Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo:

User visible:

  * Add several futex 'perf bench' microbenchmarks (Davidlohr Bueso)

  * Speed up thread map generation (Don Zickus)

  * Fix synthesizing mmaps for threads (Don Zickus)

  * Fix invalid output on event group stdio report  (Namhyung Kim)

  * Introduce 'perf kvm --list-cmds' command line option for use by
    scripts (Ramkumar Ramachandra)

Documentation:

  * Clarify load-latency information in the 'perf mem' docs (Andi Kleen)

  * Clarify x86 register naming in 'perf probe' docs (Andi Kleen)

Refactorings:

  * hists browser refactorings to reuse code accross UIs (Namhyung Kim)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

27 files changed, 1094 insertions, 301 deletions

diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 888d51137fb..1d78a4064da 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -18,6 +18,10 @@ from it, into perf.data. Perf record options are accepted and are passed through
 "perf mem -t <TYPE> report" displays the result. It invokes perf report with the
 right set of options to display a memory access profile.
 
+Note that on Intel systems the memory latency reported is the use-latency,
+not the pure load (or store latency). Use latency includes any pipeline
+queueing delays in addition to the memory subsystem latency.
+
 OPTIONS
 -------
 <command>...::
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index b715cb71592..1513935c399 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -136,6 +136,8 @@ Each probe argument follows below syntax.
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
 
+On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
+
 LINE SYNTAX
 -----------
 Line range is described by following syntax.
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 1f7ec48ac95..50d875d970c 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -426,6 +426,9 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 0fdc85269c4..eba46709b27 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -31,6 +31,9 @@ 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 __maybe_unused);
 extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
+extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_requeue(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/futex-hash.c b/tools/perf/bench/futex-hash.c
new file mode 100644
index 00000000000..a84206e9c4a
--- /dev/null
+++ b/tools/perf/bench/futex-hash.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-hash: Stress the hell out of the Linux kernel futex uaddr hashing.
+ *
+ * This program is particularly useful for measuring the kernel's futex hash
+ * table/function implementation. In order for it to make sense, use with as
+ * many threads and futexes as possible.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs    = 10;
+/* amount of futexes per thread */
+static unsigned int nfutexes = 1024;
+static bool fshared = false, done = false, silent = false;
+
+struct timeval start, end, runtime;
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats throughput_stats;
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+	int tid;
+	u_int32_t *futex;
+	pthread_t thread;
+	unsigned long ops;
+};
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &nsecs,    "Specify runtime (in seconds)"),
+	OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_END()
+};
+
+static const char * const bench_futex_hash_usage[] = {
+	"perf bench futex hash <options>",
+	NULL
+};
+
+static void *workerfn(void *arg)
+{
+	int ret;
+	unsigned int i;
+	struct worker *w = (struct worker *) arg;
+
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	do {
+		for (i = 0; i < nfutexes; i++, w->ops++) {
+			/*
+			 * We want the futex calls to fail in order to stress
+			 * the hashing of uaddr and not measure other steps,
+			 * such as internal waitqueue handling, thus enlarging
+			 * the critical region protected by hb->lock.
+			 */
+			ret = futex_wait(&w->futex[i], 1234, NULL,
+					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			if (!silent &&
+			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
+				warn("Non-expected futex return call");
+		}
+	}  while (!done);
+
+	return NULL;
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	/* inform all threads that we're done for the day */
+	done = true;
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &runtime);
+}
+
+static void print_summary(void)
+{
+	unsigned long avg = avg_stats(&throughput_stats);
+	double stddev = stddev_stats(&throughput_stats);
+
+	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
+	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+	       (int) runtime.tv_sec);
+}
+
+int bench_futex_hash(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	cpu_set_t cpu;
+	struct sigaction act;
+	unsigned int i, ncpus;
+	pthread_attr_t thread_attr;
+	struct worker *worker = NULL;
+
+	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_hash_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads) /* default to the number of CPUs */
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		goto errmem;
+
+	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
+	       getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
+
+	init_stats(&throughput_stats);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	threads_starting = nthreads;
+	pthread_attr_init(&thread_attr);
+	gettimeofday(&start, NULL);
+	for (i = 0; i < nthreads; i++) {
+		worker[i].tid = i;
+		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
+		if (!worker[i].futex)
+			goto errmem;
+
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		ret = pthread_create(&worker[i].thread, &thread_attr, workerfn,
+				     (void *)(struct worker *) &worker[i]);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_create");
+
+	}
+	pthread_attr_destroy(&thread_attr);
+
+	pthread_mutex_lock(&thread_lock);
+	while (threads_starting)
+		pthread_cond_wait(&thread_parent, &thread_lock);
+	pthread_cond_broadcast(&thread_worker);
+	pthread_mutex_unlock(&thread_lock);
+
+	sleep(nsecs);
+	toggle_done(0, NULL, NULL);
+
+	for (i = 0; i < nthreads; i++) {
+		ret = pthread_join(worker[i].thread, NULL);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_join");
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+
+	for (i = 0; i < nthreads; i++) {
+		unsigned long t = worker[i].ops/runtime.tv_sec;
+		update_stats(&throughput_stats, t);
+		if (!silent) {
+			if (nfutexes == 1)
+				printf("[thread %2d] futex: %p [ %ld ops/sec ]\n",
+				       worker[i].tid, &worker[i].futex[0], t);
+			else
+				printf("[thread %2d] futexes: %p ... %p [ %ld ops/sec ]\n",
+				       worker[i].tid, &worker[i].futex[0],
+				       &worker[i].futex[nfutexes-1], t);
+		}
+
+		free(worker[i].futex);
+	}
+
+	print_summary();
+
+	free(worker);
+	return ret;
+errmem:
+	err(EXIT_FAILURE, "calloc");
+}
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
new file mode 100644
index 00000000000..a16255876f1
--- /dev/null
+++ b/tools/perf/bench/futex-requeue.c
@@ -0,0 +1,211 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-requeue: Block a bunch of threads on futex1 and requeue them
+ *                on futex2, N at a time.
+ *
+ * This program is particularly useful to measure the latency of nthread
+ * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+static u_int32_t futex1 = 0, futex2 = 0;
+
+/*
+ * How many tasks to requeue at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nrequeue = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+static pthread_t *worker;
+static bool done = 0, silent = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats requeuetime_stats, requeued_stats;
+static unsigned int ncpus, threads_starting, nthreads = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
+	OPT_UINTEGER('r', "repeat",   &repeat,   "Specify amount of times to repeat the run"),
+	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
+	OPT_END()
+};
+
+static const char * const bench_futex_requeue_usage[] = {
+	"perf bench futex requeue <options>",
+	NULL
+};
+
+static void print_summary(void)
+{
+	double requeuetime_avg = avg_stats(&requeuetime_stats);
+	double requeuetime_stddev = stddev_stats(&requeuetime_stats);
+	unsigned int requeued_avg = avg_stats(&requeued_stats);
+
+	printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
+	       requeued_avg,
+	       nthreads,
+	       requeuetime_avg/1e3,
+	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
+}
+
+static void *workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	return NULL;
+}
+
+static void block_threads(pthread_t *w,
+			  pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	/* create and block all threads */
+	for (i = 0; i < nthreads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_requeue(int argc, const char **argv,
+			const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
+	if (argc)
+		goto err;
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
+	       "%d at a time.\n\n",
+	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+
+	init_stats(&requeued_stats);
+	init_stats(&requeuetime_stats);
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < repeat && !done; j++) {
+		unsigned int nrequeued = 0;
+		struct timeval start, end, runtime;
+
+		/* create, launch & block all threads */
+		block_threads(worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start requeueing */
+		gettimeofday(&start, NULL);
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+			/*
+			 * Do not wakeup any tasks blocked on futex1, allowing
+			 * us to really measure futex_wait functionality.
+			 */
+			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
+					  FUTEX_PRIVATE_FLAG);
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &runtime);
+
+		update_stats(&requeued_stats, nrequeued);
+		update_stats(&requeuetime_stats, runtime.tv_usec);
+
+		if (!silent) {
+			printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
+			       j + 1, nrequeued, nthreads, runtime.tv_usec/1e3);
+		}
+
+		/* everybody should be blocked on futex2, wake'em up */
+		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		if (nthreads != nrequeued)
+			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
+
+		for (i = 0; i < nthreads; i++) {
+			ret = pthread_join(worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(worker);
+	return ret;
+err:
+	usage_with_options(bench_futex_requeue_usage, options);
+	exit(EXIT_FAILURE);
+}
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
new file mode 100644
index 00000000000..d096169b161
--- /dev/null
+++ b/tools/perf/bench/futex-wake.c
@@ -0,0 +1,201 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time.
+ *
+ * This program is particularly useful to measure the latency of nthread wakeups
+ * in non-error situations:  all waiters are queued and all wake calls wakeup
+ * one or more tasks, and thus the waitqueue is never empty.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+/* all threads will block on the same futex */
+static u_int32_t futex1 = 0;
+
+/*
+ * How many wakeups to do at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nwakes = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+pthread_t *worker;
+static bool done = 0, silent = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting, nthreads = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
+	OPT_UINTEGER('r', "repeat",  &repeat,   "Specify amount of times to repeat the run"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_END()
+};
+
+static const char * const bench_futex_wake_usage[] = {
+	"perf bench futex wake <options>",
+	NULL
+};
+
+static void *workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	return NULL;
+}
+
+static void print_summary(void)
+{
+	double waketime_avg = avg_stats(&waketime_stats);
+	double waketime_stddev = stddev_stats(&waketime_stats);
+	unsigned int wakeup_avg = avg_stats(&wakeup_stats);
+
+	printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
+	       wakeup_avg,
+	       nthreads,
+	       waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void block_threads(pthread_t *w,
+			  pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	/* create and block all threads */
+	for (i = 0; i < nthreads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_wake(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_wake_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	       "waking up %d at a time.\n\n",
+	       getpid(), nthreads, &futex1, nwakes);
+
+	init_stats(&wakeup_stats);
+	init_stats(&waketime_stats);
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < repeat && !done; j++) {
+		unsigned int nwoken = 0;
+		struct timeval start, end, runtime;
+
+		/* create, launch & block all threads */
+		block_threads(worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start waking folks up */
+		gettimeofday(&start, NULL);
+		while (nwoken != nthreads)
+			nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &runtime);
+
+		update_stats(&wakeup_stats, nwoken);
+		update_stats(&waketime_stats, runtime.tv_usec);
+
+		if (!silent) {
+			printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
+			       j + 1, nwoken, nthreads, runtime.tv_usec/1e3);
+		}
+
+		for (i = 0; i < nthreads; i++) {
+			ret = pthread_join(worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(worker);
+	return ret;
+}
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
new file mode 100644
index 00000000000..71f2844cf97
--- /dev/null
+++ b/tools/perf/bench/futex.h
@@ -0,0 +1,71 @@
+/*
+ * Glibc independent futex library for testing kernel functionality.
+ * Shamelessly stolen from Darren Hart <dvhltc@us.ibm.com>
+ *    http://git.kernel.org/cgit/linux/kernel/git/dvhart/futextest.git/
+ */
+
+#ifndef _FUTEX_H
+#define _FUTEX_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/futex.h>
+
+/**
+ * futex() - SYS_futex syscall wrapper
+ * @uaddr:	address of first futex
+ * @op:		futex op code
+ * @val:	typically expected value of uaddr, but varies by op
+ * @timeout:	typically an absolute struct timespec (except where noted
+ *		otherwise). Overloaded by some ops
+ * @uaddr2:	address of second futex for some ops\
+ * @val3:	varies by op
+ * @opflags:	flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG
+ *
+ * futex() is used by all the following futex op wrappers. It can also be
+ * used for misuse and abuse testing. Generally, the specific op wrappers
+ * should be used instead. It is a macro instead of an static inline function as
+ * some of the types over overloaded (timeout is used for nr_requeue for
+ * example).
+ *
+ * These argument descriptions are the defaults for all
+ * like-named arguments in the following wrappers except where noted below.
+ */
+#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \
+	syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3)
+
+/**
+ * futex_wait() - block on uaddr with optional timeout
+ * @timeout:	relative timeout
+ */
+static inline int
+futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags);
+}
+
+/**
+ * futex_wake() - wake one or more tasks blocked on uaddr
+ * @nr_wake:	wake up to this many tasks
+ */
+static inline int
+futex_wake(u_int32_t *uaddr, int nr_wake, int opflags)
+{
+	return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
+}
+
+/**
+* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
+* @nr_wake:        wake up to this many tasks
+* @nr_requeue:        requeue up to this many tasks
+*/
+static inline int
+futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake,
+		 int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
+		 val, opflags);
+}
+
+#endif /* _FUTEX_H */
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index e47f90cc7b9..f600b74216d 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -12,6 +12,7 @@
  *  sched ... scheduler and IPC performance
  *  mem   ... memory access performance
  *  numa  ... NUMA scheduling and MM performance
+ *  futex ... Futex performance
  */
 #include "perf.h"
 #include "util/util.h"
@@ -54,6 +55,14 @@ static struct bench mem_benchmarks[] = {
 	{ NULL,		NULL,						NULL			}
 };
 
+static struct bench futex_benchmarks[] = {
+	{ "hash",	"Benchmark for futex hash table",               bench_futex_hash	},
+	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
+	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
+	{ "all",	"Test all futex benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -61,11 +70,12 @@ struct collection {
 };
 
 static struct collection collections[] = {
-	{ "sched",	"Scheduler and IPC benchmarks",		sched_benchmarks	},
+	{ "sched",	"Scheduler and IPC benchmarks",			sched_benchmarks	},
 	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},
 #ifdef HAVE_LIBNUMA_SUPPORT
 	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
 #endif
+	{"futex",       "Futex stressing benchmarks",                   futex_benchmarks        },
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index a77e31246c0..204fffe2253 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -952,8 +952,8 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
 				 dfmt->header_width, buf);
 }
 
-static int hpp__header(struct perf_hpp_fmt *fmt,
-		       struct perf_hpp *hpp)
+static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		       struct perf_evsel *evsel __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
@@ -963,7 +963,8 @@ static int hpp__header(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__width(struct perf_hpp_fmt *fmt,
-		      struct perf_hpp *hpp __maybe_unused)
+		      struct perf_hpp *hpp __maybe_unused,
+		      struct perf_evsel *evsel __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index a7350519c63..21c164b8f9d 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1691,17 +1691,15 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 		OPT_END()
 	};
 
-
-	const char * const kvm_usage[] = {
-		"perf kvm [<options>] {top|record|report|diff|buildid-list|stat}",
-		NULL
-	};
+	const char *const kvm_subcommands[] = { "top", "record", "report", "diff",
+						"buildid-list", "stat", NULL };
+	const char *kvm_usage[] = { NULL, NULL };
 
 	perf_host  = 0;
 	perf_guest = 1;
 
-	argc = parse_options(argc, argv, kvm_options, kvm_usage,
-			PARSE_OPT_STOP_AT_NON_OPTION);
+	argc = parse_options_subcommand(argc, argv, kvm_options, kvm_subcommands, kvm_usage,
+					PARSE_OPT_STOP_AT_NON_OPTION);