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
  ...

6 files changed, 28 insertions, 16 deletions

diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 205b063e3e3..74a2e312e8a 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 74df3f1eddf..48eb30a8606 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 a32b18ce6ea..3a16c1483b4 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 a6962d9161a..ccb805966f6 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 a7d2db9a74f..c0180fd372d 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 461ce432b1c..e8fb2c7a5f4 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