Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

41 files changed, 1656 insertions, 756 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 4f55c736be11..5b448a74d0f7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -47,18 +47,29 @@ config KPROBES
 	  If in doubt, say "N".
 
 config JUMP_LABEL
-       bool "Optimize trace point call sites"
+       bool "Optimize very unlikely/likely branches"
        depends on HAVE_ARCH_JUMP_LABEL
        help
+         This option enables a transparent branch optimization that
+	 makes certain almost-always-true or almost-always-false branch
+	 conditions even cheaper to execute within the kernel.
+
+	 Certain performance-sensitive kernel code, such as trace points,
+	 scheduler functionality, networking code and KVM have such
+	 branches and include support for this optimization technique.
+
          If it is detected that the compiler has support for "asm goto",
-	 the kernel will compile trace point locations with just a
-	 nop instruction. When trace points are enabled, the nop will
-	 be converted to a jump to the trace function. This technique
-	 lowers overhead and stress on the branch prediction of the
-	 processor.
-
-	 On i386, options added to the compiler flags may increase
-	 the size of the kernel slightly.
+	 the kernel will compile such branches with just a nop
+	 instruction. When the condition flag is toggled to true, the
+	 nop will be converted to a jump instruction to execute the
+	 conditional block of instructions.
+
+	 This technique lowers overhead and stress on the branch prediction
+	 of the processor and generally makes the kernel faster. The update
+	 of the condition is slower, but those are always very rare.
+
+	 ( On 32-bit x86, the necessary options added to the compiler
+	   flags may increase the size of the kernel slightly. )
 
 config OPTPROBES
 	def_bool y
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 8143cd7cdbfb..0dae252f7a33 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -685,6 +685,10 @@ static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 99cfe3607989..7523340afb8a 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,10 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/* ARM performance counters start from 1 (in the cp15 accesses) so use the
- * same indexes here for consistency. */
-#define PERF_EVENT_INDEX_OFFSET 1
-
 /* ARM perf PMU IDs for use by internal perf clients. */
 enum arm_perf_pmu_ids {
 	ARM_PERF_PMU_ID_XSCALE1	= 0,
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index b2abfa18f137..8a89d3b7626b 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -539,6 +539,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
 
diff --git a/arch/frv/include/asm/perf_event.h b/arch/frv/include/asm/perf_event.h
index a69e0155d146..c52ea5546b5b 100644
--- a/arch/frv/include/asm/perf_event.h
+++ b/arch/frv/include/asm/perf_event.h
@@ -12,6 +12,4 @@
 #ifndef _ASM_PERF_EVENT_H
 #define _ASM_PERF_EVENT_H
 
-#define PERF_EVENT_INDEX_OFFSET	0
-
 #endif /* _ASM_PERF_EVENT_H */
diff --git a/arch/hexagon/include/asm/perf_event.h b/arch/hexagon/include/asm/perf_event.h
index 6c2910f91180..8b8526b491c7 100644
--- a/arch/hexagon/include/asm/perf_event.h
+++ b/arch/hexagon/include/asm/perf_event.h
@@ -19,6 +19,4 @@
 #ifndef _ASM_PERF_EVENT_H
 #define _ASM_PERF_EVENT_H
 
-#define PERF_EVENT_INDEX_OFFSET	0
-
 #endif /* _ASM_PERF_EVENT_H */
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
index 32551d304cd7..b149b88ea795 100644
--- a/arch/ia64/include/asm/paravirt.h
+++ b/arch/ia64/include/asm/paravirt.h
@@ -281,9 +281,9 @@ paravirt_init_missing_ticks_accounting(int cpu)
 		pv_time_ops.init_missing_ticks_accounting(cpu);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline int
 paravirt_do_steal_accounting(unsigned long *new_itm)
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
index 100868216c55..1b22f6de2932 100644
--- a/arch/ia64/kernel/paravirt.c
+++ b/arch/ia64/kernel/paravirt.c
@@ -634,8 +634,8 @@ struct pv_irq_ops pv_irq_ops = {
  * pv_time_ops
  * time operations
  */
-struct jump_label_key paravirt_steal_enabled;
-struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
 static int
 ia64_native_do_steal_accounting(unsigned long *new_itm)
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 1881b316ca45..4d6d77ed9b9d 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -20,7 +20,7 @@
 #define WORD_INSN ".word"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\tnop\n\t"
 		"nop\n\t"
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index e3b897acfbc0..811084f4e422 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -606,6 +606,10 @@ static int mipspmu_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 938986e412f1..ae098c438f00 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 #define JUMP_ENTRY_TYPE		stringify_in_c(FTR_ENTRY_LONG)
 #define JUMP_LABEL_NOP_SIZE	4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\n\t"
 		 "nop\n\t"
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 8f1df1208d23..1a8093fa8f71 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -61,8 +61,6 @@ struct pt_regs;
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 
-#define PERF_EVENT_INDEX_OFFSET	1
-
 /*
  * Only override the default definitions in include/linux/perf_event.h
  * if we have hardware PMU support.
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 64483fde95c6..c2e27ede07ec 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1084,6 +1084,10 @@ static int power_pmu_event_init(struct perf_event *event)
 	if (!ppmu)
 		return -ENOENT;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
@@ -1193,6 +1197,11 @@ static int power_pmu_event_init(struct perf_event *event)
 	return err;
 }
 
+static int power_pmu_event_idx(struct perf_event *event)
+{
+	return event->hw.idx;
+}
+
 struct pmu power_pmu = {
 	.pmu_enable	= power_pmu_enable,
 	.pmu_disable	= power_pmu_disable,
@@ -1205,6 +1214,7 @@ struct pmu power_pmu = {
 	.start_txn	= power_pmu_start_txn,
 	.cancel_txn	= power_pmu_cancel_txn,
 	.commit_txn	= power_pmu_commit_txn,
+	.event_idx	= power_pmu_event_idx,
 };
 
 /*
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 95a6cf2b5b67..6c32190dc73e 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 #define ASM_ALIGN ".balign 4"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index a75f168d2718..4eb444edbe49 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -6,4 +6,3 @@
 
 /* Empty, just to avoid compiling error */
 
-#define PERF_EVENT_INDEX_OFFSET 0
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 10b14e3a7eb8..068b8a2759b5 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -310,6 +310,10 @@ static int sh_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HW_CACHE:
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index fc73a82366f8..5080d16a832f 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -7,7 +7,7 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 		asm goto("1:\n\t"
 			 "nop\n\t"
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 614da624330c..8e16a4a21582 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1105,6 +1105,10 @@ static int sparc_pmu_event_init(struct perf_event *event)
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (attr->type) {
 	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 205b063e3e32..74a2e312e8a2 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -97,11 +97,12 @@
 
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
 extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     insn_byte_t last_pfx,
+					     int lpfx_id,
 					     insn_attr_t esc_attr);
 extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    insn_byte_t last_pfx,
+					    int lpfx_id,
 					    insn_attr_t esc_attr);
 extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
 					  insn_byte_t vex_m,
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 74df3f1eddfd..48eb30a86062 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -96,12 +96,6 @@ struct insn {
 #define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
-/* The last prefix is needed for two-byte and three-byte opcodes */
-static inline insn_byte_t insn_last_prefix(struct insn *insn)
-{
-	return insn->prefixes.bytes[3];
-}
-
 extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
 extern void insn_get_prefixes(struct insn *insn);
 extern void insn_get_opcode(struct insn *insn);
@@ -160,6 +154,18 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
 		return X86_VEX_P(insn->vex_prefix.bytes[2]);
 }
 
+/* Get the last prefix id from last prefix or VEX prefix */
+static inline int insn_last_prefix_id(struct insn *insn)
+{
+	if (insn_is_avx(insn))
+		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
+
+	if (insn->prefixes.bytes[3])
+		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
+
+	return 0;
+}
+
 /* Offset of each field from kaddr */
 static inline int insn_offset_rex_prefix(struct insn *insn)
 {
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index a32b18ce6ead..3a16c1483b45 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -9,12 +9,12 @@
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:"
-		JUMP_LABEL_INITIAL_NOP
+		STATIC_KEY_INITIAL_NOP
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a6962d9161a0..ccb805966f68 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,13 @@
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
 
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a7d2db9a74fb..c0180fd372d2 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -230,9 +230,9 @@ static inline unsigned long long paravirt_sched_clock(void)
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 461ce432b1c2..e8fb2c7a5f4f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -188,8 +188,6 @@ extern u32 get_ibs_caps(void);
 #ifdef CONFIG_PERF_EVENTS
 extern void perf_events_lapic_init(void);
 
-#define PERF_EVENT_INDEX_OFFSET			0
-
 /*
  * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
  * This flag is otherwise unused and ABI specified to be 0, so nobody should
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5369059c07a9..532d2e090e6f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f4773f4aae35..0a44b90602b0 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 
 #include <linux/io.h>
+#include <linux/sched.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
@@ -456,6 +457,8 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+		if (!check_tsc_unstable())
+			sched_clock_stable = 1;
 	}
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5adce1040b11..0a18d16cb58d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
+#include <linux/device.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -31,6 +32,7 @@
 #include <asm/compat.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
+#include <asm/timer.h>
 
 #include "perf_event.h"
 
@@ -351,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event)
 	return 0;
 }
 
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+	u64 m = event->attr.branch_sample_type;
+	u64 b = 0;
+
+	/* must capture all branches */
+	if (!(m & PERF_SAMPLE_BRANCH_ANY))
+		return 0;
+
+	m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_user)
+		b |= PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_kernel)
+		b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+	/*
+	 * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+	 */
+
+	return m == b;
+}
+
 int x86_pmu_hw_config(struct perf_event *event)
 {
 	if (event->attr.precise_ip) {
@@ -367,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+		/*
+		 * check that PEBS LBR correction does not conflict with
+		 * whatever the user is asking with attr->branch_sample_type
+		 */
+		if (event->attr.precise_ip > 1) {
+			u64 *br_type = &event->attr.branch_sample_type;
+
+			if (has_branch_stack(event)) {
+				if (!precise_br_compat(event))
+					return -EOPNOTSUPP;
+
+				/* branch_sample_type is compatible */
+
+			} else {
+				/*
+				 * user did not specify  branch_sample_type
+				 *
+				 * For PEBS fixups, we capture all
+				 * the branches at the priv level of the
+				 * event.
+				 */
+				*br_type = PERF_SAMPLE_BRANCH_ANY;
+
+				if (!event->attr.exclude_user)
+					*br_type |= PERF_SAMPLE_BRANCH_USER;
+
+				if (!event->attr.exclude_kernel)
+					*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+			}
+		}
 	}
 
 	/*
@@ -424,6 +486,10 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
 
+	/* mark not used */
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
 	return x86_pmu.hw_config(event);
 }
 
@@ -1210,6 +1276,8 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 
 	case CPU_STARTING:
+		if (x86_pmu.attr_rdpmc)
+			set_in_cr4(X86_CR4_PCE);
 		if (x86_pmu.cpu_starting)
 			x86_pmu.cpu_starting(cpu);
 		break;
@@ -1319,6 +1387,8 @@ static int __init init_hw_perf_events(void)
 		}
 	}
 
+	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
@@ -1542,23 +1612,106 @@ static int x86_pmu_event_init(struct perf_event *event)
 	return err;
 }
 
+static int x86_pmu_event_idx(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
+		idx -= X86_PMC_IDX_FIXED;
+		idx |= 1 << 30;
+	}
+
+	return idx + 1;
+}
+
+static ssize_t get_attr_rdpmc(struct device *cdev,
+			      struct device_attribute *attr,
+