", "power:cpu_idle",
+	};
+	unsigned int old_power_args_nr = ARRAY_SIZE(old_power_args);
+
+	const char * const tasks_args[] = {
 		"-e", "sched:sched_wakeup",
 		"-e", "sched:sched_switch",
 	};
-	unsigned int rec_argc, i, j;
-	const char **rec_argv;
-	const char * const *record_args = record_new_args;
-	unsigned int record_elems = ARRAY_SIZE(record_new_args);
+	unsigned int tasks_args_nr = ARRAY_SIZE(tasks_args);
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 	if (!is_valid_tracepoint("power:cpu_idle") &&
 	    is_valid_tracepoint("power:power_start")) {
 		use_old_power_events = 1;
-		record_args = record_old_args;
-		record_elems = ARRAY_SIZE(record_old_args);
+		power_args_nr = 0;
+	} else {
+		old_power_args_nr = 0;
 	}
 #endif
 
-	rec_argc = record_elems + argc - 1;
+	if (tchart->power_only)
+		tasks_args_nr = 0;
+
+	if (tchart->tasks_only) {
+		power_args_nr = 0;
+		old_power_args_nr = 0;
+	}
+
+	if (!tchart->with_backtrace)
+		backtrace_args_no = 0;
+
+	record_elems = common_args_nr + tasks_args_nr +
+		power_args_nr + old_power_args_nr + backtrace_args_no;
+
+	rec_argc = record_elems + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
 		return -ENOMEM;
 
-	for (i = 0; i < record_elems; i++)
-		rec_argv[i] = strdup(record_args[i]);
+	p = rec_argv;
+	for (i = 0; i < common_args_nr; i++)
+		*p++ = strdup(common_args[i]);
+
+	for (i = 0; i < backtrace_args_no; i++)
+		*p++ = strdup(backtrace_args[i]);
+
+	for (i = 0; i < tasks_args_nr; i++)
+		*p++ = strdup(tasks_args[i]);
+
+	for (i = 0; i < power_args_nr; i++)
+		*p++ = strdup(power_args[i]);
 
-	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	for (i = 0; i < old_power_args_nr; i++)
+		*p++ = strdup(old_power_args[i]);
 
-	return cmd_record(i, rec_argv, NULL);
+	for (j = 1; j < (unsigned int)argc; j++)
+		*p++ = argv[j];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
 }
 
 static int
@@ -1086,20 +1251,56 @@ parse_process(const struct option *opt __maybe_unused, const char *arg,
 	return 0;
 }
 
+static int
+parse_highlight(const struct option *opt __maybe_unused, const char *arg,
+		int __maybe_unused unset)
+{
+	unsigned long duration = strtoul(arg, NULL, 0);
+
+	if (svg_highlight || svg_highlight_name)
+		return -1;
+
+	if (duration)
+		svg_highlight = duration;
+	else
+		svg_highlight_name = strdup(arg);
+
+	return 0;
+}
+
 int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
+	struct timechart tchart = {
+		.tool = {
+			.comm		 = process_comm_event,
+			.fork		 = process_fork_event,
+			.exit		 = process_exit_event,
+			.sample		 = process_sample_event,
+			.ordered_samples = true,
+		},
+		.proc_num = 15,
+	};
 	const char *output_name = "output.svg";
-	const struct option options[] = {
+	const struct option timechart_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
-	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
+	OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
+		      "highlight tasks. Pass duration in ns or process name.",
+		       parse_highlight),
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
+	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
+		    "min. number of tasks to print"),
+	OPT_BOOLEAN('t', "topology", &tchart.topology,
+		    "sort CPUs according to topology"),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
@@ -1107,17 +1308,41 @@ int cmd_timechart(int argc, const char **argv,
 		NULL
 	};
 
-	argc = parse_options(argc, argv, options, timechart_usage,
+	const struct option record_options[] = {
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+		    "output processes data only"),
+	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
+	OPT_END()
+	};
+	const char * const record_usage[] = {
+		"perf timechart record [<options>]",
+		NULL
+	};
+	argc = parse_options(argc, argv, timechart_options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (tchart.power_only && tchart.tasks_only) {
+		pr_err("-P and -T options cannot be used at the same time.\n");
+		return -1;
+	}
+
 	symbol__init();
 
-	if (argc && !strncmp(argv[0], "rec", 3))
-		return __cmd_record(argc, argv);
-	else if (argc)
-		usage_with_options(timechart_usage, options);
+	if (argc && !strncmp(argv[0], "rec", 3)) {
+		argc = parse_options(argc, argv, record_options, record_usage,
+				     PARSE_OPT_STOP_AT_NON_OPTION);
+
+		if (tchart.power_only && tchart.tasks_only) {
+			pr_err("-P and -T options cannot be used at the same time.\n");
+			return -1;
+		}
+
+		return timechart__record(&tchart, argc, argv);
+	} else if (argc)
+		usage_with_options(timechart_usage, timechart_options);
 
 	setup_pager();
 
-	return __cmd_timechart(output_name);
+	return __cmd_timechart(&tchart, output_name);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 71e6402729a8..03d37a76c612 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -634,26 +634,9 @@ repeat:
 	return NULL;
 }
 
-/* Tag samples to be skipped. */
-static const char *skip_symbols[] = {
-	"intel_idle",
-	"default_idle",
-	"native_safe_halt",
-	"cpu_idle",
-	"enter_idle",
-	"exit_idle",
-	"mwait_idle",
-	"mwait_idle_with_hints",
-	"poll_idle",
-	"ppc64_runlatch_off",
-	"pseries_dedicated_idle_sleep",
-	NULL
-};
-
 static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
 	const char *name = sym->name;
-	int i;
 
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the
@@ -671,12 +654,8 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	    strstr(name, "_text_end"))
 		return 1;
 
-	for (i = 0; skip_symbols[i]; i++) {
-		if (!strcmp(skip_symbols[i], name)) {
-			sym->ignore = true;
-			break;
-		}
-	}
+	if (symbol__is_idle(sym))
+		sym->ignore = true;
 
 	return 0;
 }
@@ -1084,7 +1063,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "dump the symbol table used for profiling"),
 	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
-	OPT_BOOLEAN('g', "group", &opts->group,
+	OPT_BOOLEAN(0, "group", &opts->group,
 			    "put the counters into a counter group"),
 	OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
 		    "child tasks do not inherit counters"),
@@ -1105,7 +1084,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		   " abort, in_tx, transaction"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+	OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
 			   NULL, "enables call-graph recording",
 			   &callchain_opt),
 	OPT_CALLBACK(0, "call-graph", &top.record_opts,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8be17fc462ba..56bbca5bc2dc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -11,6 +11,8 @@
 #include "util/intlist.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "trace-event.h"
+#include "util/parse-events.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -172,6 +174,10 @@ static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void
 {
 	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
 
+	/* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
+	if (evsel == NULL)
+		evsel = perf_evsel__newtp("syscalls", direction);
+
 	if (evsel) {
 		if (perf_evsel__init_syscall_tp(evsel, handler))
 			goto out_delete;
@@ -1430,11 +1436,11 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	sc->fmt  = syscall_fmt__find(sc->name);
 
 	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
-	sc->tp_format = event_format__new("syscalls", tp_name);
+	sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 
 	if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) {
 		snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
-		sc->tp_format = event_format__new("syscalls", tp_name);
+		sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 	}
 
 	if (sc->tp_format == NULL)
@@ -1764,8 +1770,10 @@ static int trace__process_sample(struct perf_tool *tool,
 	if (!trace->full_time && trace->base_time == 0)
 		trace->base_time = sample->time;
 
-	if (handler)
+	if (handler) {
+		++trace->nr_events;
 		handler(trace, evsel, sample);
+	}
 
 	return err;
 }
@@ -1800,10 +1808,11 @@ static int trace__record(int argc, const char **argv)
 		"-R",
 		"-m", "1024",
 		"-c", "1",
-		"-e", "raw_syscalls:sys_enter,raw_syscalls:sys_exit",
+		"-e",
 	};
 
-	rec_argc = ARRAY_SIZE(record_args) + argc;
+	/* +1 is for the event string below */
+	rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -1812,6 +1821,17 @@ static int trace__record(int argc, const char **argv)
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = record_args[i];
 
+	/* event string may be different for older kernels - e.g., RHEL6 */
+	if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+		rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+	else if (is_valid_tracepoint("syscalls:sys_enter"))
+		rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
+	else {
+		pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+		return -1;
+	}
+	i++;
+
 	for (j = 0; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -1890,7 +1910,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
-	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
 	if (err < 0) {
 		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
 		goto out_close_evlist;
@@ -2047,6 +2067,10 @@ static int trace__replay(struct trace *trace)
 
 	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 						     "raw_syscalls:sys_enter");
+	/* older kernels have syscalls tp versus raw_syscalls */
+	if (evsel == NULL)
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "syscalls:sys_enter");
 	if (evsel == NULL) {
 		pr_err("Data file does not have raw_syscalls:sys_enter event\n");
 		goto out;
@@ -2060,6 +2084,9 @@ static int trace__replay(struct trace *trace)
 
 	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 						     "raw_syscalls:sys_exit");
+	if (evsel == NULL)
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "syscalls:sys_exit");
 	if (evsel == NULL) {
 		pr_err("Data file does not have raw_syscalls:sys_exit event\n");
 		goto out;
@@ -2158,7 +2185,6 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	size_t printed = data->printed;
 	struct trace *trace = data->trace;
 	struct thread_trace *ttrace = thread->priv;
-	const char *color;
 	double ratio;
 
 	if (ttrace == NULL)
@@ -2166,17 +2192,9 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 
 	ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
 
-	color = PERF_COLOR_NORMAL;
-	if (ratio > 50.0)
-		color = PERF_COLOR_RED;
-	else if (ratio > 25.0)
-		color = PERF_COLOR_GREEN;
-	else if (ratio > 5.0)
-		color = PERF_COLOR_YELLOW;
-
-	printed += color_fprintf(fp, color, " %s (%d), ", thread__comm_str(thread), thread->tid);
+	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
 	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
-	printed += color_fprintf(fp, color, "%.1f%%", ratio);
+	printed += fprintf(fp, "%.1f%%", ratio);
 	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
 	printed += thread__dump_stats(ttrace, trace, fp);
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f7d11a811c74..5a1f4df3c3a8 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -36,6 +36,30 @@ ifeq ($(ARCH),arm)
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
+ifeq ($(LIBUNWIND_LIBS),)
+  NO_LIBUNWIND := 1
+else
+  #
+  # For linking with debug library, run like:
+  #
+  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+  #
+  ifdef LIBUNWIND_DIR
+    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+  endif
+  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+  # Set per-feature check compilation flags
+  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
+  #  and the flags for the test-all case
+  FEATURE_CHECK_CFLAGS-all += $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-all += $(LIBUNWIND_LDFLAGS)
+endif
+
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
@@ -102,7 +126,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS="$(LDFLAGS)" LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -141,7 +165,6 @@ CORE_FEATURE_TESTS =			\
 	libslang			\
 	libunwind			\
 	on-exit				\
-	stackprotector			\
 	stackprotector-all		\
 	timerfd
 
@@ -209,10 +232,6 @@ ifeq ($(feature-stackprotector-all), 1)
   CFLAGS += -fstack-protector-all
 endif
 
-ifeq ($(feature-stackprotector), 1)
-  CFLAGS += -Wstack-protector
-endif
-
 ifeq ($(DEBUG),0)
   ifeq ($(feature-fortify-source), 1)
     CFLAGS += -D_FORTIFY_SOURCE=2
@@ -310,21 +329,7 @@ ifndef NO_LIBELF
   endif # NO_DWARF
 endif # NO_LIBELF
 
-ifeq ($(LIBUNWIND_LIBS),)
-  NO_LIBUNWIND := 1
-endif
-
 ifndef NO_LIBUNWIND
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  := -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
-  endif
-
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1);
     NO_LIBUNWIND := 1
@@ -339,14 +344,12 @@ ifndef NO_LIBUNWIND
       # non-ARM has no dwarf_find_debug_frame() function:
       CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
     endif
-  endif
-endif
 
-ifndef NO_LIBUNWIND
-  CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
-  EXTLIBS += $(LIBUNWIND_LIBS)
-  CFLAGS += $(LIBUNWIND_CFLAGS)
-  LDFLAGS += $(LIBUNWIND_LDFLAGS)
+    CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
+    EXTLIBS += $(LIBUNWIND_LIBS)
+    CFLAGS += $(LIBUNWIND_CFLAGS)
+    LDFLAGS += $(LIBUNWIND_LDFLAGS)
+  endif # ifneq ($(feature-libunwind), 1)
 endif
 
 ifndef NO_LIBAUDIT
@@ -533,7 +536,7 @@ endif
 
 ifndef NO_LIBNUMA
   ifeq ($(feature-libnuma), 0)
-    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
     CFLAGS += -DHAVE_LIBNUMA_SUPPORT
@@ -598,3 +601,11 @@ else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+
+# If we install to $(HOME) we keep the traceevent default:
+# $(HOME)/.traceevent/plugins
+# Otherwise we install plugins into the global $(libdir).
+ifdef DESTDIR
+plugindir=$(libdir)/traceevent/plugins
+plugindir_SQ= $(subst ','\'',$(prefix)/$(plugindir))
+endif
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 87e790017c69..bc86462e80a2 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -26,19 +26,18 @@ FILES=					\
 	test-libunwind-debug-frame	\
 	test-on-exit			\
 	test-stackprotector-all		\
-	test-stackprotector		\
 	test-timerfd
 
 CC := $(CC) -MD
 
 all: $(FILES)
 
-BUILD = $(CC) $(CFLAGS) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
+BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $@.c $(LDFLAGS)
 
 ###############################
 
 test-all:
-	$(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
 test-hello:
 	$(BUILD)
@@ -46,9 +45,6 @@ test-hello:
 test-stackprotector-all:
 	$(BUILD) -Werror -fstack-protector-all
 
-test-stackprotector:
-	$(BUILD) -Werror -fstack-protector -Wstack-protector
-
 test-fortify-source:
 	$(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
 
@@ -74,10 +70,10 @@ test-libnuma:
 	$(BUILD) -lnuma
 
 test-libunwind:
-	$(BUILD) $(LIBUNWIND_LIBS) -lelf
+	$(BUILD) -lelf
 
 test-libunwind-debug-frame:
-	$(BUILD) $(LIBUNWIND_LIBS) -lelf
+	$(BUILD) -lelf
 
 test-libaudit:
 	$(BUILD) -laudit
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index 59e7a705e146..9b8a544155bb 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -85,6 +85,10 @@
 # include "test-timerfd.c"
 #undef main
 
+#define main main_test_stackprotector_all
+# include "test-stackprotector-all.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -106,6 +110,7 @@ int main(int argc, char *argv[])
 	main_test_backtrace();
 	main_test_libnuma();
 	main_test_timerfd();
+	main_test_stackprotector_all();
 
 	return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-stackprotector.c b/tools/perf/config/feature-checks/test-stackprotector.c
deleted file mode 100644
index c9f398d87868..000000000000
--- a/tools/perf/config/feature-checks/test-stackprotector.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#include <stdio.h>
-
-int main(void)
-{
-	return puts("hi");
-}
diff --git a/tools/perf/bash_completion b/tools/perf/perf-completion.sh
index 62e157db2e2b..496e2abb5482 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/perf-completion.sh
@@ -1,4 +1,4 @@
-# perf completion
+# perf bash and zsh completion
 
 # Taken from git.git's completion script.
 __my_reassemble_comp_words_by_ref()
@@ -89,37 +89,117 @@ __ltrim_colon_completions()
 	fi
 }
 
-type perf &>/dev/null &&
-_perf()
+__perfcomp ()
 {
-	local cur words cword prev cmd
+	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
+}
 
-	COMPREPLY=()
-	_get_comp_words_by_ref -n =: cur words cword prev
+__perfcomp_colon ()
+{
+	__perfcomp "$1" "$2"
+	__ltrim_colon_completions $cur
+}
+
+__perf_main ()
+{
+	local cmd
 
 	cmd=${words[0]}
+	COMPREPLY=()
 
 	# List perf subcommands or long options
 	if [ $cword -eq 1 ]; then
 		if [[ $cur == --* ]]; then
-			COMPREPLY=( $( compgen -W '--help --version \
+			__perfcomp '--help --version \
 			--exec-path --html-path --paginate --no-pager \
-			--perf-dir --work-tree --debugfs-dir' -- "$cur" ) )
+			--perf-dir --work-tree --debugfs-dir' -- "$cur"
 		else
 			cmds=$($cmd --list-cmds)
-			COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+			__perfcomp "$cmds" "$cur"
 		fi
 	# List possible events for -e option
 	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
 		evts=$($cmd list --raw-dump)
-		COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
-		__ltrim_colon_completions $cur
+		__perfcomp_colon "$evts" "$cur"
+	# List subcommands for 'perf kvm'
+	elif [[ $prev == "kvm" ]]; then
+		subcmds="top record report diff buildid-list stat"
+		__perfcomp_colon "$subcmds" "$cur"
 	# List long option names
 	elif [[ $cur == --* ]];  then
 		subcmd=${words[1]}
 		opts=$($cmd $subcmd --list-opts)
-		COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
+		__perfcomp "$opts" "$cur"
 	fi
+}
+
+if [[ -n ${ZSH_VERSION-} ]]; then
+	autoload -U +X compinit && compinit
+
+	__perfcomp ()
+	{
+		emulate -L zsh
+
+		local c IFS=$' \t\n'
+		local -a array
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[${#array[@]}+1]="$c"
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	__perfcomp_colon ()
+	{
+		emulate -L zsh
+
+		local cur_="${2-$cur}"
+		local c IFS=$' \t\n'
+		local -a array
+
+		if [[ "$cur_" == *:* ]]; then
+			local colon_word=${cur_%"${cur_##*:}"}
+		fi
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[$#array+1]=${c#"$colon_word"}
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	_perf ()
+	{
+		local _ret=1 cur cword prev
+		cur=${words[CURRENT]}
+		prev=${words[CURRENT-1]}
+		let cword=CURRENT-1
+		emulate ksh -c __perf_main
+		let _ret && _default && _ret=0
+		return _ret
+	}
+
+	compdef _perf perf
+	return
+fi
+
+type perf &>/dev/null &&
+_perf()
+{
+	local cur words cword prev
+	_get_comp_words_by_ref -n =: cur words cword prev
+	__perf_main
 } &&
 
 complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 8b38b4e80ec2..431798a4110d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,7 +13,7 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <pthread.h>
 
 const char perf_usage_string[] =
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b079304bd53d..b23fed527514 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -254,6 +254,7 @@ struct perf_record_opts {
 	bool	     inherit_stat;
 	bool	     no_delay;
 	bool	     no_inherit;
+	bool	     no_inherit_set;
 	bool	     no_samples;
 	bool	     raw_samples;
 	bool	     sample_address;
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 9079a25cd643..44edcb2edcd5 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -3,5 +3,5 @@ command = record
 args    = -i kill >/dev/null 2>&1
 
 [event:base-record]
-sample_type=259
+sample_type=263
 inherit=0
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 3cbd10496087..e4ce8aed29d3 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -3,7 +3,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "fs.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index cf6242c92ee2..0fcd81ea31ae 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -900,7 +900,7 @@ fallback:
 		 * cache, or is just a kallsyms file, well, lets hope that this
 		 * DSO is the same as when 'perf record' ran.
 		 */
-		filename = dso->long_name;
+		filename = (char *)dso->long_name;
 		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
 			 symbol_conf.symfs, filename);
 		free_filename = false;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a92770c98cc7..6baabe63182b 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -89,7 +89,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf)
 	return raw - build_id;
 }
 
-char *dso__build_id_filename(struct dso *dso, char *bf, size_t size)
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 929f28a7c14d..845ef865eced 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -10,7 +10,7 @@ extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
-char *dso__build_id_filename(struct dso *dso, char *bf, size_t size);
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 7d09faf85cf1..1fbcd8bdc11b 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -118,3 +118,9 @@ void perf_data_file__close(struct perf_data_file *file)
 {
 	close(file->fd);
 }
+
+ssize_t perf_data_file__write(struct perf_data_file *file,
+			      void *buf, size_t size)
+{
+	return writen(file->fd, buf, size);
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 8c2df80152a5..2b15d0c95c7f 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -9,12 +9,12 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-	const char *path;
-	int fd;
-	bool is_pipe;
-	bool force;
-	unsigned long size;
-	enum perf_data_mode mode;
+	const char		*path;
+	int			 fd;
+	bool			 is_pipe;
+	bool			 force;
+	unsigned long		 size;
+	enum perf_data_mode	 mode;
 };
 
 static inline bool perf_data_file__is_read(struct perf_data_file *file)
@@ -44,5 +44,7 @@ static inline unsigned long perf_data_file__size(struct perf_data_file *file)
 
 int perf_data_file__open(struct perf_data_file *file);
 void perf_data_file__close(struct perf_data_file *file);
+ssize_t perf_data_file__write(struct perf_data_file *file,
+			      void *buf, size_t size);
 
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 399e74c34c1a..8640a9121e72 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -16,13 +16,11 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 
-int eprintf(int level, const char *fmt, ...)
+static int _eprintf(int level, const char *fmt, va_list args)
 {
-	va_list args;
 	int ret = 0;
 
 	if (verbose >= level) {
-		va_start(args, fmt);
 		if (use_browser >= 1)
 			ui_helpline__vshow(fmt, args);
 		else
@@ -33,6 +31,32 @@ int eprintf(int level, const char *fmt, ...)
 	return ret;
 }
 
+int eprintf(int level, const char *fmt, ...)
+{
+	va_list args;
+	int ret;
+
+	va_start(args, fmt);
+	ret = _eprintf(level, fmt, args);
+	va_end(args);
+
+	return ret;
+}
+
+/*
+ * Overloading libtraceevent standard info print
+ * function, display with -v in perf.
+ */
+void pr_stat(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	_eprintf(1, fmt, args);
+	va_end(args);
+	eprintf(1, "\n");
+}
+
 int dump_printf(const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index efbd98805ad0..443694c36b03 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -17,4 +17,6 @@ void trace_event(union perf_event *event);
 int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
 int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
+void pr_stat(const char *fmt, ...);
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index af4c687cc49b..4ddeecb9ff85 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -28,8 +28,9 @@ char dso__symtab_origin(const struct dso *dso)
 	return origin[dso->symtab_type];
 }
 
-int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
-			  char *root_dir, char *file, size_t size)
+int dso__read_binary_type_filename(const struct dso *dso,
+				   enum dso_binary_type type,
+				   char *root_dir, char *filename, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = 0;
@@ -38,36 +39,36 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 	case DSO_BINARY_TYPE__DEBUGLINK: {
 		char *debuglink;
 
-		strncpy(file, dso->long_name, size);
-		debuglink = file + dso->long_name_len;
-		while (debuglink != file && *debuglink != '/')
+		strncpy(filename, dso->long_name, size);
+		debuglink = filename + dso->long_name_len;
+		while (debuglink != filename && *debuglink != '/')
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
 		filename__read_debuglink(dso->long_name, debuglink,
-					 size - (debuglink - file));
+					 size - (debuglink - filename));
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
 		/* skip the locally configured cache if a symfs is given */
 		if (symbol_conf.symfs[0] ||
-		    (dso__build_id_filename(dso, file, size) == NULL))
+		    (dso__build_id_filename(dso, filename, size) == NULL))
 			ret = -1;
 		break;
 
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-		snprintf(file, size, "%s/usr/lib/debug%s.debug",
+		snprintf(filename, size, "%s/usr/lib/debug%s.debug",
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-		snprintf(file, size, "%s/usr/lib/debug%s",
+		snprintf(filename, size, "%s/usr/lib/debug%s",
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
-		char *last_slash;
+		const char *last_slash;
 		size_t len;
 		size_t dir_size;
 
@@ -75,14 +76,14 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 		while (last_slash != dso->long_name && *last_slash != '/')
 			last_slash--;
 
-		len = scnprintf(file, size, "%s", symbol_conf.symfs);
+		len = scnprintf(filename, size, "%s", symbol_conf.symfs);
 		dir_size = last_slash - dso->long_name + 2;
 		if (dir_size > (size - len)) {
 			ret = -1;
 			break;
 		}
-		len += scnprintf(file + len, dir_size, "%s",  dso->long_name);
-		len += scnprintf(file + len , size - len, ".debug%s",
+		len += scnprintf(filename + len, dir_size, "%s",  dso->long_name);
+		len += scnprintf(filename + len , size - len, ".debug%s",
 								last_slash);
 		break;
 	}
@@ -96,7 +97,7 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 		build_id__sprintf(dso->build_id,
 				  sizeof(dso->build_id),
 				  build_id_hex);
-		snprintf(file, size,
+		snprintf(filename, size,
 			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
 			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
 		break;
@@ -104,23 +105,23 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-		snprintf(file, size, "%s%s",
+		snprintf(filename, size, "%s%s",
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
-		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+		snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
 			 root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-		snprintf(file, size, "%s%s", symbol_conf.symfs,
+		snprintf(filename, size, "%s%s", symbol_conf.symfs,
 			 dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__KCORE:
 	case DSO_BINARY_TYPE__GUEST_KCORE:
-		snprintf(file, size, "%s", dso->long_name);
+		snprintf(filename, size, "%s", dso->long_name);
 		break;
 
 	default:
@@ -137,19 +138,18 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 
 static int open_dso(struct dso *dso, struct machine *machine)
 {
-	char *root_dir = (char *) "";
-	char *name;
 	int fd;
+	char *root_dir = (char *)"";
+	char *name = malloc(PATH_MAX);
 
-	name = malloc(PATH_MAX);
 	if (!name)
 		return -ENOMEM;
 
 	if (machine)
 		root_dir = machine->root_dir;
 
-	if (dso__binary_type_file(dso, dso->data_type,
-				  root_dir, name, PATH_MAX)) {
+	if (dso__read_binary_type_filename(dso, dso->binary_type,
+					    root_dir, name, PATH_MAX)) {
 		free(name);
 		return -EINVAL;
 	}
@@ -161,26 +161,26 @@ static int open_dso(struct dso *dso, struct machine *machine)
 
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
-	static enum dso_binary_type binary_type_data[] = {
+	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,
 		DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 		DSO_BINARY_TYPE__NOT_FOUND,
 	};
 	int i = 0;
 
-	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
 		return open_dso(dso, machine);
 
 	do {
 		int fd;
 
-		dso->data_type = binary_type_data[i++];
+		dso->binary_type = binary_type_data[i++];
 
 		fd = open_dso(dso, machine);
 		if (fd >= 0)
 			return fd;
 
-	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
 	return -EINVAL;
 }
@@ -200,11 +200,10 @@ dso_cache__free(struct rb_root *root)
 	}
 }
 
-static struct dso_cache*
-dso_cache__find(struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
+	struct rb_node * const *p = &root->rb_node;
+	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 
 	while (*p != NULL) {
@@ -379,32 +378,63 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 	 * processing we had no idea this was the kernel dso.
 	 */
 	if (dso != NULL) {
-		dso__set_short_name(dso, short_name);
+		dso__set_short_name(dso, short_name, false);
 		dso->kernel = dso_type;
 	}
 
 	return dso;
 }
 
-void dso__set_long_name(struct dso *dso, char *name)
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	if (name == NULL)
 		return;
-	dso->long_name = name;
-	dso->long_name_len = strlen(name);
+
+	if (dso->long_name_allocated)
+		free((char *)dso->long_name);
+
+	dso->long_name		 = name;
+	dso->long_name_len	 = strlen(name);
+	dso->long_name_allocated = name_allocated;
 }
 
-void dso__set_short_name(struct dso *dso, const char *name)
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	if (name == NULL)
 		return;
-	dso->short_name = name;
-	dso->short_name_len = strlen(name);
+
+	if (dso->short_name_allocated)
+		free((char *)dso->short_name);
+
+	dso->short_name		  = name;
+	dso->short_name_len	  = strlen(name);
+	dso->short_name_allocated = name_allocated;
 }
 
 static void dso__set_basename(struct dso *dso)
 {
-	dso__set_short_name(dso, basename(dso->long_name));
+       /*
+        * basename() may modify path buffer, so we must pass
+        * a copy.
+        */
+       char *base, *lname = strdup(dso->long_name);
+
+       if (!lname)
+               return;
+
+       /*
+        * basename() may return a pointer to internal
+        * storage which is reused in subsequent calls
+        * so copy the result.
+        */
+       base = strdup(basename(lname));
+
+       free(lname);
+
+       if (!base)
+               return;
+
+       dso__set_short_name(dso, base, true);
 }
 
 int dso__name_len(const struct dso *dso)
@@ -439,18 +469,19 @@ struct dso *dso__new(const char *name)
 	if (dso != NULL) {
 		int i;
 		strcpy(dso->name, name);
-		dso__set_long_name(dso, dso->name);
-		dso__set_short_name(dso, dso->name);
+		dso__set_long_name(dso, dso->name, false);
+		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->cache = RB_ROOT;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
-		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->rel = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
 		dso->has_srcline = 1;
+		dso->a2l_fails = 1;
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
@@ -464,11 +495,23 @@ void dso__delete(struct dso *dso)
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
-	if (dso->sname_alloc)
+
+	if (dso->short_name_allocated) {
 		free((char *)dso->short_name);
-	if (dso->lname_alloc)
-		free(dso->long_name);
+		dso->short_name		  = NULL;
+		dso->short_name_allocated = false;
+	}
+
+	if (dso->long_name_allocated) {
+		free((char *)dso->long_name);
+		dso->long_name		 = NULL;
+		dso->long_name_allocated = false;
+	}
+
 	dso_cache__free(&dso->cache);
+	dso__free_a2l(dso);
+	free(dso->symsrc_filename);
+	dso->symsrc_filename = NULL;
 	free(dso);
 }
 
@@ -543,7 +586,7 @@ void dsos__add(struct list_head *head, struct dso *dso)
 	list_add_tail(&dso->node, head);
 }
 
-struct dso *dsos__find(struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
 {
 	struct dso *pos;
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 9ac666abbe7e..cd7d6f078cdd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -77,23 +77,26 @@ struct dso {
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	struct rb_root	 cache;
+	void		 *a2l;
+	char		 *symsrc_filename;
+	unsigned int	 a2l_fails;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
-	enum dso_binary_type	data_type;
+	enum dso_binary_type	binary_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 has_srcline:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
-	u8		 sname_alloc:1;
-	u8		 lname_alloc:1;
+	u8		 short_name_allocated:1;
+	u8		 long_name_allocated:1;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 rel;
 	u8		 build_id[BUILD_ID_SIZE];
 	const char	 *short_name;
-	char		 *long_name;
+	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
 	char		 name[0];
@@ -107,8 +110,8 @@ static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
 
-void dso__set_short_name(struct dso *dso, const char *name);
-void dso__set_long_name(struct dso *dso, char *name);
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
@@ -125,8 +128,8 @@ void dso__read_running_kernel_build_id(struct dso *dso,
 int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 
 char dso__symtab_origin(const struct dso *dso);
-int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
-			  char *root_dir, char *file, size_t size);
+int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
+				   char *root_dir, char *filename, size_t size);
 
 int dso__data_fd(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
@@ -140,7 +143,7 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 				const char *short_name, int dso_type);
 
 void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(struct list_head *head, const char *name,
+struct dso *dsos__find(const struct list_head *head, const char *name,
 		       bool cmp_short);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
@@ -156,14 +159,16 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
 static inline bool dso__is_vmlinux(struct dso *dso)
 {
-	return dso->data_type == DSO_BINARY_TYPE__VMLINUX ||
-	       dso->data_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
+	return dso->binary_type == DSO_BINARY_TYPE__VMLINUX ||
+	       dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
 }
 
 static inline bool dso__is_kcore(struct dso *dso)
 {
-	return dso->data_type == DSO_BINARY_TYPE__KCORE ||
-	       dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE;
+	return dso->binary_type == DSO_BINARY_TYPE__KCORE ||
+	       dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
+void dso__free_a2l(struct dso *dso);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bb788c109fe6..694876877ae2 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,6 +7,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
+#include "symbol/kallsyms.h"
 
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
@@ -732,8 +733,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	if (thread == NULL)
 		return -1;
 
-	if (symbol_conf.comm_list &&
-	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread)))
+	if (thread__is_filtered(thread))
 		goto out_filtered;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bbc746aa5716..da3182914984 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -7,7 +7,7 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 #include "util.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -732,11 +732,13 @@ static long parse_pages_arg(const char *str, unsigned long min,
 			return -EINVAL;
 	}
 
-	if ((pages == 0) && (min == 0)) {
+	if (pages == 0 && min == 0) {
 		/* leave number of pages at 0 */
-	} else if (pages < (1UL << 31) && !is_power_of_2(pages)) {
+	} else if (!is_power_of_2(pages)) {
 		/* round pages up to next power of 2 */
-		pages = next_pow2(pages);
+		pages = next_pow2_l(pages);
+		if (!pages)
+			return -EINVAL;
 		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
 			pages * page_size, pages);
 	}
@@ -754,7 +756,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
 	unsigned long max = UINT_MAX;
 	long pages;
 
-	if (max < SIZE_MAX / page_size)
+	if (max > SIZE_MAX / page_size)
 		max = SIZE_MAX / page_size;
 
 	pages = parse_pages_arg(str, 1, max);
@@ -819,11 +821,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target->force_per_cpu)
-		evlist->cpus = cpu_map__new(target->cpu_list);
-	else if (target__has_task(target))
-		evlist->cpus = cpu_map__dummy_new();
-	else if (!target__has_cpu(target) && !target->uses_mmap)
+	if (target__uses_dummy_map(target))
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(target->cpu_list);
@@ -1193,8 +1191,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 				    "Error:\t%s.\n"
 				    "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
 
-		if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
-			break;
+		value = perf_event_paranoid();
 
 		printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
 
@@ -1215,3 +1212,20 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 
 	return 0;
 }
+
+void perf_evlist__to_front(struct perf_evlist *evlist,
+			   struct perf_evsel *move_evsel)
+{
+	struct perf_evsel *evsel, *n;
+	LIST_HEAD(move);
+
+	if (move_evsel == perf_evlist__first(evlist))
+		return;
+
+	list_for_each_entry_safe(evsel, n, &evlist->entries, node) {
+		if (evsel->leader == move_evsel->leader)
+			list_move_tail(&evsel->node, &move);
+	}
+
+	list_splice(&move, &evlist->entries);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 649d6ea98a84..9f64ede3ecbd 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -193,4 +193,9 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md,
 	pc->data_tail = tail;
 }
 
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
+void perf_evlist__to_front(struct perf_evlist *evlist,
+			   struct perf_evsel *move_evsel);
+
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 46dd4c2a41ce..01ff4cfde1f5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -9,7 +9,7 @@
 
 #include <byteswap.h>
 #include <linux/bitops.h>
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
@@ -23,6 +23,7 @@
 #include "target.h"
 #include "perf_regs.h"
 #include "debug.h"
+#include "trace-event.h"
 
 static struct {
 	bool sample_id_all;
@@ -162,6 +163,8 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->idx	   = idx;
 	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
+	evsel->unit	   = "";
+	evsel->scale	   = 1.0;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
@@ -178,47 +181,6 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-struct event_format *event_format__new(const char *sys, const char *name)
-{
-	int fd, n;
-	char *filename;
-	void *bf = NULL, *nbf;
-	size_t size = 0, alloc_size = 0;
-	struct event_format *format = NULL;
-
-	if (asprintf(&filename, "%s/%s/%s/format", tracing_events_path, sys, name) < 0)
-		goto out;
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		goto out_free_filename;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (nbf == NULL)
-				goto out_free_bf;
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0)
-			goto out_free_bf;
-		size += n;
-	} while (n > 0);
-
-	pevent_parse_format(&format, bf, size, sys);
-
-out_free_bf:
-	free(bf);
-	close(fd);
-out_free_filename:
-	free(filename);
-out:
-	return format;
-}
-
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
 	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
@@ -233,7 +195,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
 		if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
 			goto out_free;
 
-		evsel->tp_format = event_format__new(sys, name);
+		evsel->tp_format = trace_event__tp_format(sys, name);
 		if (evsel->tp_format == NULL)
 			goto out_free;
 
@@ -572,6 +534,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
+	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
@@ -645,7 +608,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		}
 	}
 
-	if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
+	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
@@ -653,7 +616,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target) || opts->target.force_per_cpu))
+	     target__has_cpu(&opts->target) || per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 1ea7c92e6e33..8120eeb86ac1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -68,6 +68,8 @@ struct perf_evsel {
 	u32			ids;
 	struct hists		hists;
 	char			*name;
+	double			scale;
+	const char		*unit;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -138,6 +140,7 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 					    char *bf, size_t size);
 const char *perf_evsel__name(struct perf_evsel *evsel);
+
 const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1cd035708931..61c54213704b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -177,7 +177,7 @@ perf_header__set_cmdline(int argc, const char **argv)
 			continue;		\
 		else
 
-static int write_buildid(char *name, size_t name_len, u8 *build_id,
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 			 pid_t pid, u16 misc, int fd)
 {
 	int err;
@@ -209,7 +209,7 @@ static int __dsos__write_buildid_table(struct list_head *head,
 
 	dsos__for_each_with_build_id(pos, head) {
 		int err;
-		char  *name;
+		const char *name;
 		size_t name_len;
 
 		if (!pos->hit)
@@ -387,7 +387,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
 	bool is_vdso = is_vdso_map(dso->short_name);
-	char *name = dso->long_name;
+	const char *name = dso->long_name;
 	char nm[PATH_MAX];
 
 	if (dso__is_kcore(dso)) {
@@ -1709,7 +1709,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
 			  struct perf_header *ph, int fd,
 			  void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	u32 nr;
 
 	ret = readn(fd, &nr, sizeof(nr));
@@ -1753,7 +1753,7 @@ static int process_total_mem(struct perf_file_section *section __maybe_unused,
 			     void *data __maybe_unused)
 {
 	uint64_t mem;
-	size_t ret;
+	ssize_t ret;
 
 	ret = readn(fd, &mem, sizeof(mem));
 	if (ret != sizeof(mem))
@@ -1822,7 +1822,7 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused,
 			   struct perf_header *ph, int fd,
 			   void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	char *str;
 	u32 nr, i;
 	struct strbuf sb;
@@ -1858,7 +1858,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 				struct perf_header *ph, int fd,
 				void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	u32 nr, i;
 	char *str;
 	struct strbuf sb;
@@ -1914,7 +1914,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 				 struct perf_header *ph, int fd,
 				 void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	u32 nr, node, i;
 	char *str;
 	uint64_t mem_total, mem_free;
@@ -1974,7 +1974,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
 				struct perf_header *ph, int fd,
 				void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	char *name;
 	u32 pmu_num;
 	u32 type;
@@ -2327,7 +2327,8 @@ int perf_session__write_header(struct perf_session *session,
 		}
 	}
 
-	header->data_offset = lseek(fd, 0, SEEK_CUR);
+	if (!header->data_offset)
+		header->data_offset = lseek(fd, 0, SEEK_CUR);
 	header->feat_offset = header->data_offset + header->data_size;
 
 	if (at_exit) {
@@ -2534,7 +2535,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd)
 {
-	int ret;
+	ssize_t ret;
 
 	lseek(fd, 0, SEEK_SET);
 
@@ -2628,7 +2629,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 				       struct perf_header *ph, int fd,
 				       bool repipe)
 {
-	int ret;
+	ssize_t ret;
 
 	ret = readn(fd, header, sizeof(*header));
 	if (ret <= 0)
@@ -2669,7 +2670,7 @@ static int read_attr(int fd, struct perf_header *ph,
 	struct perf_event_attr *attr = &f_attr->attr;
 	size_t sz, left;
 	size_t our_sz = sizeof(f_attr->attr);
-	int ret;
+	ssize_t ret;
 
 	memset(f_attr, 0, sizeof(*f_attr));
 
@@ -2834,11 +2835,11 @@ int perf_session__read_header(struct perf_session *session)
 
 	symbol_conf.nr_events = nr_attrs;
 
-	perf_header__process_sections(header, fd, &session->pevent,
+	perf_header__process_sections(header, fd, &session->tevent,
 				      perf_file_section__process);
 
 	if (perf_evlist__prepare_tracepoint_events(session->evlist,
-						   session->pevent))
+						   session->tevent.pevent))
 		goto out_delete_evlist;
 
 	return 0;
@@ -3003,7 +3004,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
 	lseek(fd, offset + sizeof(struct tracing_data_event),
 	      SEEK_SET);
 
-	size_read = trace_report(fd, &session->pevent,
+	size_read = trace_report(fd, &session->tevent,
 				 session->repipe);
 	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
@@ -3025,7 +3026,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
 	}
 
 	perf_evlist__prepare_tracepoint_events(session->evlist,
-					       session->pevent);
+					       session->tevent.pevent);
 
 	return size_read + padding;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 84cdb072ac83..c78cc84f433e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include <stdbool.h>
+#include <symbol/kallsyms.h>
 #include "unwind.h"
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
@@ -502,15 +503,11 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
 	char path[PATH_MAX];
 	struct process_args args;
 
-	if (machine__is_host(machine)) {
-		filename = "/proc/kallsyms";
-	} else {
-		if (machine__is_default_guest(machine))
-			filename = (char *)symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
+	if (machine__is_default_guest(machine))
+		filename = (char *)symbol_conf.default_guest_kallsyms;
+	else {
+		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+		filename = path;
 	}
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
@@ -767,8 +764,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 				ret = -1;
 				goto out;
 			}
-			dso__set_long_name(map->dso, long_name);
-			map->dso->lname_alloc = 1;
+			dso__set_long_name(map->dso, long_name, true);
 			dso__kernel_module_get_build_id(map->dso, "");
 		}
 	}
@@ -939,8 +935,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (name == NULL)
 			goto out_problem;
 
-		map->dso->short_name = name;
-		map->dso->sname_alloc = 1;
+		dso__set_short_name(map->dso, name, true);
 		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
 		const char *symbol_name = (event->mmap.filename +
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index ef5bc913ca7a..9b9bd719aa19 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -11,6 +11,7 @@
 #include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
+#include "util.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -252,6 +253,22 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 	return fprintf(fp, "%s", dsoname);
 }
 
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp)
+{
+	char *srcline;
+	int ret = 0;
+
+	if (map && map->dso) {
+		srcline = get_srcline(map->dso,
+				      map__rip_2objdump(map, addr));
+		if (srcline != SRCLINE_UNKNOWN)
+			ret = fprintf(fp, "%s%s", prefix, srcline);
+		free_srcline(srcline);
+	}
+	return ret;
+}
+
 /**
  * map__rip_2objdump - convert symbol start address to objdump address.
  * @map: memory map
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index e4e259c3ba16..18068c6b71c1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -103,6 +103,8 @@ struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp);
 
 int map__load(struct map *map, symbol_filter_t filter);
 struct symbol *map__find_symbol(struct map *map,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6de6f89c2a61..094c28ba2fae 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,7 +10,7 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
@@ -269,9 +269,10 @@ const char *event_type(int type)
 
 
 
-static int __add_event(struct list_head *list, int *idx,
-		       struct perf_event_attr *attr,
-		       char *name, struct cpu_map *cpus)
+static struct perf_evsel *
+__add_event(struct list_head *list, int *idx,
+	    struct perf_event_attr *attr,
+	    char *name, struct cpu_map *cpus)
 {
 	struct perf_evsel *evsel;
 
@@ -279,19 +280,19 @@ static int __add_event(struct list_head *list, int *idx,
 
 	evsel = perf_evsel__new_idx(attr, (*idx)++);
 	if (!evsel)
-		return -ENOMEM;
+		return NULL;
 
 	evsel->cpus = cpus;
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
-	return 0;
+	return evsel;
 }
 
 static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, char *name)
 {
-	return __add_event(list, idx, attr, name, NULL);
+	return __add_event(list, idx, attr, name, NULL) ? 0 : -ENOMEM;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -633,6 +634,9 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 {
 	struct perf_event_attr attr;
 	struct perf_pmu *pmu;
+	struct perf_evsel *evsel;
+	char *unit;
+	double scale;
 
 	pmu = perf_pmu__find(name);
 	if (!pmu)
@@ -640,7 +644,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
 	memset(&attr, 0, sizeof(attr));
 
-	if (perf_pmu__check_alias(pmu, head_config))
+	if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
 		return -EINVAL;
 
 	/*
@@ -652,8 +656,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (perf_pmu__config(pmu, &attr, head_config))
 		return -EINVAL;
 
-	return __add_event(list, idx, &attr, pmu_event_name(head_config),
-			   pmu->cpus);
+	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
+			    pmu->cpus);
+	if (evsel) {
+		evsel->unit = unit;
+		evsel->scale = scale;
+	}
+
+	return evsel ? 0 : -ENOMEM;
 }
 
 int parse_events__modifier_group(struct list_head *list,
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 31f404a032a9..d22e3f8017dc 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -78,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 
 	case OPTION_BOOLEAN:
 		*(bool *)opt->value = unset ? false : true;
+		if (opt->set)
+			*(bool *)opt->set = true;
 		return 0;
 
 	case OPTION_INCR:
@@ -224,6 +226,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
 			return 0;
 		}
 		if (!rest) {
+			if (!prefixcmp(options->long_name, "no-")) {
+				/*
+				 * The long name itself starts with "no-", so
+				 * accept the option without "no-" so that users
+				 * do not have to enter "no-no-" to get the
+				 * negation.
+				 */
+				rest = skip_prefix(arg, options->long_name + 3);
+				if (rest) {
+					flags |= OPT_UNSET;
+					goto match;
+				}
+				/* Abbreviated case */
+				if (!prefixcmp(options->long_name + 3, arg)) {
+					flags |= OPT_UNSET;
+					goto is_abbreviated;
+				}
+			}
 			/* abbreviated? */
 			if (!strncmp(options->long_name, arg, arg_end - arg)) {
 is_abbreviated:
@@ -259,6 +279,7 @@ is_abbreviated:
 			if (!rest)
 				continue;
 		}
+match:
 		if (*rest) {
 			if (*rest != '=')
 				continue;
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b0241e28eaf7..cbf0149cf221 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
  *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
+ *
+ * `set`::
+ *   whether an option was set by the user
  */
 struct option {
 	enum parse_opt_type type;
@@ -94,6 +97,7 @@ struct option {
 	int flags;
 	parse_opt_cb *callback;
 	intptr_t defval;
+	bool *set;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -103,6 +107,10 @@ struct option {
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
 #define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
 #define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_BOOLEAN_SET(s, l, v, os, h) \
+	{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
+	.value = check_vtype(v, bool *), .help = (h), \
+	.set = check_vtype(os, bool *)}
 #define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index c232d8dd410b..56fc10a5e288 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,19 +1,23 @@
 #include <linux/list.h>
 #include <sys/types.h>
-#include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <dirent.h>
 #include "fs.h"
+#include <locale.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
 
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
 struct perf_pmu_alias {
 	char *name;
 	struct list_head terms;
 	struct list_head list;
+	char unit[UNIT_MAX_LEN+1];
+	double scale;
 };
 
 struct perf_pmu_format {
@@ -94,7 +98,80 @@ static int pmu_format(const char *name, struct list_head *format)
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	struct stat st;
+	ssize_t sret;
+	char scale[128];
+	int fd, ret = -1;
+	char path[PATH_MAX];
+	char *lc;
+
+	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	if (fstat(fd, &st) < 0)
+		goto error;
+
+	sret = read(fd, scale, sizeof(scale)-1);
+	if (sret < 0)
+		goto error;
+
+	scale[sret] = '\0';
+	/*
+	 * save current locale
+	 */
+	lc = setlocale(LC_NUMERIC, NULL);
+
+	/*
+	 * force to C locale to ensure kernel
+	 * scale string is converted correctly.
+	 * kernel uses default C locale.
+	 */
+	setlocale(LC_NUMERIC, "C");
+
+	alias->scale = strtod(scale, NULL);
+
+	/* restore locale */
+	setlocale(LC_NUMERIC, lc);
+
+	ret = 0;
+error:
+	close(fd);
+	return ret;
+}
+
+static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	ssize_t sret;
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	if (sret < 0)
+		goto error;
+
+	close(fd);
+
+	alias->unit[sret] = '\0';
+
+	return 0;
+error:
+	close(fd);
+	alias->unit[0] = '\0';
+	return -1;
+}
+
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
 	struct perf_pmu_alias *alias;
 	char buf[256];
@@ -110,6 +187,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&alias->terms);
+	alias->scale = 1.0;
+	alias->unit[0] = '\0';
+
 	ret = parse_events_terms(&alias->terms, buf);
 	if (ret) {
 		free(alias);
@@ -117,7 +197,14 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
 	}
 
 	alias->name = strdup(name);
+	/*
+	 * load unit name and scale if available
+	 */
+	perf_pmu__parse_unit(alias, dir, name);
+	perf_pmu__parse_scale(alias, dir, name);
+
 	list_add_tail(&alias->list, list);
+
 	return 0;
 }
 
@@ -129,6 +216,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
+	size_t len;
 	int ret = 0;
 
 	event_dir = opendir(dir);
@@ -143,13 +231,24 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 		if (!strcmp(name, ".") || !strcmp(name, ".."))
 			continue;
 
+		/*
+		 * skip .unit and .scale info files
+		 * parsed in perf_pmu__new_alias()
+		 */
+		len = strlen(name);
+		if (len > 5 && !strcmp(name + len - 5, ".unit"))
+			continue;
+		if (len > 6 && !strcmp(name + len - 6, ".scale"))
+			continue;
+
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
 		ret = -EINVAL;
 		file = fopen(path, "r");
 		if (!file)
 			break;
-		ret = perf_pmu__new_alias(head, name, file);
+
+		ret = perf_pmu__new_alias(head, dir, name, file);
 		fclose(file);
 	}
 
@@ -508,16 +607,42 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 	return NULL;
 }
 
+
+static int check_unit_scale(struct perf_pmu_alias *alias,
+			    char **unit, double *scale)
+{
+	/*
+	 * Only one term in event definition can
+	 * define unit and scale, fail if there's
+	 * more than one.
+	 */
+	if ((*unit && alias->unit) ||
+	    (*scale && alias->scale))
+		return -EINVAL;
+
+	if (alias->unit)
+		*unit = alias->unit;
+
+	if (alias->scale)
+		*scale = alias->scale;
+
+	return 0;
+}
+
 /*
  * Find alias in the terms list and replace it with the terms
  * defined for the alias
  */
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+			  char **unit, double *scale)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	*unit   = NULL;
+	*scale  = 0;
+
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
 		if (!alias)
@@ -525,6 +650,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
 		ret = pmu_alias_terms(alias, &term->list);
 		if (ret)
 			return ret;
+
+		ret = check_unit_scale(alias, unit, scale);
+		if (ret)
+			return ret;
+
 		list_del(&term->list);
 		free(term);
 	}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1179b26f244a..9183380e2038 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -28,7 +28,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms);
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+			  char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				  struct list_head *head_terms);
 int perf_pmu_wrap(void);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9c6989ca2bea..544ac1898a9f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,7 +40,7 @@
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
@@ -154,7 +154,7 @@ static struct dso *kernel_get_module_dso(const char *module)
 
 	vmlinux_name = symbol_conf.vmlinux_name;
 	if (vmlinux_name) {
-		if (dso__load_vmlinux(dso, map, vmlinux_name, NULL) <= 0)
+		if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
 			return NULL;
 	} else {
 		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 239036fb2b2c..595bfc73d2ed 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -18,4 +18,5 @@ util/cgroup.c
 util/rblist.c
 util/strlist.c
 util/fs.c
+util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index c8845b107f60..e5104538c354 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -177,3 +177,40 @@ int perf_record_opts__config(struct perf_record_opts *opts)
 {
 	return perf_record_opts__config_freq(opts);
 }
+
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
+{
+	struct perf_evlist *temp_evlist;
+	struct perf_evsel *evsel;
+	int err, fd, cpu;
+	bool ret = false;
+
+	temp_evlist = perf_evlist__new();
+	if (!temp_evlist)
+		return false;
+
+	err = parse_events(temp_evlist, str);
+	if (err)
+		goto out_delete;
+
+	evsel = perf_evlist__last(temp_evlist);
+
+	if (!evlist || cpu_map__empty(evlist->cpus)) {
+		struct cpu_map *cpus = cpu_map__new(NULL);
+
+		cpu =  cpus ? cpus->map[0] : 0;
+		cpu_map__delete(cpus);
+	} else {
+		cpu = evlist->cpus->map[0];
+	}
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd >= 0) {
+		close(fd);
+		ret = true;
+	}
+
+out_delete:
+	perf_evlist__delete(temp_evlist);
+	return ret;
+}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f36d24a02445..989b2e377626 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -247,27 +247,6 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	}
 }
  
-void mem_bswap_32(void *src, int byte_size)
-{
-	u32 *m = src;
-	while (byte_size > 0) {
-		*m = bswap_32(*m);
-		byte_size -= sizeof(u32);
-		++m;
-	}
-}
-
-void mem_bswap_64(void *src, int byte_size)
-{
-	u64 *m = src;
-
-	while (byte_size > 0) {
-		*m = bswap_64(*m);
-		byte_size -= sizeof(u64);
-		++m;
-	}
-}
-
 static void swap_sample_id_all(union perf_event *event, void *data)
 {
 	void *end = (void *) event + event->header.size;
@@ -1158,7 +1137,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session,
 	void *buf = NULL;
 	int skip = 0;
 	u64 head;
-	int err;
+	ssize_t err;
 	void *p;
 
 	perf_tool__fill_defaults(tool);
@@ -1487,28 +1466,23 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 	return NULL;
 }
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
-			  struct perf_sample *sample, struct machine *machine,
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+			  struct machine *machine, struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth)
 {
-	struct addr_location al;
 	struct callchain_cursor_node *node;
 	int print_ip = print_opts & PRINT_IP_OPT_IP;
 	int print_sym = print_opts & PRINT_IP_OPT_SYM;
 	int print_dso = print_opts & PRINT_IP_OPT_DSO;
 	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
 	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
+	int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
 	char s = print_oneline ? ' ' : '\t';
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
-		error("problem processing %d event, skipping it.\n",
-			event->header.type);
-		return;
-	}
-
 	if (symbol_conf.use_callchain && sample->callchain) {
+		struct addr_location node_al;
 
-		if (machine__resolve_callchain(machine, evsel, al.thread,
+		if (machine__resolve_callchain(machine, evsel, al->thread,
 					       sample, NULL, NULL,
 					       PERF_MAX_STACK_DEPTH) != 0) {
 			if (verbose)
@@ -1517,20 +1491,31 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 		}
 		callchain_cursor_commit(&callchain_cursor);
 
+		if (print_symoffset)
+			node_al = *al;
+
 		while (stack_depth) {
+			u64 addr = 0;
+
 			node = callchain_cursor_current(&callchain_cursor);
 			if (!node)
 				break;
 
+			if (node->sym && node->sym->ignore)
+				goto next;
+
 			if (print_ip)
 				printf("%c%16" PRIx64, s, node->ip);
 
+			if (node->map)
+				addr = node->map->map_ip(node->map, node->ip);
+
 			if (print_sym) {
 				printf(" ");
 				if (print_symoffset) {
-					al.addr = node->ip;
-					al.map  = node->map;
-					symbol__fprintf_symname_offs(node->sym, &al, stdout);
+					node_al.addr = addr;
+					node_al.map  = node->map;
+					symbol__fprintf_symname_offs(node->sym, &node_al, stdout);
 				} else
 					symbol__fprintf_symname(node->sym, stdout);
 			}
@@ -1541,32 +1526,42 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 				printf(")");
 			}
 
+			if (print_srcline)
+				map__fprintf_srcline(node->map, addr, "\n  ",
+						     stdout);
+
 			if (!print_oneline)
 				printf("\n");
 
-			callchain_cursor_advance(&callchain_cursor);
-
 			stack_depth--;
+next:
+			callchain_cursor_advance(&callchain_cursor);
 		}
 
 	} else {
+		if (al->sym && al->sym->ignore)
+			return;
+
 		if (print_ip)
 			printf("%16" PRIx64, sample->ip);
 
 		if (print_sym) {
 			printf(" ");
 			if (print_symoffset)
-				symbol__fprintf_symname_offs(al.sym, &al,
+				symbol__fprintf_symname_offs(al->sym, al,
 							     stdout);
 			else
-				symbol__fprintf_symname(al.sym, stdout);
+				symbol__fprintf_symname(al->sym, stdout);
 		}
 
 		if (print_dso) {
 			printf(" (");
-			map__fprintf_dsoname(al.map, stdout);
+			map__fprintf_dsoname(al->map, stdout);
 			printf(")");
 		}
+
+		if (print_srcline)
+			map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 	}
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 50f640958f0f..9c25d49900af 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
+#include "trace-event.h"
 #include "hist.h"
 #include "event.h"
 #include "header.h"
@@ -32,7 +33,7 @@ struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
 	struct perf_evlist	*evlist;
-	struct pevent		*pevent;
+	struct trace_event	tevent;
 	struct events_stats	stats;
 	bool			repipe;
 	struct ordered_samples	ordered_samples;
@@ -44,6 +45,7 @@ struct perf_session {
 #define PRINT_IP_OPT_DSO		(1<<2)
 #define PRINT_IP_OPT_SYMOFFSET	(1<<3)
 #define PRINT_IP_OPT_ONELINE	(1<<4)
+#define PRINT_IP_OPT_SRCLINE	(1<<5)
 
 struct perf_tool;
 
@@ -72,8 +74,6 @@ int perf_session__resolve_callchain(struct perf_session *session,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg);
 
-void mem_bswap_64(void *src, int byte_size);
-void mem_bswap_32(void *src, int byte_size);
 void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *session);
@@ -105,8 +105,8 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
-			  struct perf_sample *sample, struct machine *machine,
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+			  struct machine *machine, struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 58ea5ca6c255..d0aee4b9dfd4 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -25,7 +25,7 @@ cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
-liblk = getenv('LIBLK')
+libapikfs = getenv('LIBAPIKFS')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -34,7 +34,7 @@ perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
-		  extra_objects = [libtraceevent, liblk],
+		  extra_objects = [libtraceevent, libapikfs],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index d11aefbc4b8d..58b2bd8f38c9 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -146,18 +146,24 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 }
 
 static int addr2line(const char *dso_name, unsigned long addr,
-		     char **file, unsigned int *line)
+		     char **file, unsigned int *line, struct dso *dso)
 {
 	int ret = 0;
-	struct a2l_data *a2l;
+	struct a2l_data *a2l = dso->a2l;
+
+	if (!a2l) {
+		dso->a2l = addr2line_init(dso_name);
+		a2l = dso->a2l;
+	}
 
-	a2l = addr2line_init(dso_name);
 	if (a2l == NULL) {
 		pr_warning("addr2line_init failed for %s\n", dso_name);
 		return 0;
 	}
 
 	a2l->addr = addr;
+	a2l->found = false;
+
 	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
 	if (a2l->found && a2l->filename) {
@@ -168,14 +174,26 @@ static int addr2line(const char *dso_name, unsigned long addr,
 			ret = 1;
 	}
 
-	addr2line_cleanup(a2l);
 	return ret;
 }
 
+void dso__free_a2l(struct dso *dso)
+{
+	struct a2l_data *a2l = dso->a2l;
+
+	if (!a2l)
+		return;
+
+	addr2line_cleanup(a2l);
+
+	dso->a2l = NULL;
+}
+
 #else /* HAVE_LIBBFD_SUPPORT */
 
 static int addr2line(const char *dso_name, unsigned long addr,
-		     char **file, unsigned int *line_nr)
+		     char **file, unsigned int *line_nr,
+		     struct dso *dso __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
@@ -219,42 +237,58 @@ out:
 	pclose(fp);
 	return ret;
 }
+
+void dso__free_a2l(struct dso *dso __maybe_unused)
+{
+}
+
 #endif /* HAVE_LIBBFD_SUPPORT */
 
+/*
+ * Number of addr2line failures (without success) before disabling it for that
+ * dso.
+ */
+#define A2L_FAIL_LIMIT 123
+
 char *get_srcline(struct dso *dso, unsigned long addr)
 {
 	char *file = NULL;
 	unsigned line = 0;
 	char *srcline;
-	char *dso_name = dso->long_name;
-	size_t size;
+	const char *dso_name;
 
 	if (!dso->has_srcline)
 		return SRCLINE_UNKNOWN;
 
+	if (dso->symsrc_filename)
+		dso_name = dso->symsrc_filename;
+	else
+		dso_name = dso->long_name;
+
 	if (dso_name[0] == '[')
 		goto out;
 
 	if (!strncmp(dso_name, "/tmp/perf-", 10))
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line))
+	if (!addr2line(dso_name, addr, &file, &line, dso))
 		goto out;
 
-	/* just calculate actual length */
-	size = snprintf(NULL, 0, "%s:%u", file, line) + 1;
+	if (asprintf(&srcline, "%s:%u", file, line) < 0) {
+		free(file);
+		goto out;
+	}
 
-	srcline = malloc(size);
-	if (srcline)
-		snprintf(srcline, size, "%s:%u", file, line);
-	else
-		srcline = SRCLINE_UNKNOWN;
+	dso->a2l_fails = 0;
 
 	free(file);
 	return srcline;
 
 out:
-	dso->has_srcline = 0;
+	if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
+		dso->has_srcline = 0;
+		dso__free_a2l(dso);
+	}
 	return SRCLINE_UNKNOWN;
 }
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96c866045d60..56a84f2cc46d 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -17,8 +17,11 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
+#include <linux/bitops.h>
 
+#include "perf.h"
 #include "svghelper.h"
+#include "cpumap.h"
 
 static u64 first_time, last_time;
 static u64 turbo_frequency, max_freq;
@@ -28,6 +31,8 @@ static u64 turbo_frequency, max_freq;
 #define SLOT_HEIGHT 25.0
 
 int svg_page_width = 1000;
+u64 svg_highlight;
+const char *svg_highlight_name;
 
 #define MIN_TEXT_SIZE 0.01
 
@@ -39,9 +44,14 @@ static double cpu2slot(int cpu)
 	return 2 * cpu + 1;
 }
 
+static int *topology_map;
+
 static double cpu2y(int cpu)
 {
-	return cpu2slot(cpu) * SLOT_MULT;
+	if (topology_map)
+		return cpu2slot(topology_map[cpu]) * SLOT_MULT;
+	else
+		return cpu2slot(cpu) * SLOT_MULT;
 }
 
 static double time2pixels(u64 __time)
@@ -95,6 +105,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
 	total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
 	fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
+	fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n");
 	fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
 	fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
@@ -103,6 +114,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "      rect.process  { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample   { fill:rgb(  0,  0,255); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.sample_hi{ fill:rgb(255,128,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.blocked  { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.waiting  { fill:rgb(224,214,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.WAITING  { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
@@ -128,14 +140,42 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
-void svg_sample(int Yslot, int cpu, u64 start, u64 end)
+static char *time_to_string(u64 duration);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
+{
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
+		time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace);
+	svg_box(Yslot, start, end, "blocked");
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	double text_size;
+	const char *type;
+
 	if (!svgfile)
 		return;
 
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
-		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
+	if (svg_highlight && end - start > svg_highlight)
+		type = "sample_hi";
+	else
+		type = "sample";
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>#%d running %s</title>\n",
+		cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
+	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
+		type);
 
 	text_size = (time2pixels(end)-time2pixels(start));
 	if (cpu > 9)
@@ -148,6 +188,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end)
 		fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
 			time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *time_to_string(u64 duration)
@@ -168,7 +209,7 @@ static char *time_to_string(u64 duration)
 	return text;
 }
 
-void svg_waiting(int Yslot, u64 start, u64 end)
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	char *text;
 	const char *style;
@@ -192,6 +233,9 @@ void svg_waiting(int Yslot, u64 start, u64 end)
 	font_size = round_text_size(font_size);
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
@@ -242,28 +286,42 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	max_freq = __max_freq;
 	turbo_frequency = __turbo_freq;
 
+	fprintf(svgfile, "<g>\n");
+
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
 		time2pixels(first_time),
 		time2pixels(last_time)-time2pixels(first_time),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
 
-	sprintf(cpu_string, "CPU %i", (int)cpu+1);
+	sprintf(cpu_string, "CPU %i", (int)cpu);
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
 
 	fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace)
 {
 	double width;
+	const char *type;
 
 	if (!svgfile)
 		return;
 
+	if (svg_highlight && end - start >= svg_highlight)
+		type = "sample_hi";
+	else if (svg_highlight_name && strstr(name, svg_highlight_name))
+		type = "sample_hi";
+	else
+		type = "sample";
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+	fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
@@ -288,6 +346,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
 	if (type > 6)
 		type = 6;
 	sprintf(style, "c%i", type);
@@ -306,6 +366,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 	if (width > MIN_TEXT_SIZE)
 		fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
 			time2pixels(start), cpu2y(cpu)+width, width, type);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *HzToHuman(unsigned long hz)
@@ -339,6 +401,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
 	if (max_freq)
 		height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
 	height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
@@ -347,10 +411,11 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
 		time2pixels(start), height+0.9, HzToHuman(freq));
 
+	fprintf(svgfile, "</g>\n");
 }
 
 
-void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2)
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace)
 {
 	double height;
 
@@ -358,6 +423,15 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>%s wakes up %s</title>\n",
+		desc1 ? desc1 : "?",
+		desc2 ? desc2 : "?");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2) {
 		if (row1) {
 			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
@@ -395,9 +469,11 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	if (row1)
 		fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_wakeline(u64 start, int row1, int row2)
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 {
 	double height;
 
@@ -405,6 +481,11 @@ void svg_wakeline(u64 start, int row1, int row2)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2)
 		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
@@ -417,17 +498,28 @@ void svg_wakeline(u64 start, int row1, int row2)
 		height += SLOT_HEIGHT;
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_interrupt(u64 start, int row)
+void svg_interrupt(u64 start, int row, const char *backtrace)
 {
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_text(int Yslot, u64 start, const char *text)
@@ -455,6 +547,7 @@ void svg_legenda(void)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
 	svg_legenda_box(0,	"Running", "sample");
 	svg_legenda_box(100,	"Idle","c1");
 	svg_legenda_box(200,	"Deeper Idle", "c3");
@@ -462,6 +555,7 @@ void svg_legenda(void)
 	svg_legenda_box(550,	"Sleeping", "process2");
 	svg_legenda_box(650,	"Waiting for cpu", "waiting");
 	svg_legenda_box(800,	"Blocked on IO", "blocked");
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_time_grid(void)
@@ -499,3 +593,123 @@ void svg_close(void)
 		svgfile = NULL;
 	}
 }
+
+#define cpumask_bits(maskp) ((maskp)->bits)
+typedef struct { DECLARE_BITMAP(bits, MAX_NR_CPUS); } cpumask_t;
+
+struct topology {
+	cpumask_t *sib_core;
+	int sib_core_nr;
+	cpumask_t *sib_thr;
+	int sib_thr_nr;
+};
+
+static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos)
+{
+	int i;
+	int thr;
+
+	for (i = 0; i < t->sib_thr_nr; i++) {
+		if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i])))
+			continue;
+
+		for_each_set_bit(thr,
+				 cpumask_bits(&t->sib_thr[i]),
+				 MAX_NR_CPUS)
+			if (map[thr] == -1)
+				map[thr] = (*pos)++;
+	}
+}
+
+static void scan_core_topology(int *map, struct topology *t)
+{
+	int pos = 0;
+	int i;
+	int cpu;
+
+	for (i = 0; i < t->sib_core_nr; i++)
+		for_each_set_bit(cpu,
+				 cpumask_bits(&t->sib_core[i]),
+				 MAX_NR_CPUS)
+			scan_thread_topology(map, t, cpu, &pos);
+}
+
+static int str_to_bitmap(char *s, cpumask_t *b)
+{
+	int i;
+	int ret = 0;
+	struct cpu_map *m;
+	int c;
+
+	m = cpu_map__new(s);
+	if (!m)
+		return -1;
+
+	for (i = 0; i < m->nr; i++) {
+		c = m->map[i];
+		if (c >= MAX_NR_CPUS) {
+			ret = -1;
+			break;
+		}
+
+		set_bit(c, cpumask_bits(b));
+	}
+
+	cpu_map__delete(m);
+
+	return ret;
+}
+
+int svg_build_topology_map(char *sib_core, int sib_core_nr,
+			   char *sib_thr, int sib_thr_nr)
+{
+	int i;
+	struct topology t;
+
+	t.sib_core_nr = sib_core_nr;
+	t.sib_thr_nr = sib_thr_nr;
+	t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t));
+	t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t));
+
+	if (!t.sib_core || !t.sib_thr) {
+		fprintf(stderr, "topology: no memory\n");
+		goto exit;
+	}
+
+	for (i = 0; i < sib_core_nr; i++) {
+		if (str_to_bitmap(sib_core, &t.sib_core[i])) {
+			fprintf(stderr, "topology: can't parse siblings map\n");
+			goto exit;
+		}
+
+		sib_core += strlen(sib_core) + 1;
+	}
+
+	for (i = 0; i < sib_thr_nr; i++) {
+		if (str_to_bitmap(sib_thr, &t.sib_thr[i])) {
+			fprintf(stderr, "topology: can't parse siblings map\n");
+			goto exit;
+		}
+
+		sib_thr += strlen(sib_thr) + 1;
+	}
+
+	topology_map = malloc(sizeof(int) * MAX_NR_CPUS);
+	if (!topology_map) {
+		fprintf(stderr, "topology: no memory\n");
+		goto exit;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++)
+		topology_map[i] = -1;
+
+	scan_core_topology(topology_map, &t);
+
+	return 0;
+
+exit:
+	free(t.sib_core);
+	free(t.sib_thr);
+
+	return -1;
+}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e0781989cc31..f7b4d6e699ea 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -5,24 +5,29 @@
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_sample(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_waiting(int Yslot, u64 start, u64 end);
+extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name);
+extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
 extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 
 extern void svg_time_grid(void);
 extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2);
-extern void svg_interrupt(u64 start, int row);
+extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+extern void svg_interrupt(u64 start, int row, const char *backtrace);
 extern void svg_text(int Yslot, u64 start, const char *text);
 extern void svg_close(void);
+extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
+				  char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
+extern u64 svg_highlight;
+extern const char *svg_highlight_name;
 
 #endif /* __PERF_SVGHELPER_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index eed0b96302af..bf0ce29567b6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include <symbol/kallsyms.h>
 #include "debug.h"
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 2d2dd0532b5a..ac7070a2f2b6 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -253,6 +253,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused,
 	if (!ss->name)
 		goto out_close;
 
+	ss->fd = fd;
 	ss->type = type;
 
 	return 0;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c0c36965fff0..923d00040bbf 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -18,12 +18,9 @@
 
 #include <elf.h>
 #include <limits.h>
+#include <symbol/kallsyms.h>
 #include <sys/utsname.h>
 
-#ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
-#endif
-
 static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter);
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
@@ -446,62 +443,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 	return ret;
 }
 
-int kallsyms__parse(const char *filename, void *arg,
-		    int (*process_symbol)(void *arg, const char *name,
-					  char type, u64 start))
-{
-	char *line = NULL;
-	size_t n;
-	int err = -1;
-	FILE *file = fopen(filename, "r");
-
-	if (file == NULL)
-		goto out_failure;
-
-	err = 0;
-
-	while (!feof(file)) {
-		u64 start;
-		int line_len, len;
-		char symbol_type;
-		char *symbol_name;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0 || !line)
-			break;
-
-		line[--line_len] = '\0'; /* \n */
-
-		len = hex2u64(line, &start);
-
-		len++;
-		if (len + 2 >= line_len)
-			continue;
-
-		symbol_type = line[len];
-		len += 2;
-		symbol_name = line + len;
-		len = line_len - len;
-
-		if (len >= KSYM_NAME_LEN) {
-			err = -1;
-			break;
-		}
-
-		err = process_symbol(arg, symbol_name,
-				     symbol_type, start);
-		if (err)
-			break;
-	}
-
-	free(line);
-	fclose(file);
-	return err;
-
-out_failure:
-	return -1;
-}
-
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
 					 u64 start))
@@ -565,12 +506,34 @@ struct process_kallsyms_args {
 	struct dso *dso;
 };
 
-static u8 kallsyms2elf_type(char type)
+bool symbol__is_idle(struct symbol *sym)
 {
-	if (type == 'W')
-		return STB_WEAK;
+	const char * const idle_symbols[] = {
+		"cpu_idle",
+		"intel_idle",
+		"default_idle",
+		"native_safe_halt",
+		"enter_idle",
+		"exit_idle",
+		"mwait_idle",
+		"mwait_idle_with_hints",
+		"poll_idle",
+		"ppc64_runlatch_off",
+		"pseries_dedicated_idle_sleep",
+		NULL
+	};
+
+	int i;
+
+	if (!sym)
+		return false;
+
+	for (i = 0; idle_symbols[i]; i++) {
+		if (!strcmp(idle_symbols[i], sym->name))
+			return true;
+	}
 
-	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
+	return false;
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,
@@ -1126,10 +1089,10 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	 * dso__data_read_addr().
 	 */
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE;
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
 	else
-		dso->data_type = DSO_BINARY_TYPE__KCORE;
-	dso__set_long_name(dso, strdup(kcore_filename));
+		dso->binary_type = DSO_BINARY_TYPE__KCORE;
+	dso__set_long_name(dso, strdup(kcore_filename), true);
 
 	close(fd);
 
@@ -1295,8 +1258,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 		enum dso_binary_type symtab_type = binary_type_symtab[i];
 
-		if (dso__binary_type_file(dso, symtab_type,
-					  root_dir, name, PATH_MAX))
+		if (dso__read_binary_type_filename(dso, symtab_type,
+						   root_dir, name, PATH_MAX))
 			continue;
 
 		/* Name is now the name of the next image to try */
@@ -1306,6 +1269,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		if (!syms_ss && symsrc__has_symtab(ss)) {
 			syms_ss = ss;
 			next_slot = true;
+			if (!dso->symsrc_filename)
+				dso->symsrc_filename = strdup(name);
 		}
 
 		if (!runtime_ss && symsrc__possibly_runtime(ss)) {
@@ -1376,7 +1341,8 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, symbol_filter_t filter)
+		      const char *vmlinux, bool vmlinux_allocated,
+		      symbol_filter_t filter)
 {
 	int err = -1;
 	struct symsrc ss;
@@ -1402,10 +1368,10 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 
 	if (err > 0) {
 		if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-			dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+			dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 		else
-			dso->data_type = DSO_BINARY_TYPE__VMLINUX;
-		dso__set_long_name(dso, (char *)vmlinux);
+			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
+		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
 		dso__set_loaded(dso, map->type);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
@@ -1424,21 +1390,16 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 
 	filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
-		err = dso__load_vmlinux(dso, map, filename, filter);
-		if (err > 0) {
-			dso->lname_alloc = 1;
+		err = dso__load_vmlinux(dso, map, filename, true, filter);
+		if (err > 0)
 			goto out;
-		}
 		free(filename);
 	}
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
-		if (err > 0) {
-			dso__set_long_name(dso, strdup(vmlinux_path[i]));
-			dso->lname_alloc = 1;
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
+		if (err > 0)
 			break;
-		}
 	}
 out:
 	return err;
@@ -1496,14 +1457,15 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
+	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
+		  sbuild_id);
+
 	/* Use /proc/kallsyms if possible */
 	if (is_host) {
 		DIR *d;
 		int fd;
 
 		/* If no cached kcore go with /proc/kallsyms */
-		scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
-			  buildid_dir, sbuild_id);
 		d = opendir(path);
 		if (!d)
 			goto proc_kallsyms;
@@ -1528,6 +1490,10 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 		goto proc_kallsyms;
 	}
 
+	/* Find kallsyms in build-id cache with kcore */
+	if (!find_matching_kcore(map, path, sizeof(path)))
+		return strdup(path);
+
 	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
 		  buildid_dir, sbuild_id);
 
@@ -1570,15 +1536,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 	}
 
 	if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
-		err = dso__load_vmlinux(dso, map,
-					symbol_conf.vmlinux_name, filter);
-		if (err > 0) {
-			dso__set_long_name(dso,
-					   strdup(symbol_conf.vmlinux_name));
-			dso->lname_alloc = 1;
-			return err;
-		}
-		return err;
+		return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name,
+					 false, filter);
 	}
 
 	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
@@ -1604,7 +1563,7 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
-		dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
+		dso__set_long_name(dso, "[kernel.kallsyms]", false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1634,7 +1593,8 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 		 */
 		if (symbol_conf.default_guest_vmlinux_name != NULL) {
 			err = dso__load_vmlinux(dso, map,
-				symbol_conf.default_guest_vmlinux_name, filter);
+						symbol_conf.default_guest_vmlinux_name,
+						false, filter);
 			return err;
 		}
 
@@ -1651,7 +1611,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
 		machine__mmap_name(machine, path, sizeof(path));
-		dso__set_long_name(dso, strdup(path));
+		dso__set_long_name(dso, strdup(path), true);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1719,7 +1679,7 @@ out_fail:
 	return -1;
 }
 
-static int setup_list(struct strlist **list, const char *list_str,
+int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
 	if (list_str == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 07de8fea2f48..8a9d910c5345 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -206,7 +206,8 @@ bool symsrc__possibly_runtime(struct symsrc *ss);
 
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, symbol_filter_t filter);
+		      const char *vmlinux, bool vmlinux_allocated,
+		      symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
@@ -220,9 +221,6 @@ struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
-int kallsyms__parse(const char *filename, void *arg,
-		    int (*process_symbol)(void *arg, const char *name,
-					  char type, u64 start));
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
 					 u64 start));
@@ -240,6 +238,7 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
+bool symbol__is_idle(struct symbol *sym);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
@@ -273,4 +272,7 @@ void kcore_extract__delete(struct kcore_extract *kce);
 int kcore_copy(const char *from_dir, const char *to_dir);
 int compare_proc_modules(const char *from, const char *to);
 
+int setup_list(struct strlist **list, const char *list_str,
+	       const char *list_name);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3c778a07b7cc..e74c5963dc7a 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
 			ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
 	}
 
+	/* THREAD and SYSTEM/CPU are mutually exclusive */
+	if (target->per_thread && (target->system_wide || target->cpu_list)) {
+		target->per_thread = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+	}
+
 	return ret;
 }
 
@@ -100,6 +107,7 @@ static const char *target__error_str[] = {
 	"UID switch overriding CPU",
 	"PID/TID switch overriding SYSTEM",
 	"UID switch overriding SYSTEM",
+	"SYSTEM/CPU switch overriding PER-THREAD",
 	"Invalid User: %s",
 	"Problems obtaining information for user %s",
 };
@@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
 	msg = target__error_str[idx];
 
 	switch (errnum) {
-	case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
+	case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+	     TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
 		snprintf(buf, buflen, "%s", msg);
 		break;
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 2d0c50690892..7381b1ca4041 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,7 +12,8 @@ struct target {
 	uid_t	     uid;
 	bool	     system_wide;
 	bool	     uses_mmap;
-	bool	     force_per_cpu;
+	bool	     default_per_cpu;
+	bool	     per_thread;
 };
 
 enum target_errno {
@@ -33,6 +34,7 @@ enum target_errno {
 	TARGET_ERRNO__UID_OVERRIDE_CPU,
 	TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
 	TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
+	TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
 
 	/* for target__parse_uid() */
 	TARGET_ERRNO__INVALID_UID,
@@ -61,4 +63,17 @@ static inline bool target__none(struct target *target)
 	return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__uses_dummy_map(struct target *target)
+{
+	bool use_dummy = false;
+
+	if (target->default_per_cpu)
+		use_dummy = target->per_thread ? true : false;
+	else if (target__has_task(target) ||
+	         (!target__has_cpu(target) && !target->uses_mmap))
+		use_dummy = true;
+
+	return use_dummy;
+}
+
 #endif /* _PERF_TARGET_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 49eaf1d7d89d..e3948612543e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -126,7 +126,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 		if (!comm)
 			return -ENOMEM;
 		err = thread__set_comm(thread, comm, timestamp);
-		if (!err)
+		if (err)
 			return err;
 		thread->comm_set = true;
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 897c1b2a750a..5b856bf942e1 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include "symbol.h"
+#include <strlist.h>
 
 struct thread {
 	union {
@@ -66,4 +67,15 @@ static inline void thread__set_priv(struct thread *thread, void *p)
 {
 	thread->priv = p;
 }
+
+static inline bool thread__is_filtered(struct thread *thread)
+{
+	if (symbol_conf.comm_list &&
+	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
+		return true;
+	}
+
+	return false;
+}
+
 #endif	/* __PERF_THREAD_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index f3c9e551bd35..c354b95a2348 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,7 +38,7 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "evsel.h"
 
 #define VERSION "0.5"
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 6681f71f2f95..e0d6d07f6848 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -28,19 +28,6 @@
 #include "util.h"
 #include "trace-event.h"
 
-struct pevent *read_trace_init(int file_bigendian, int host_bigendian)
-{
-	struct pevent *pevent = pevent_alloc();
-
-	if (pevent != NULL) {
-		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-		pevent_set_file_bigendian(pevent, file_bigendian);
-		pevent_set_host_bigendian(pevent, host_bigendian);
-	}
-
-	return pevent;
-}
-
 static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f2112270c663..e113e180c48f 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -343,7 +343,7 @@ static int read_event_files(struct pevent *pevent)
 	return 0;
 }
 
-ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
+ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
 	char buf[BUFSIZ];
 	char test[] = { 23, 8, 68 };
@@ -356,11 +356,9 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 	int host_bigendian;
 	int file_long_size;
 	int file_page_size;
-	struct pevent *pevent;
+	struct pevent *pevent = NULL;
 	int err;
 
-	*ppevent = NULL;
-
 	repipe = __repipe;
 	input_fd = fd;
 
@@ -390,12 +388,17 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
-	pevent = read_trace_init(file_bigendian, host_bigendian);
-	if (pevent == NULL) {
-		pr_debug("read_trace_init failed");
+	if (trace_event__init(tevent)) {
+		pr_debug("trace_event__init failed");
 		goto out;
 	}
 
+	pevent = tevent->pevent;
+
+	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+	pevent_set_file_bigendian(pevent, file_bigendian);
+	pevent_set_host_bigendian(pevent, host_bigendian);
+
 	if (do_read(buf, 1) < 0)
 		goto out;
 	file_long_size = buf[0];
@@ -432,11 +435,10 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 		pevent_print_printk(pevent);
 	}
 
-	*ppevent = pevent;
 	pevent = NULL;
 
 out:
 	if (pevent)
-		pevent_free(pevent);
+		trace_event__cleanup(tevent);
 	return size;
 }
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
new file mode 100644
index 000000000000..d9f5f6137ab3
--- /dev/null
+++ b/tools/perf/util/trace-event.c
@@ -0,0 +1,82 @@
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include <traceevent/event-parse.h>
+#include "trace-event.h"
+#include "util.h"
+
+/*
+ * global trace_event object used by trace_event__tp_format
+ *
+ * TODO There's no cleanup call for this. Add some sort of
+ * __exit function support and call trace_event__cleanup
+ * there.
+ */
+static struct trace_event tevent;
+
+int trace_event__init(struct trace_event *t)
+{
+	struct pevent *pevent = pevent_alloc();
+
+	if (pevent) {
+		t->plugin_list = traceevent_load_plugins(pevent);
+		t->pevent  = pevent;
+	}
+
+	return pevent ? 0 : -1;
+}
+
+void trace_event__cleanup(struct trace_event *t)
+{
+	pevent_free(t->pevent);
+	traceevent_unload_plugins(t->plugin_list);
+}
+
+static struct event_format*
+tp_format(const char *sys, const char *name)
+{
+	struct pevent *pevent = tevent.pevent;
+	struct event_format *event = NULL;
+	char path[PATH_MAX];
+	size_t size;
+	char *data;
+
+	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
+		  tracing_events_path, sys, name);
+
+	if (filename__read_str(path, &data, &size))
+		return NULL;
+
+	pevent_parse_format(pevent, &event, data, size, sys);
+
+	free(data);
+	return event;
+}
+
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name)
+{
+	static bool initialized;
+
+	if (!initialized) {
+		int be = traceevent_host_bigendian();
+		struct pevent *pevent;
+
+		if (trace_event__init(&tevent))
+			return NULL;
+
+		pevent = tevent.pevent;
+		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+		pevent_set_file_bigendian(pevent, be);
+		pevent_set_host_bigendian(pevent, be);
+		initialized = true;
+	}
+
+	return tp_format(sys, name);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 04df63114109..3a01618c5b87 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,17 +3,26 @@
 
 #include <traceevent/event-parse.h>
 #include "parse-events.h"
-#include "session.h"
 
 struct machine;
 struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
+struct plugin_list;
+
+struct trace_event {
+	struct pevent		*pevent;
+	struct plugin_list	*plugin_list;
+};
+
+int trace_event__init(struct trace_event *t);
+void trace_event__cleanup(struct trace_event *t);
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name);
 
 int bigendian(void);
 
-struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
 void event_format__print(struct event_format *event,
 			 int cpu, void *data, int size);
 
@@ -27,7 +36,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
 
-ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
+ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
 struct event_format *trace_find_next_event(struct pevent *pevent,
 					   struct event_format *event);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 28a0a89c1f73..42ad667bb317 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,11 +1,17 @@
 #include "../perf.h"
 #include "util.h"
+#include "fs.h"
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <limits.h>
+#include <byteswap.h>
+#include <linux/kernel.h>
 
 /*
  * XXX We need to find a better place for these things...
@@ -151,21 +157,40 @@ unsigned long convert_unit(unsigned long value, char *unit)
 	return value;
 }
 
-int readn(int fd, void *buf, size_t n)
+static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
 {
 	void *buf_start = buf;
+	size_t left = n;
 
-	while (n) {
-		int ret = read(fd, buf, n);
+	while (left) {
+		ssize_t ret = is_read ? read(fd, buf, left) :
+					write(fd, buf, left);
 
 		if (ret <= 0)
 			return ret;
 
-		n -= ret;
-		buf += ret;
+		left -= ret;
+		buf  += ret;
 	}
 
-	return buf - buf_start;
+	BUG_ON((size_t)(buf - buf_start) != n);
+	return n;
+}
+
+/*
+ * Read exactly 'n' bytes or return an error.
+ */
+ssize_t readn(int fd, void *buf, size_t n)
+{
+	return ion(true, fd, buf, n);
+}
+
+/*
+ * Write exactly 'n' bytes or return an error.
+ */
+ssize_t writen(int fd, void *buf, size_t n)
+{
+	return ion(false, fd, buf, n);
 }
 
 size_t hex_width(u64 v)
@@ -413,3 +438,102 @@ int filename__read_int(const char *filename, int *value)
 	close(fd);
 	return err;
 }
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	size_t size = 0, alloc_size = 0;
+	void *bf = NULL, *nbf;
+	int fd, n, err = 0;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (!nbf) {
+				err = -ENOMEM;
+				break;
+			}
+
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, alloc_size - size);
+		if (n < 0) {
+			if (size) {
+				pr_warning("read failed %d: %s\n",
+					   errno, strerror(errno));
+				err = 0;
+			} else
+				err = -errno;
+
+			break;
+		}
+
+		size += n;
+	} while (n > 0);
+
+	if (!err) {
+		*sizep = size;
+		*buf   = bf;
+	} else
+		free(bf);
+
+	close(fd);
+	return err;
+}
+
+const char *get_filename_for_perf_kvm(void)
+{
+	const char *filename;
+
+	if (perf_host && !perf_guest)
+		filename = strdup("perf.data.host");
+	else if (!perf_host && perf_guest)
+		filename = strdup("perf.data.guest");
+	else
+		filename = strdup("perf.data.kvm");
+
+	return filename;
+}
+
+int perf_event_paranoid(void)
+{
+	char path[PATH_MAX];
+	const char *procfs = procfs__mountpoint();
+	int value;
+
+	if (!procfs)
+		return INT_MAX;
+
+	scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
+
+	if (filename__read_int(path, &value))
+		return INT_MAX;
+
+	return value;
+}
+
+void mem_bswap_32(void *src, int byte_size)
+{
+	u32 *m = src;
+	while (byte_size > 0) {
+		*m = bswap_32(*m);
+		byte_size -= sizeof(u32);
+		++m;
+	}
+}
+
+void mem_bswap_64(void *src, int byte_size)
+{
+	u64 *m = src;
+
+	while (byte_size > 0) {
+		*m = bswap_64(*m);
+		byte_size -= sizeof(u64);
+		++m;
+	}
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c8f362daba87..9a2c268ad718 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -71,8 +71,9 @@
 #include <linux/magic.h>
 #include "types.h"
 #include <sys/ttydefaults.h>
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <termios.h>
+#include <linux/bitops.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -253,7 +254,8 @@ bool strlazymatch(const char *str, const char *pat);
 int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
-int readn(int fd, void *buf, size_t size);
+ssize_t readn(int fd, void *buf, size_t n);
+ssize_t writen(int fd, void *buf, size_t n);
 
 struct perf_event_attr;
 
@@ -280,6 +282,17 @@ static inline unsigned next_pow2(unsigned x)
 	return 1ULL << (32 - __builtin_clz(x - 1));
 }
 
+static inline unsigned long next_pow2_l(unsigned long x)
+{
+#if BITS_PER_LONG == 64
+	if (x <= (1UL << 31))
+		return next_pow2(x);
+	return (unsigned long)next_pow2(x >> 32) << 32;
+#else
+	return next_pow2(x);
+#endif
+}
+
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
@@ -307,4 +320,11 @@ char *get_srcline(struct dso *dso, unsigned long addr);
 void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
+int perf_event_paranoid(void);
+
+void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
+
+const char *get_filename_for_perf_kvm(void);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 39159822d58f..0ddb3b8a89ec 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -103,7 +103,7 @@ struct dso *vdso__dso_findnew(struct list_head *head)
 		dso = dso__new(VDSO__MAP_NAME);
 		if (dso != NULL) {
 			dsos__add(head, dso);
-			dso__set_long_name(dso, file);
+			dso__set_long_name(dso, file, false);
 		}
 	}
 
diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore
new file mode 100644
index 000000000000..05838f6f2ebe
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/.gitignore
@@ -0,0 +1,6 @@
+initrd
+linux-2.6
+b[0-9]*
+rcu-test-image
+res
+*.swp
diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh
new file mode 100644
index 000000000000..9f9ffcd427d3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh
@@ -0,0 +1,25 @@
+#!/bin/sh
+# Usage: sh config2frag.sh < .config > configfrag
+#
+# Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the
+# resulting file becomes a legitimate Kconfig fragment.
+#
+# 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>
+
+LANG=C sed -e 's/^# CONFIG_\([a-zA-Z0-9_]*\) is not set$/CONFIG_\1=n/'
diff --git a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
new file mode 100755
index 000000000000..43540f1828cc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+#
+# Extract the number of CPUs expected from the specified Kconfig-file
+# fragment by checking CONFIG_SMP and CONFIG_NR_CPUS.  If the specified
+# file gives no clue, base the number on the number of idle CPUs on
+# the system.
+#
+# 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>
+
+cf=$1
+if test ! -r $cf
+then
+	echo Unreadable config fragment $cf 1>&2
+	exit -1
+fi
+if grep -q '^CONFIG_SMP=n$' $cf
+then
+	echo 1
+	exit 0
+fi
+if grep -q '^CONFIG_NR_CPUS=' $cf
+then
+	grep '^CONFIG_NR_CPUS=' $cf | 
+		sed -e 's/^CONFIG_NR_CPUS=\([0-9]*\).*$/\1/'
+	exit 0
+fi
+cpus2use.sh
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
new file mode 100755
index 000000000000..d686537dd55c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -0,0 +1,54 @@
+#!/bin/sh
+# Usage: sh 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.
+#
+# 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>
+
+T=/tmp/abat-chk-config.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+cat $1 > $T/.config
+
+cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' |
+awk	'
+BEGIN	{
+		print "if grep -q \"" $0 "\" < '"$T/.config"'";
+		print "then";
+		print "\t:";
+		print "else";
+		if ($1 == "#") {
+			print "\tif grep -q \"" $2 "\" < '"$T/.config"'";
+			print "\tthen";
+			print "\t\tif test \"$firsttime\" = \"\""
+			print "\t\tthen"
+			print "\t\t\tfirsttime=1"
+			print "\t\tfi"
+			print "\t\techo \":" $2 ": improperly set\"";
+			print "\telse";
+			print "\t\t:";
+			print "\tfi";
+		} else {
+			print "\tif test \"$firsttime\" = \"\""
+			print "\tthen"
+			print "\t\tfirsttime=1"
+			print "\tfi"
+			print "\techo \":" $0 ": improperly set\"";
+		}
+		print "fi";
+	}' | sh
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
new file mode 100755
index 000000000000..a1be6e62add1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -0,0 +1,74 @@
+#!/bin/sh
+#
+# sh configinit.sh config-spec-file [ build output dir ]
+#
+# Create a .config file from the spec file.  Run from the kernel source tree.
+# Exits with 0 if all went well, with 1 if all went well but the config
+# did not match, and some other number for other failures.
+#
+# The first argument is the .config specification file, which contains
+# desired settings, for example, "CONFIG_NO_HZ=y".  For best results,
+# this should be a full pathname.
+#
+# The second argument is a optional path to a build output directory,
+# 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>
+
+T=/tmp/configinit.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+# Capture config spec file.
+
+c=$1
+buildloc=$2
+builddir=
+if test -n $buildloc
+then
+	if echo $buildloc | grep -q '^O='
+	then
+		builddir=`echo $buildloc | sed -e 's/^O=//'`
+		if test ! -d $builddir
+		then
+			mkdir $builddir
+		fi
+	else
+		echo Bad build directory: \"$builddir\"
+		exit 2
+	fi
+fi
+
+sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
+sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh
+grep '^grep' < $T/u.sh > $T/upd.sh
+echo "cat - $c" >> $T/upd.sh
+make mrproper
+make $buildloc distclean > $builddir/Make.distclean 2>&1
+make $buildloc defconfig > $builddir/Make.defconfig.out 2>&1
+mv $builddir/.config $builddir/.config.sav
+sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
+cp $builddir/.config $builddir/.config.new
+yes '' | make $buildloc oldconfig > $builddir/Make.modconfig.out 2>&1
+
+# verify new config matches specification.
+configcheck.sh $builddir/.config $c
+
+exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
new file mode 100755
index 000000000000..abe14b7f36e9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+#
+# Get an estimate of how CPU-hoggy to be.
+#
+# Usage: cpus2use.sh
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
+idlecpus=`mpstat | tail -1 | \
+	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'`
+awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null '
+BEGIN {
+	cpus2use = idlecpus;
+	if (cpus2use < 1)
+		cpus2use = 1;
+	if (cpus2use < ncpus / 10)
+		cpus2use = ncpus / 10;
+	if (cpus2use == int(cpus2use))
+		cpus2use = int(cpus2use)
+	else
+		cpus2use = int(cpus2use) + 1
+	print cpus2use;
+}'
+
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
new file mode 100644
index 000000000000..587561d7c035
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -0,0 +1,198 @@
+#!/bin/bash
+#
+# 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>
+
+# bootparam_hotplug_cpu bootparam-string
+#
+# Returns 1 if the specified boot-parameter string tells rcutorture to
+# test CPU-hotplug operations.
+bootparam_hotplug_cpu () {
+	echo "$1" | grep -q "rcutorture\.onoff_"
+}
+
+# checkarg --argname argtype $# arg mustmatch cannotmatch
+#
+# Checks the specified argument "arg" against the mustmatch and cannotmatch
+# patterns.
+checkarg () {
+	if test $3 -le 1
+	then
+		echo $1 needs argument $2 matching \"$5\"
+		usage
+	fi
+	if echo "$4" | grep -q -e "$5"
+	then
+		:
+	else
+		echo $1 $2 \"$4\" must match \"$5\"
+		usage
+	fi
+	if echo "$4" | grep -q -e "$6"
+	then
+		echo $1 $2 \"$4\" must not match \"$6\"
+		usage
+	fi
+}
+
+# configfrag_boot_params bootparam-string config-fragment-file
+#
+# Adds boot parameters from the .boot file, if any.
+configfrag_boot_params () {
+	if test -r "$2.boot"
+	then
+		echo $1 `grep -v '^#' "$2.boot" | tr '\012' ' '`
+	else
+		echo $1
+	fi
+}
+
+# configfrag_hotplug_cpu config-fragment-file
+#
+# Returns 1 if the config fragment specifies hotplug CPU.
+configfrag_hotplug_cpu () {
+	if test ! -r "$1"
+	then
+		echo Unreadable config fragment "$1" 1>&2
+		exit -1
+	fi
+	grep -q '^CONFIG_HOTPLUG_CPU=y$' "$1"
+}
+
+# identify_qemu builddir
+#
+# Returns our best guess as to which qemu command is appropriate for
+# the kernel at hand.  Override with the RCU_QEMU_CMD environment variable.
+identify_qemu () {
+	local u="`file "$1"`"
+	if test -n "$RCU_QEMU_CMD"
+	then
+		echo $RCU_QEMU_CMD
+	elif echo $u | grep -q x86-64
+	then
+		echo qemu-system-x86_64
+	elif echo $u | grep -q "Intel 80386"
+	then
+		echo qemu-system-i386
+	elif uname -a | grep -q ppc64
+	then
+		echo qemu-system-ppc64
+	else
+		echo Cannot figure out what qemu command to use! 1>&2
+		# Usually this will be one of /usr/bin/qemu-system-*
+		# Use RCU_QEMU_CMD environment variable or appropriate
+		# argument to top-level script.
+		exit 1
+	fi
+}
+
+# identify_qemu_append qemu-cmd
+#
+# Output arguments for the qemu "-append" string based on CPU type
+# and the RCU_QEMU_INTERACTIVE environment variable.
+identify_qemu_append () {
+	case "$1" in
+	qemu-system-x86_64|qemu-system-i386)
+		echo noapic selinux=0 initcall_debug debug
+		;;
+	esac
+	if test -n "$RCU_QEMU_INTERACTIVE"
+	then
+		echo root=/dev/sda
+	else
+		echo console=ttyS0
+	fi
+}
+
+# identify_qemu_args qemu-cmd serial-file
+#
+# Output arguments for qemu arguments based on the RCU_QEMU_MAC
+# and RCU_QEMU_INTERACTIVE environment variables.
+identify_qemu_args () {
+	case "$1" in
+	qemu-system-x86_64|qemu-system-i386)
+		;;
+	qemu-system-ppc64)
+		echo -enable-kvm -M pseries -cpu POWER7 -nodefaults
+		echo -device spapr-vscsi
+		if test -n "$RCU_QEMU_INTERACTIVE" -a -n "$RCU_QEMU_MAC"
+		then
+			echo -device spapr-vlan,netdev=net0,mac=$RCU_QEMU_MAC
+			echo -netdev bridge,br=br0,id=net0
+		elif test -n "$RCU_QEMU_INTERACTIVE"
+		then
+			echo -net nic -net user
+		fi
+		;;
+	esac
+	if test -n "$RCU_QEMU_INTERACTIVE"
+	then
+		echo -monitor stdio -serial pty -S
+	else
+		echo -serial file:$2
+	fi
+}
+
+# identify_qemu_vcpus
+#
+# Returns the number of virtual CPUs available to the aggregate of the
+# guest OSes.
+identify_qemu_vcpus () {
+	lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://'
+}
+
+# print_bug
+#
+# Prints "BUG: " in red followed by remaining arguments
+print_bug () {
+	printf '\033[031mBUG: \033[m'
+	echo $*
+}
+
+# print_warning
+#
+# Prints "WARNING: " in yellow followed by remaining arguments
+print_warning () {
+	printf '\033[033mWARNING: \033[m'
+	echo $*
+}
+
+# specify_qemu_cpus qemu-cmd qemu-args #cpus
+#
+# Appends a string containing "-smp XXX" to qemu-args, unless the incoming
+# qemu-args already contains "-smp".
+specify_qemu_cpus () {
+	local nt;
+
+	if echo $2 | grep -q -e -smp
+	then
+		echo $2
+	else
+		case "$1" in
+		qemu-system-x86_64|qemu-system-i386)
+			echo $2 -smp $3
+			;;
+		qemu-system-ppc64)
+			nt="`lscpu | grep '^NUMA node0' | sed -e 's/^[^,]*,\([0-9]*\),.*$/\1/'`"
+			echo $2 -smp cores=`expr \( $3 + $nt - 1 \) / $nt`,threads=$nt
+			;;
+		esac
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
new file mode 100755
index 000000000000..197901ec10bf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -0,0 +1,71 @@
+#!/bin/bash
+#
+# Build a kvm-ready Linux kernel from the tree in the current directory.
+#
+# Usage: sh kvm-build.sh config-template build-dir more-configs
+#
+# 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>
+
+config_template=${1}
+if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template"
+then
+	echo "kvm-build.sh :$config_template: Not a readable file"
+	exit 1
+fi
+builddir=${2}
+if test -z "$builddir" -o ! -d "$builddir" -o ! -w "$builddir"
+then
+	echo "kvm-build.sh :$builddir: Not a writable directory, cannot build into it"
+	exit 1
+fi
+moreconfigs=${3}
+if test -z "$moreconfigs" -o ! -r "$moreconfigs"
+then
+	echo "kvm-build.sh :$moreconfigs: Not a readable file"
+	exit 1
+fi
+
+T=/tmp/test-linux.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+cat ${config_template} | grep -v CONFIG_RCU_TORTURE_TEST > $T/config
+cat << ___EOF___ >> $T/config
+CONFIG_INITRAMFS_SOURCE="$RCU_INITRD"
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_CONSOLE=y
+___EOF___
+cat $moreconfigs >> $T/config
+
+configinit.sh $T/config O=$builddir
+retval=$?
+if test $retval -gt 1
+then
+	exit 2
+fi
+ncpus=`cpus2use.sh`
+make O=$builddir -j$ncpus $RCU_KMAKE_ARG > $builddir/Make.out 2>&1
+retval=$?
+if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+then
+	echo Kernel build error
+	egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+	echo Run aborted.
+	exit 3
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
new file mode 100755
index 000000000000..baef09f3469b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+#
+# Given the results directories for previous KVM runs of rcutorture,
+# check the build and console output for errors.  Given a directory
+# containing results directories, this recursively checks them all.
+#
+# Usage: sh 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>
+
+PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
+for rd in "$@"
+do
+	dirs=`find $rd -name Make.defconfig.out -print | sort | sed -e 's,/[^/]*$,,' | sort -u`
+	for i in $dirs
+	do
+		configfile=`echo $i | sed -e 's/^.*\///'`
+		echo $configfile
+		configcheck.sh $i/.config $i/ConfigFragment
+		parse-build.sh $i/Make.out $configfile
+		parse-rcutorture.sh $i/console.log $configfile
+		parse-console.sh $i/console.log $configfile
+		if test -r $i/Warnings
+		then
+			cat $i/Warnings
+		fi
+	done
+done
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
new file mode 100755
index 000000000000..151b23788935
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -0,0 +1,192 @@
+#!/bin/bash
+#
+# Run a kvm-based test of the specified tree on the specified configs.
+# Fully automated run and error checking, no graphics console.
+#
+# Execute this in the source tree.  Do not run it as a background task
+# because qemu does not seem to like that much.
+#
+# Usage: sh kvm-test-1-rcu.sh config builddir resdir minutes qemu-args bootargs
+#
+# qemu-args defaults to "" -- you will want "-nographic" if running headless.
+# bootargs defaults to	"root=/dev/sda noapic selinux=0 console=ttyS0"
+#			"initcall_debug debug rcutorture.stat_interval=15"
+#			"rcutorture.shutdown_secs=$((minutes * 60))"
+#			"rcutorture.rcutorture_runnable=1"
+#
+# Anything you specify for either qemu-args or bootargs is appended to
+# the default values.  The "-smp" value is deduced from the contents of
+# the config fragment.
+#
+# 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>
+
+grace=120
+
+T=/tmp/kvm-test-1-rcu.sh.$$
+trap 'rm -rf $T' 0
+
+. $KVM/bin/functions.sh
+. $KVPATH/ver_functions.sh
+
+config_template=${1}
+title=`echo $config_template | sed -e 's/^.*\///'`
+builddir=${2}
+if test -z "$builddir" -o ! -d "$builddir" -o ! -w "$builddir"
+then
+	echo "kvm-test-1-rcu.sh :$builddir: Not a writable directory, cannot build into it"
+	exit 1
+fi
+resdir=${3}
+if test -z "$resdir" -o ! -d "$resdir" -o ! -w "$resdir"
+then
+	echo "kvm-test-1-rcu.sh :$resdir: Not a writable directory, cannot build into it"
+	exit 1
+fi
+cp $config_template $resdir/ConfigFragment
+echo ' ---' `date`: Starting build
+echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
+cat << '___EOF___' >> $T
+CONFIG_RCU_TORTURE_TEST=y
+___EOF___
+# Optimizations below this point
+# CONFIG_USB=n
+# CONFIG_SECURITY=n
+# CONFIG_NFS_FS=n
+# CONFIG_SOUND=n
+# CONFIG_INPUT_JOYSTICK=n
+# CONFIG_INPUT_TABLET=n
+# CONFIG_INPUT_TOUCHSCREEN=n
+# CONFIG_INPUT_MISC=n
+# CONFIG_INPUT_MOUSE=n
+# # CONFIG_NET=n # disables console access, so accept the slower build.
+# CONFIG_SCSI=n
+# CONFIG_ATA=n
+# CONFIG_FAT_FS=n
+# CONFIG_MSDOS_FS=n
+# CONFIG_VFAT_FS=n
+# CONFIG_ISO9660_FS=n
+# CONFIG_QUOTA=n
+# CONFIG_HID=n
+# CONFIG_CRYPTO=n
+# CONFIG_PCCARD=n
+# CONFIG_PCMCIA=n
+# CONFIG_CARDBUS=n
+# CONFIG_YENTA=n
+if kvm-build.sh $config_template $builddir $T
+then
+	cp $builddir/Make*.out $resdir
+	cp $builddir/.config $resdir
+	cp $builddir/arch/x86/boot/bzImage $resdir
+	parse-build.sh $resdir/Make.out $title
+else
+	cp $builddir/Make*.out $resdir
+	echo Build failed, not running KVM, see $resdir.
+	exit 1
+fi
+minutes=$4
+seconds=$(($minutes * 60))
+qemu_args=$5
+boot_args=$6
+
+cd $KVM
+kstarttime=`awk 'BEGIN { print systime() }' < /dev/null`
+echo ' ---' `date`: Starting kernel
+
+# Determine the appropriate flavor of qemu command.
+QEMU="`identify_qemu $builddir/vmlinux.o`"
+
+# Generate -smp qemu argument.
+cpu_count=`configNR_CPUS.sh $config_template`
+vcpus=`identify_qemu_vcpus`
+if test $cpu_count -gt $vcpus
+then
+	echo CPU count limited from $cpu_count to $vcpus
+	touch $resdir/Warnings
+	echo CPU count limited from $cpu_count to $vcpus >> $resdir/Warnings
+	cpu_count=$vcpus
+fi
+qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`"
+
+# Generate architecture-specific and interaction-specific qemu arguments
+qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$builddir/console.log"`"
+
+# Generate qemu -append arguments
+qemu_append="`identify_qemu_append "$QEMU"`"
+
+# Pull in Kconfig-fragment boot parameters
+boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
+# Generate CPU-hotplug boot parameters
+boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`"
+# Generate rcu_barrier() boot parameter
+boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
+# Pull in standard rcutorture boot arguments
+boot_args="$boot_args rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1"
+
+echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+if test -n "$RCU_BUILDONLY"
+then
+	echo Build-only run specified, boot/test omitted.
+	exit 0
+fi
+$QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append $boot_args" &
+qemu_pid=$!
+commandcompleted=0
+echo Monitoring qemu job at pid $qemu_pid
+for ((i=0;i<$seconds;i++))
+do
+	if kill -0 $qemu_pid > /dev/null 2>&1
+	then
+		sleep 1
+	else
+		commandcompleted=1
+		kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
+		if test $kruntime -lt $seconds
+		then
+			echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1
+		else
+			echo ' ---' `date`: Kernel done
+		fi
+		break
+	fi
+done
+if test $commandcompleted -eq 0
+then
+	echo Grace period for qemu job at pid $qemu_pid
+	for ((i=0;i<=$grace;i++))
+	do
+		if kill -0 $qemu_pid > /dev/null 2>&1
+		then
+			sleep 1
+		else
+			break
+		fi
+		if test $i -eq $grace
+		then
+			kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }'`
+			echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
+			kill -KILL $qemu_pid
+		fi
+	done
+fi
+
+cp $builddir/console.log $resdir
+parse-rcutorture.sh $resdir/console.log $title
+parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
new file mode 100644
index 000000000000..1b7923bf6a70
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -0,0 +1,210 @@
+#!/bin/bash
+#
+# Run a series of 14 tests under KVM.  These are not particularly
+# well-selected or well-tuned, but are the current set.  Run from the
+# top level of the source tree.
+#
+# Edit the definitions below to set the locations of the various directories,
+# as well as the test duration.
+#
+# Usage: sh 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>
+
+scriptname=$0
+args="$*"
+
+dur=30
+KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
+PATH=${KVM}/bin:$PATH; export PATH
+builddir="${KVM}/b1"
+RCU_INITRD="$KVM/initrd"; export RCU_INITRD
+RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG
+resdir=""
+configs=""
+ds=`date +%Y.%m.%d-%H:%M:%S`
+kversion=""
+
+. functions.sh
+
+usage () {
+	echo "Usage: $scriptname optional arguments:"
+	echo "       --bootargs kernel-boot-arguments"
+	echo "       --builddir absolute-pathname"
+	echo "       --buildonly"
+	echo "       --configs \"config-file list\""
+	echo "       --datestamp string"
+	echo "       --duration minutes"
+	echo "       --interactive"
+	echo "       --kmake-arg kernel-make-arguments"
+	echo "       --kversion vN.NN"
+	echo "       --mac nn:nn:nn:nn:nn:nn"
+	echo "       --no-initrd"
+	echo "       --qemu-args qemu-system-..."
+	echo "       --qemu-cmd qemu-system-..."
+	echo "       --results absolute-pathname"
+	echo "       --relbuilddir relative-pathname"
+	exit 1
+}
+
+while test $# -gt 0
+do
+	case "$1" in
+	--bootargs)
+		checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--'
+		RCU_BOOTARGS="$2"
+		shift
+		;;
+	--builddir)
+		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' '^error'
+		builddir=$2
+		gotbuilddir=1
+		shift
+		;;
+	--buildonly)
+		RCU_BUILDONLY=1; export RCU_BUILDONLY
+		;;
+	--configs)
+		checkarg --configs "(list of config files)" "$#" "$2" '^[^/]*$' '^--'
+		configs="$2"
+		shift
+		;;
+	--datestamp)
+		checkarg --datestamp "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
+		ds=$2
+		shift
+		;;
+	--duration)
+		checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' '^error'
+		dur=$2
+		shift
+		;;
+	--interactive)
+		RCU_QEMU_INTERACTIVE=1; export RCU_QEMU_INTERACTIVE
+		;;
+	--kmake-arg)
+		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
+		RCU_KMAKE_ARG="$2"; export RCU_KMAKE_ARG
+		shift
+		;;
+	--kversion)
+		checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' '^error'
+		kversion=$2
+		shift
+		;;
+	--mac)
+		checkarg --mac "(MAC address)" $# "$2" '^\([0-9a-fA-F]\{2\}:\)\{5\}[0-9a-fA-F]\{2\}$' error
+		RCU_QEMU_MAC=$2; export RCU_QEMU_MAC
+		shift
+		;;
+	--no-initrd)
+		RCU_INITRD=""; export RCU_INITRD
+		;;
+	--qemu-args)
+		checkarg --qemu-args "-qemu args" $# "$2" '^-' '^error'
+		RCU_QEMU_ARG="$2"
+		shift
+		;;
+	--qemu-cmd)
+		checkarg --qemu-cmd "(qemu-system-...)" $# "$2" 'qemu-system-' '^--'
+		RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD
+		shift
+		;;
+	--relbuilddir)
+		checkarg --relbuilddir "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
+		relbuilddir=$2
+		gotrelbuilddir=1
+		builddir=${KVM}/${relbuilddir}
+		shift
+		;;
+	--results)
+		checkarg --results "(absolute pathname)" "$#" "$2" '^/' '^error'
+		resdir=$2
+		shift
+		;;
+	*)
+		echo Unknown argument $1
+		usage
+		;;
+	esac
+	shift
+done
+
+CONFIGFRAG=${KVM}/configs; export CONFIGFRAG
+KVPATH=${CONFIGFRAG}/$kversion; export KVPATH
+
+if test -z "$configs"
+then
+	configs="`cat $CONFIGFRAG/$kversion/CFLIST`"
+fi
+
+if test -z "$resdir"
+then
+	resdir=$KVM/res
+	if ! test -e $resdir
+	then
+		mkdir $resdir || :
+	fi
+else
+	if ! test -e $resdir
+	then
+		mkdir -p "$resdir" || :
+	fi
+fi
+mkdir $resdir/$ds
+touch $resdir/$ds/log
+echo $scriptname $args >> $resdir/$ds/log
+
+pwd > $resdir/$ds/testid.txt
+if test -d .git
+then
+	git status >> $resdir/$ds/testid.txt
+	git rev-parse HEAD >> $resdir/$ds/testid.txt
+fi
+builddir=$KVM/b1
+if ! test -e $builddir
+then
+	mkdir $builddir || :
+fi
+
+for CF in $configs
+do
+	# Running TREE01 multiple times creates TREE01, TREE01.2, TREE01.3, ...
+	rd=$resdir/$ds/$CF
+	if test -d "${rd}"
+	then
+		n="`ls -d "${rd}"* | grep '\.[0-9]\+$' |
+			sed -e 's/^.*\.\([0-9]\+\)/\1/' |
+			sort -k1n | tail -1`"
+		if test -z "$n"
+		then
+			rd="${rd}.2"
+		else
+			n="`expr $n + 1`"
+			rd="${rd}.${n}"
+		fi
+	fi
+	mkdir "${rd}"
+	echo Results directory: $rd
+	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
+done
+# Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier
+
+echo " --- `date` Test summary:"
+kvm-recheck.sh $resdir/$ds
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
new file mode 100755
index 000000000000..543230951c38
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -0,0 +1,57 @@
+#!/bin/sh
+#
+# Check the build output from an rcutorture run for goodness.
+# The "file" is a pathname on the local system, and "title" is
+# a text string for error-message purposes.
+#
+# The file must contain kernel build output.
+#
+# Usage:
+#	sh 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>
+
+T=$1
+title=$2
+
+. functions.sh
+
+if grep -q CC < $T
+then
+	:
+else
+	print_bug $title no build
+	exit 1
+fi
+
+if grep -q "error:" < $T
+then
+	print_bug $title build errors:
+	grep "error:" < $T
+	exit 2
+fi
+exit 0
+
+if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+then
+	print_warning $title build errors:
+	egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+	exit 2
+fi
+exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
new file mode 100755
index 000000000000..4185d4cab32e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -0,0 +1,41 @@
+#!/bin/sh
+#
+# Check the console output from an rcutorture run for oopses.
+# The "file" is a pathname on the local system, and "title" is
+# a text string for error-message purposes.
+#
+# Usage:
+#	sh 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>
+
+T=/tmp/abat-chk-badness.sh.$$
+trap 'rm -f $T' 0
+
+file="$1"
+title="$2"
+
+. functions.sh
+
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
+if test -s $T
+then
+	print_warning Assertion failure in $file $title
+	cat $T
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
new file mode 100755
index 000000000000..dd0a275d9796
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
@@ -0,0 +1,106 @@
+#!/bin/sh
+#
+# Check the console output from an rcutorture run for goodness.
+# The "file" is a pathname on the local system, and "title" is
+# a text string for error-message purposes.
+#
+# The file must contain rcutorture output, but can be interspersed
+# with other dmesg text.
+#
+# Usage:
+#	sh parse-rcutorture.sh file title
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+T=/tmp/parse-rcutorture.sh.$$
+file="$1"
+title="$2"
+
+trap 'rm -f $T.seq' 0
+
+. functions.sh
+
+# check for presence of rcutorture.txt file
+
+if test -f "$file" -a -r "$file"
+then
+	:
+else
+	echo $title unreadable rcutorture.txt file: $file
+	exit 1
+fi
+
+# check for abject failure
+
+if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
+then
+	nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+	print_bug $title FAILURE, $nerrs instances
+	echo "   " $url
+	exit
+fi
+
+grep --binary-files=text 'torture:.*ver:' $file | grep --binary-files=text -v '(null)' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
+awk '
+BEGIN	{
+	ver = 0;
+	badseq = 0;
+	}
+
+	{
+	if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
+		badseqno1 = ver;
+		badseqno2 = $5;
+		badseqnr = NR;
+		badseq = 1;
+	}
+	ver = $5
+	}
+
+END	{
+	if (badseq) {
+		if (badseqno1 == badseqno2 && badseqno2 == ver)
+			print "RCU GP HANG at " ver " rcutorture stat " badseqnr;
+		else
+			print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " RCU version " badseqnr;
+	}
+	}' > $T.seq
+
+if grep -q SUCCESS $file
+then
+	if test -s $T.seq
+	then
+		print_warning $title $title `cat $T.seq`
+		echo "   " $file
+		exit 2
+	fi
+else
+	if grep -q RCU_HOTPLUG $file
+	then
+		print_warning HOTPLUG FAILURES $title `cat $T.seq`
+		echo "   " $file
+		exit 3
+	fi
+	echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful RCU version messages
+	if test -s $T.seq
+	then
+		print_warning $title `cat $T.seq`
+	fi
+	exit 2
+fi
diff --git a/tools/testing/selftests/rcutorture/configs/CFLIST b/tools/testing/selftests/rcutorture/configs/CFLIST
new file mode 100644
index 000000000000..cd3d29cb0a47
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/CFLIST
@@ -0,0 +1,13 @@
+TREE01
+TREE02
+TREE03
+TREE04
+TREE05
+TREE06
+TREE07
+TREE08
+TREE09
+SRCU-N
+SRCU-P
+TINY01
+TINY02
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N b/tools/testing/selftests/rcutorture/configs/SRCU-N
new file mode 100644
index 000000000000..10a0e27f4c75
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-N
@@ -0,0 +1,8 @@
+CONFIG_RCU_TRACE=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/SRCU-N.boot
new file mode 100644
index 000000000000..238bfe3bd0cc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-N.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=srcu
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/SRCU-P
new file mode 100644
index 000000000000..6650e00c6d91
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-P
@@ -0,0 +1,8 @@
+CONFIG_RCU_TRACE=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/SRCU-P.boot
new file mode 100644
index 000000000000..238bfe3bd0cc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-P.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=srcu
diff --git a/tools/testing/selftests/rcutorture/configs/TINY01 b/tools/testing/selftests/rcutorture/configs/TINY01
new file mode 100644
index 000000000000..0c2823f21712
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TINY01
@@ -0,0 +1,13 @@
+CONFIG_SMP=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PREEMPT_COUNT=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TINY02 b/tools/testing/selftests/rcutorture/configs/TINY02
new file mode 100644
index 000000000000..e5072d7528b6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TINY02
@@ -0,0 +1,13 @@
+CONFIG_SMP=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_HZ_PERIODIC=y
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PREEMPT_COUNT=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE01 b/tools/testing/selftests/rcutorture/configs/TREE01
new file mode 100644
index 000000000000..141119a00044
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE01
@@ -0,0 +1,23 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_ZERO=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE01.boot b/tools/testing/selftests/rcutorture/configs/TREE01.boot
new file mode 100644
index 000000000000..0fc8a3428938
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/TREE02 b/tools/testing/selftests/rcutorture/configs/TREE02
new file mode 100644
index 000000000000..2d4d09608528
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE02
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n 
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_LEAF=3
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=y
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE03 b/tools/testing/selftests/rcutorture/configs/TREE03
new file mode 100644
index 000000000000..a47de5be8a04
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE03
@@ -0,0 +1,23 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=y
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=4
+CONFIG_RCU_FANOUT_LEAF=4
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE04 b/tools/testing/selftests/rcutorture/configs/TREE04
new file mode 100644
index 000000000000..8d839b86a1d5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE04
@@ -0,0 +1,25 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_ALL=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_VERBOSE=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE04.boot b/tools/testing/selftests/rcutorture/configs/TREE04.boot
new file mode 100644
index 000000000000..0fc8a3428938
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE04.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/TREE05 b/tools/testing/selftests/rcutorture/configs/TREE05
new file mode 100644
index 000000000000..b5ba72ea25cb
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE05
@@ -0,0 +1,25 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=6
+CONFIG_RCU_FANOUT_LEAF=6
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE05.boot b/tools/testing/selftests/rcutorture/configs/TREE05.boot
new file mode 100644
index 000000000000..3b42b8b033cd
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE05.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=sched
diff --git a/tools/testing/selftests/rcutorture/configs/TREE06 b/tools/testing/selftests/rcutorture/configs/TREE06
new file mode 100644
index 000000000000..7c95ab48d29f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE06
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=6
+CONFIG_RCU_FANOUT_LEAF=6
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE07 b/tools/testing/selftests/rcutorture/configs/TREE07
new file mode 100644
index 000000000000..1467404bdec1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE07
@@ -0,0 +1,24 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=16
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_ALL=y
+CONFIG_NO_HZ_FULL_SYSIDLE=y
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE08 b/tools/testing/selftests/rcutorture/configs/TREE08
new file mode 100644
index 000000000000..7d097a61ac2a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE08
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=16
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE08-T b/tools/testing/selftests/rcutorture/configs/TREE08-T
new file mode 100644
index 000000000000..442c4e450ab3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE08-T
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=16
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE09 b/tools/testing/selftests/rcutorture/configs/TREE09
new file mode 100644
index 000000000000..0d1ec0d3dfee
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE09
@@ -0,0 +1,21 @@
+CONFIG_SMP=n
+CONFIG_NR_CPUS=1
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST b/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST
new file mode 100644
index 000000000000..18223947bbcb
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST
@@ -0,0 +1,14 @@
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..d3ef873eb6e7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..02e418572b1b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b3100f69c8cf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..c56b44530725
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..90d924fea9e9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh b/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh
new file mode 100644
index 000000000000..023f312a931c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH b/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH
new file mode 100644
index 000000000000..6fd0235dae73
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..f72402d7c13d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..0f3b667d2a9f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b035e141bf2a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..3ccf6a9447f5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..ef624ce73d8e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh b/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh
new file mode 100644
index 000000000000..e3361c3894a1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH b/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH
new file mode 100644
index 000000000000..64abfc3b4d94
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
new file mode 100644
index 000000000000..e8052539af54
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+#
+# 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>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	echo $1
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	echo $1
+}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST b/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST
new file mode 100644
index 000000000000..da4cbc668f2a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST
@@ -0,0 +1,17 @@
+sysidleY.2013.06.19a
+sysidleN.2013.06.19a
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+P6---t-nh-SD-smp-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..d81e11d280aa
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..02e418572b1b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b3100f69c8cf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..c56b44530725
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..90d924fea9e9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp
new file mode 100644
index 000000000000..0ccc36d72738
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=1
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..3f640cf84973
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP
@@ -0,0 +1,26 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..285da2dd8ac3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=14
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh b/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh
new file mode 100644
index 000000000000..023f312a931c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH b/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH
new file mode 100644
index 000000000000..6fd0235dae73
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..9647c44cf4b7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..0f3b667d2a9f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b035e141bf2a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..3ccf6a9447f5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..ef624ce73d8e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp
new file mode 100644
index 000000000000..f4c9175828bf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=n
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..77a8c5b75763
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=n
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all
new file mode 100644
index 000000000000..0eecebc6e95f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none
new file mode 100644
index 000000000000..0eecebc6e95f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp
new file mode 100644
index 000000000000..588bc70420cd
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=n
+CONFIG_RCU_NOCB_CPU_ZERO=y
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh b/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh
new file mode 100644
index 000000000000..e3361c3894a1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH b/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH
new file mode 100644
index 000000000000..64abfc3b4d94
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST b/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST
new file mode 100644
index 000000000000..18223947bbcb
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST
@@ -0,0 +1,14 @@
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..d81e11d280aa
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..02e418572b1b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b3100f69c8cf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..c56b44530725
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..90d924fea9e9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh b/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh
new file mode 100644
index 000000000000..023f312a931c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH b/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH
new file mode 100644
index 000000000000..6fd0235dae73
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..9647c44cf4b7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..0f3b667d2a9f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b035e141bf2a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..3ccf6a9447f5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..ef624ce73d8e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh b/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh
new file mode 100644
index 000000000000..e3361c3894a1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH b/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH
new file mode 100644
index 000000000000..64abfc3b4d94
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
new file mode 100644
index 000000000000..c37432f3572c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+#
+# 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>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	echo $1
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding rcutorture onoff.
+		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+	else
+		echo $1
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST b/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST
new file mode 100644
index 000000000000..18223947bbcb
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST
@@ -0,0 +1,14 @@
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..d81e11d280aa
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..02e418572b1b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b3100f69c8cf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..c56b44530725
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..90d924fea9e9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh b/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh
new file mode 100644
index 000000000000..023f312a931c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH b/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH
new file mode 100644
index 000000000000..6fd0235dae73
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 000000000000..9647c44cf4b7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 000000000000..0f3b667d2a9f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 000000000000..b035e141bf2a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 000000000000..3ccf6a9447f5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 000000000000..ef624ce73d8e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh b/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh
new file mode 100644
index 000000000000..e3361c3894a1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH b/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH
new file mode 100644
index 000000000000..64abfc3b4d94
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
new file mode 100644
index 000000000000..6a5f13aab44d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+#
+# 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>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
+	then
+		echo $1
+	else
+		echo $1 rcutorture.n_barrier_cbs=4
+	fi
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding rcutorture onoff.
+		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+	else
+		echo $1
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/ver_functions.sh
new file mode 100644
index 000000000000..5e40eadea777
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/ver_functions.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+#
+# 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>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
+	then
+		echo $1
+	else
+		echo $1 rcutorture.n_barrier_cbs=4
+	fi
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
+		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+	else
+		echo $1
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
new file mode 100644
index 000000000000..28db67b54e55
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
@@ -0,0 +1,40 @@
+This document gives a brief rationale for the TINY_RCU test cases.
+
+
+Kconfig Parameters:
+
+CONFIG_DEBUG_LOCK_ALLOC -- Do all three and none of the three.
+CONFIG_PREEMPT_COUNT
+CONFIG_RCU_TRACE
+
+The theory here is that randconfig testing will hit the other six possible
+combinations of these parameters.
+
+
+Kconfig Parameters Ignored:
+
+CONFIG_DEBUG_OBJECTS_RCU_HEAD
+CONFIG_PROVE_RCU
+
+	In common code tested by TREE_RCU test cases.
+
+CONFIG_NO_HZ_FULL_SYSIDLE
+CONFIG_RCU_NOCB_CPU
+CONFIG_RCU_USER_QS
+
+	Meaningless for TINY_RCU.
+
+CONFIG_RCU_STALL_COMMON
+CONFIG_RCU_TORTURE_TEST
+
+	Redundant with CONFIG_RCU_TRACE.
+
+CONFIG_HOTPLUG_CPU
+CONFIG_PREEMPT
+CONFIG_PREEMPT_RCU
+CONFIG_SMP
+CONFIG_TINY_RCU
+CONFIG_TREE_PREEMPT_RCU
+CONFIG_TREE_RCU
+
+	All forced by CONFIG_TINY_RCU.
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt
new file mode 100644
index 000000000000..adbb76cffb49
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt
@@ -0,0 +1,95 @@
+This document gives a brief rationale for the TREE_RCU-related test
+cases, a group that includes TREE_PREEMPT_RCU.
+
+
+Kconfig Parameters:
+
+CONFIG_DEBUG_LOCK_ALLOC -- Do three, covering CONFIG_PROVE_LOCKING & not.
+CONFIG_DEBUG_OBJECTS_RCU_HEAD -- Do one.
+CONFIG_HOTPLUG_CPU -- Do half.  (Every second.)
+CONFIG_HZ_PERIODIC -- Do one.
+CONFIG_NO_HZ_IDLE -- Do those not otherwise specified. (Groups of two.)
+CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE.
+CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
+CONFIG_PREEMPT -- Do half.  (First three and #8.)
+CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
+CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_RCU_DELAY -- Do one.
+CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU.
+CONFIG_RCU_BOOST_PRIO -- set to 2 for _BOOST testing.
+CONFIG_RCU_CPU_STALL_INFO -- do one with and without _VERBOSE.
+CONFIG_RCU_CPU_STALL_VERBOSE -- do one with and without _INFO.
+CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others.
+CONFIG_RCU_FANOUT_EXACT -- Do one.
+CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
+CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL.
+CONFIG_RCU_NOCB_CPU -- Do three, see below.
+CONFIG_RCU_NOCB_CPU_ALL -- Do one.
+CONFIG_RCU_NOCB_CPU_NONE -- Do one.
+CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
+CONFIG_RCU_TRACE -- Do half.
+CONFIG_SMP -- Need one !SMP for TREE_PREEMPT_RCU.
+RCU-bh: Do one with PREEMPT and one with !PREEMPT.
+RCU-sched: Do one with PREEMPT but not BOOST.
+
+
+Hierarchy:
+
+TREE01.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=8, CONFIG_RCU_FANOUT_EXACT=n.
+TREE02.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=3.
+TREE03.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=4, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=4.
+TREE04.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=2.
+TREE05.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=n
+	CONFIG_RCU_FANOUT_LEAF=6.
+TREE06.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=y
+	CONFIG_RCU_FANOUT_LEAF=6.
+TREE07.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=2.
+TREE08.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=y,
+	CONFIG_RCU_FANOUT_LEAF=2.
+TREE09.	CONFIG_NR_CPUS=1.
+
+
+Kconfig Parameters Ignored:
+
+CONFIG_64BIT
+
+	Used only to check CONFIG_RCU_FANOUT value, inspection suffices.
+
+CONFIG_NO_HZ_FULL_SYSIDLE_SMALL
+
+	Defer until Frederic uses this.
+
+CONFIG_PREEMPT_COUNT
+CONFIG_PREEMPT_RCU
+
+	Redundant with CONFIG_PREEMPT, ignore.
+
+CONFIG_RCU_BOOST_DELAY
+
+	Inspection suffices, ignore.
+
+CONFIG_RCU_CPU_STALL_TIMEOUT
+
+	Inspection suffices, ignore.
+
+CONFIG_RCU_STALL_COMMON
+
+	Implied by TREE_RCU and TREE_PREEMPT_RCU.
+
+CONFIG_RCU_TORTURE_TEST
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+	Always used in KVM testing.
+
+CONFIG_RCU_USER_QS
+
+	Redundant with CONFIG_NO_HZ_FULL.
+
+CONFIG_TREE_PREEMPT_RCU
+CONFIG_TREE_RCU
+
+	These are controlled by CONFIG_PREEMPT.
diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt
new file mode 100644
index 000000000000..49d134c25c04
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/initrd.txt
@@ -0,0 +1,90 @@
+This document describes one way to create the initrd directory hierarchy
+in order to allow an initrd to be built into your kernel.  The trick
+here is to steal the initrd file used on your Linux laptop, Ubuntu in
+this case.  There are probably much better ways of doing this.
+
+That said, here are the commands:
+
+------------------------------------------------------------------------
+zcat /initrd.img > /tmp/initrd.img.zcat
+mkdir initrd
+cd initrd
+cpio -id < /tmp/initrd.img.zcat
+------------------------------------------------------------------------
+
+Interestingly enough, if you are running rcutorture, you don't really
+need userspace in many cases.  Running without userspace has the
+advantage of allowing you to test your kernel independently of the
+distro in place, the root-filesystem layout, and so on.  To make this
+happen, put the following script in the initrd's tree's "/init" file,
+with 0755 mode.
+
+------------------------------------------------------------------------
+#!/bin/sh
+
+[ -d /dev ] || mkdir -m 0755 /dev
+[ -d /root ] || mkdir -m 0700 /root
+[ -d /sys ] || mkdir /sys
+[ -d /proc ] || mkdir /proc
+[ -d /tmp ] || mkdir /tmp
+mkdir -p /var/lock
+mount -t sysfs -o nodev,noexec,nosuid sysfs /sys
+mount -t proc -o nodev,noexec,nosuid proc /proc
+# Some things don't work properly without /etc/mtab.
+ln -sf /proc/mounts /etc/mtab
+
+# Note that this only becomes /dev on the real filesystem if udev's scripts
+# are used; which they will be, but it's worth pointing out
+if ! mount -t devtmpfs -o mode=0755 udev /dev; then
+	echo "W: devtmpfs not available, falling back to tmpfs for /dev"
+	mount -t tmpfs -o mode=0755 udev /dev
+	[ -e /dev/console ] || mknod --mode=600 /dev/console c 5 1
+	[ -e /dev/kmsg ] || mknod --mode=644 /dev/kmsg c 1 11
+	[ -e /dev/null ] || mknod --mode=666 /dev/null c 1 3
+fi
+
+mkdir /dev/pts
+mount -t devpts -o noexec,nosuid,gid=5,mode=0620 devpts /dev/pts || true
+mount -t tmpfs -o "nosuid,size=20%,mode=0755" tmpfs /run
+mkdir /run/initramfs
+# compatibility symlink for the pre-oneiric locations
+ln -s /run/initramfs /dev/.initramfs
+
+# Export relevant variables
+export ROOT=
+export ROOTDELAY=
+export ROOTFLAGS=
+export ROOTFSTYPE=
+export IP=
+export BOOT=
+export BOOTIF=
+export UBIMTD=
+export break=
+export init=/sbin/init
+export quiet=n
+export readonly=y
+export rootmnt=/root
+export debug=
+export panic=
+export blacklist=
+export resume=
+export resume_offset=
+export recovery=
+
+for i in /sys/devices/system/cpu/cpu*/online
+do
+	case $i in
+	'/sys/devices/system/cpu/cpu0/online')
+		;;
+	'/sys/devices/system/cpu/cpu*/online')
+		;;
+	*)
+		echo 1 > $i
+		;;
+	esac
+done
+
+while :
+do
+	sleep 10
+done
diff --git a/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt b/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
new file mode 100644
index 000000000000..66efb59a1bd1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
@@ -0,0 +1,42 @@
+This document describes one way to created the rcu-test-image file
+that contains the filesystem used by the guest-OS kernel.  There are
+probably much better ways of doing this, and this filesystem could no
+doubt be smaller.  It is probably also possible to simply download
+an appropriate image from any number of places.
+
+That said, here are the commands:
+
+------------------------------------------------------------------------
+dd if=/dev/zero of=rcu-test-image bs=400M count=1
+mkfs.ext3 ./rcu-test-image
+sudo mount -o loop ./rcu-test-image /mnt
+
+# Replace "precise" below with your favorite Ubuntu release.
+# Empirical evidence says this image will work for 64-bit, but...
+# Note that debootstrap does take a few minutes to run.  Or longer.
+sudo debootstrap --verbose --arch i386 precise /mnt http://archive.ubuntu.com/ubuntu
+cat << '___EOF___' | sudo dd of=/mnt/etc/fstab
+# UNCONFIGURED FSTAB FOR BASE SYSTEM
+#
+/dev/vda        /               ext3    defaults        1 1
+dev             /dev            tmpfs   rw              0 0
+tmpfs           /dev/shm        tmpfs   defaults        0 0
+devpts          /dev/pts        devpts  gid=5,mode=620  0 0
+sysfs           /sys            sysfs   defaults        0 0
+proc            /proc           proc    defaults        0 0
+___EOF___
+sudo umount /mnt
+------------------------------------------------------------------------
+
+
+References:
+
+	http://sripathikodi.blogspot.com/2010/02/creating-kvm-bootable-fedora-system.html
+	https://help.ubuntu.com/community/KVM/CreateGuests
+	https://help.ubuntu.com/community/JeOSVMBuilder
+	http://wiki.libvirt.org/page/UbuntuKVMWalkthrough
+	http://www.moe.co.uk/2011/01/07/pci_add_option_rom-failed-to-find-romfile-pxe-rtl8139-bin/ -- "apt-get install kvm-pxe"
+	http://www.landley.net/writing/rootfs-howto.html
+	http://en.wikipedia.org/wiki/Initrd
+	http://en.wikipedia.org/wiki/Cpio
+	http://wiki.libvirt.org/page/UbuntuKVMWalkthrough
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 24e9ddd93fa4..3d907dacf2ac 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -2,21 +2,21 @@
 #
 TARGETS=page-types slabinfo
 
-LK_DIR = ../lib/lk
-LIBLK = $(LK_DIR)/liblk.a
+LIB_DIR = ../lib/api
+LIBS = $(LIB_DIR)/libapikfs.a
 
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/
-LDFLAGS = $(LIBLK)
+LDFLAGS = $(LIBS)
 
-$(TARGETS): liblk
+$(TARGETS): $(LIBS)
 
-liblk:
-	make -C $(LK_DIR)
+$(LIBS):
+	make -C $(LIB_DIR)
 
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
 	$(RM) page-types slabinfo
-	make -C ../lib/lk clean
+	make -C $(LIB_DIR) clean
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index d5e9d6d185c8..f9be24d9efac 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -36,7 +36,7 @@
 #include <sys/statfs.h>
 #include "../../include/uapi/linux/magic.h"
 #include "../../include/uapi/linux/kernel-page-flags.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 
 #ifndef MAX_PATH
 # define MAX_PATH 256