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
  ...

8 files changed, 357 insertions, 4 deletions

diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index f7781c6267c0..a09bece6dad2 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -4,6 +4,7 @@
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
index d588b87696fc..d66ab799b35f 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -2,3 +2,11 @@
 MEMCPY_FN(__memcpy,
 	"x86-64-unrolled",
 	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c,
+	"x86-64-movsq",
+	"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c_e,
+	"x86-64-movsb",
+	"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 185a96d66dd1..fcd9cf00600a 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,4 +1,8 @@
-
+#define memcpy MEMCPY /* don't hide glibc's memcpy() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemcpy_c globl memcpy_c; memcpy_c
+#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e
 #include "../../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index db82021f4b91..71557225bf92 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -5,7 +5,6 @@
  *
  * Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
  */
-#include <ctype.h>
 
 #include "../perf.h"
 #include "../util/util.h"
@@ -24,6 +23,7 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
+static int		iterations	= 1;
 static bool		use_clock;
 static int		clock_fd;
 static bool		only_prefault;
@@ -35,6 +35,8 @@ static const struct option options[] = {
 		    "available unit: B, MB, GB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memcpy() invocation this number of times"),
 	OPT_BOOLEAN('c', "clock", &use_clock,
 		    "Use CPU clock for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
@@ -121,6 +123,7 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
 {
 	u64 clock_start = 0ULL, clock_end = 0ULL;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
@@ -128,7 +131,8 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
 		fn(dst, src, len);
 
 	clock_start = get_clock();
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	clock_end = get_clock();
 
 	free(src);
@@ -140,6 +144,7 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
@@ -147,7 +152,8 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
 		fn(dst, src, len);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
new file mode 100644
index 000000000000..a040fa77665b
--- /dev/null
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc)		\
+	extern void *fn(void *, int, size_t);
+
+#include "mem-memset-x86-64-asm-def.h"
+
+#undef MEMSET_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
new file mode 100644
index 000000000000..a71dff97c1f5
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -0,0 +1,12 @@
+
+MEMSET_FN(__memset,
+	"x86-64-unrolled",
+	"unrolled memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c,
+	"x86-64-stosq",
+	"movsq-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c_e,
+	"x86-64-stosb",
+	"movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
new file mode 100644
index 000000000000..9e5af89ed13a
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -0,0 +1,13 @@
+#define memset MEMSET /* don't hide glibc's memset() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemset_c globl memset_c; memset_c
+#define Lmemset_c_e globl memset_c_e; memset_c_e
+#include "../../../arch/x86/lib/memset_64.S"
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
new file mode 100644
index 000000000000..e9079185bd72
--- /dev/null
+++ b/tools/perf/bench/mem-memset.c
@@ -0,0 +1,297 @@
+/*
+ * mem-memset.c
+ *
+ * memset: Simple memory set in various ways
+ *
+ * Trivial clone of mem-memcpy.c.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "mem-memset-arch.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/time.h>
+#include <errno.h>
+
+#define K 1024
+
+static const char	*length_str	= "1MB";
+static const char	*routine	= "default";
+static int		iterations	= 1;
+static bool		use_clock;
+static int		clock_fd;
+static bool		only_prefault;
+static bool		no_prefault;
+
+static const struct option options[] = {
+	OPT_STRING('l', "length", &length_str, "1MB",
+		    "Specify length of memory to copy. "
+		    "available unit: B, MB, GB (upper and lower)"),
+	OPT_STRING('r', "routine", &routine, "default",
+		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memset() invocation this number of times"),
+	OPT_BOOLEAN('c', "clock", &use_clock,
+		    "Use CPU clock for measuring"),
+	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
+		    "Show only the result with page faults before memset()"),
+	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+		    "Show only the result without page faults before memset()"),
+	OPT_END()
+};
+
+typedef void *(*memset_t)(void *, int, size_t);
+
+struct routine {
+	const char *name;
+	const char *desc;
+	memset_t fn;
+};
+
+static const struct routine routines[] = {
+	{ "default",
+	  "Default memset() provided by glibc",
+	  memset },
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
+
+#endif
+
+	{ NULL,
+	  NULL,
+	  NULL   }
+};
+
+static const char * const bench_mem_memset_usage[] = {
+	"perf bench mem memset <options>",
+	NULL
+};
+
+static struct perf_event_attr clock_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES
+};
+
+static void init_clock(void)
+{
+	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+
+	if (clock_fd < 0 && errno == ENOSYS)
+		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+	else
+		BUG_ON(clock_fd < 0);
+}
+
+static u64 get_clock(void)
+{
+	int ret;
+	u64 clk;
+
+	ret = read(clock_fd, &clk, sizeof(u64));
+	BUG_ON(ret != sizeof(u64));
+
+	return clk;
+}
+
+static double timeval2double(struct timeval *ts)
+{
+	return (double)ts->tv_sec +
+		(double)ts->tv_usec / (double)1000000;
+}
+
+static void alloc_mem(void **dst, size_t length)
+{
+	*dst = zalloc(length);
+	if (!dst)
+		die("memory allocation failed - maybe length is too large?\n");
+}
+
+static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+{
+	u64 clock_start = 0ULL, clock_end = 0ULL;
+	void *dst = NULL;
+	int i;
+
+	alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	clock_start = get_clock();
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	clock_end = get_clock();
+
+	free(dst);
+	return clock_end - clock_start;
+}
+
+static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
+{
+	struct timeval tv_start, tv_end, tv_diff;
+	void *dst = NULL;
+	int i;
+
+	alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	BUG_ON(gettimeofday(&tv_start, NULL));
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	BUG_ON(gettimeofday(&tv_end, NULL));
+
+	timersub(&tv_end, &tv_start, &tv_diff);
+
+	free(dst);
+	return (double)((double)len / timeval2double(&tv_diff));
+}
+
+#define pf (no_prefault ? 0 : 1)
+
+#define print_bps(x) do {					\
+		if (x < K)					\
+			printf(" %14lf B/Sec", x);		\
+		else if (x < K * K)				\
+			printf(" %14lfd KB/Sec", x / K);	\
+		else if (x < K * K * K)				\
+			printf(" %14lf MB/Sec", x / K / K);	\
+		else						\
+			printf(" %14lf GB/Sec", x / K / K / K); \
+	} while (0)
+
+int bench_mem_memset(int argc, const char **argv,
+		     const char *prefix __used)
+{
+	int i;
+	size_t len;
+	double result_bps[2];
+	u64 result_clock[2];
+
+	argc = parse_options(argc, argv, options,
+			     bench_mem_memset_usage, 0);
+
+	if (use_clock)
+		init_clock();
+
+	len = (size_t)perf_atoll((char *)length_str);
+
+	result_clock[0] = result_clock[1] = 0ULL;
+	result_bps[0] = result_bps[1] = 0.0;
+
+	if ((s64)len <= 0) {
+		fprintf(stderr, "Invalid length:%s\n", length_str);
+		return 1;
+	}
+
+	/* same to without specifying either of prefault and no-prefault */
+	if (only_prefault && no_prefault)
+		only_prefault = no_prefault = false;
+
+	for (i = 0; routines[i].name; i++) {
+		if (!strcmp(routines[i].name, routine))
+			break;
+	}
+	if (!routines[i].name) {
+		printf("Unknown routine:%s\n", routine);
+		printf("Available routines...\n");
+		for (i = 0; routines[i].name; i++) {
+			printf("\t%s ... %s\n",
+			       routines[i].name, routines[i].desc);
+		}
+		return 1;
+	}
+
+	if (bench_format == BENCH_FORMAT_DEFAULT)
+		printf("# Copying %s Bytes ...\n\n", length_str);
+
+	if (!only_prefault && !no_prefault) {
+		/* show both of results */
+		if (use_clock) {
+			result_clock[0] =
+				do_memset_clock(routines[i].fn, len, false);
+			result_clock[1] =
+				do_memset_clock(routines[i].fn, len, true);
+		} else {
+			result_bps[0] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, false);
+			result_bps[1] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, true);
+		}
+	} else {
+		if (use_clock) {
+			result_clock[pf] =
+				do_memset_clock(routines[i].fn,
+						len, only_prefault);
+		} else {
+			result_bps[pf] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, only_prefault);
+		}
+	}
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		if (!only_prefault && !no_prefault) {
+			if (use_clock) {
+				printf(" %14lf Clock/Byte\n",
+					(double)result_clock[0]
+					/ (double)len);
+				printf(" %14lf Clock/Byte (with prefault)\n ",
+					(double)result_clock[1]
+					/ (double)len);
+			} else {
+				print_bps(result_bps[0]);
+				printf("\n");
+				print_bps(result_bps[1]);
+				printf(" (with prefault)\n");
+			}
+		} else {
+			if (use_clock) {
+				printf(" %14lf Clock/Byte",
+					(double)result_clock[pf]
+					/ (double)len);
+			} else
+				print_bps(result_bps[pf]);
+
+			printf("%s\n", only_prefault ? " (with prefault)" : "");
+		}
+		break;
+	case BENCH_FORMAT_SIMPLE:
+		if (!only_prefault && !no_prefault) {
+			if (use_clock) {
+				printf("%lf %lf\n",
+					(double)result_clock[0] / (double)len,
+					(double)result_clock[1] / (double)len);
+			} else {
+				printf("%lf %lf\n",
+					result_bps[0], result_bps[1]);
+			}
+		} else {
+			if (use_clock) {
+				printf("%lf\n", (double)result_clock[pf]
+					/ (double)len);
+			} else
+				printf("%lf\n", result_bps[pf]);
+		}
+		break;
+	default:
+		/* reaching this means there's some disaster: */
+		die("unknown format: %d\n", bench_format);
+		break;
+	}
+
+	return 0;
+}