11 files changed, 816 insertions, 48 deletions

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/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
index a72e36cb539..57b4ed87145 100644
--- a/tools/perf/bench/mem-memcpy-arch.h
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -1,5 +1,5 @@
 
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMCPY_FN(fn, name, desc)		\
 	extern void *fn(void *, const void *, size_t);
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 8cdca43016b..5ce71d3b72c 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -58,7 +58,7 @@ struct routine routines[] = {
 	{ "default",
 	  "Default memcpy() provided by glibc",
 	  memcpy },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMCPY_FN(fn, name, desc) { name, desc, fn },
 #include "mem-memcpy-x86-64-asm-def.h"
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
index a040fa77665..633800cb0dc 100644
--- a/tools/perf/bench/mem-memset-arch.h
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -1,5 +1,5 @@
 
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMSET_FN(fn, name, desc)		\
 	extern void *fn(void *, int, size_t);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 4a2f1208196..9af79d2b18e 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -58,7 +58,7 @@ static const struct routine routines[] = {
 	{ "default",
 	  "Default memset() provided by glibc",
 	  memset },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMSET_FN(fn, name, desc) { name, desc, fn },
 #include "mem-memset-x86-64-asm-def.h"
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 30d1c3225b4..ebfa163b80b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -429,14 +429,14 @@ static int parse_cpu_list(const char *arg)
 	return 0;
 }
 
-static void parse_setup_cpu_list(void)
+static int parse_setup_cpu_list(void)
 {
 	struct thread_data *td;
 	char *str0, *str;
 	int t;
 
 	if (!g->p.cpu_list_str)
-		return;
+		return 0;
 
 	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
 
@@ -500,8 +500,12 @@ static void parse_setup_cpu_list(void)
 
 		dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul);
 
-		BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus);
-		BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus);
+		if (bind_cpu_0 >= g->p.nr_cpus || bind_cpu_1 >= g->p.nr_cpus) {
+			printf("\nTest not applicable, system has only %d CPUs.\n", g->p.nr_cpus);
+			return -1;
+		}
+
+		BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
 		BUG_ON(bind_cpu_0 > bind_cpu_1);
 
 		for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
@@ -541,6 +545,7 @@ out:
 		printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
 
 	free(str0);
+	return 0;
 }
 
 static int parse_cpus_opt(const struct option *opt __maybe_unused,
@@ -561,14 +566,14 @@ static int parse_node_list(const char *arg)
 	return 0;
 }
 
-static void parse_setup_node_list(void)
+static int parse_setup_node_list(void)
 {
 	struct thread_data *td;
 	char *str0, *str;
 	int t;
 
 	if (!g->p.node_list_str)
-		return;
+		return 0;
 
 	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
 
@@ -619,8 +624,12 @@ static void parse_setup_node_list(void)
 
 		dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step);
 
-		BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes);
-		BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes);
+		if (bind_node_0 >= g->p.nr_nodes || bind_node_1 >= g->p.nr_nodes) {
+			printf("\nTest not applicable, system has only %d nodes.\n", g->p.nr_nodes);
+			return -1;
+		}
+
+		BUG_ON(bind_node_0 < 0 || bind_node_1 < 0);
 		BUG_ON(bind_node_0 > bind_node_1);
 
 		for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) {
@@ -651,6 +660,7 @@ out:
 		printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
 
 	free(str0);
+	return 0;
 }
 
 static int parse_nodes_opt(const struct option *opt __maybe_unused,
@@ -1110,7 +1120,7 @@ static void *worker_thread(void *__tdata)
 		/* Check whether our max runtime timed out: */
 		if (g->p.nr_secs) {
 			timersub(&stop, &start0, &diff);
-			if (diff.tv_sec >= g->p.nr_secs) {
+			if ((u32)diff.tv_sec >= g->p.nr_secs) {
 				g->stop_work = true;
 				break;
 			}
@@ -1157,7 +1167,7 @@ static void *worker_thread(void *__tdata)
 			runtime_ns_max += diff.tv_usec * 1000;
 
 			if (details >= 0) {
-				printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n",
+				printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n",
 					process_nr, thread_nr, runtime_ns_max / bytes_done, val);
 			}
 			fflush(stdout);
@@ -1356,8 +1366,8 @@ static int init(void)
 	init_thread_data();
 
 	tprintf("#\n");
-	parse_setup_cpu_list();
-	parse_setup_node_list();
+	if (parse_setup_cpu_list() || parse_setup_node_list())
+		return -1;
 	tprintf("#\n");
 
 	print_summary();
@@ -1583,6 +1593,11 @@ static void init_params(struct params *p, const char *name, int argc, const char
 	p->data_rand_walk		= true;
 	p->nr_loops			= -1;
 	p->init_random			= true;
+	p->mb_global_str		= "1";
+	p->nr_proc			= 1;
+	p->nr_threads			= 1;
+	p->nr_secs			= 5;
+	p->run_all			= argc == 1;
 }
 
 static int run_bench_numa(const char *name, const char **argv)
@@ -1600,7 +1615,6 @@ static int run_bench_numa(const char *name, const char **argv)
 	return 0;
 
 err:
-	usage_with_options(numa_usage, options);
 	return -1;
 }
 
@@ -1701,8 +1715,7 @@ static int bench_all(void)
 	BUG_ON(ret < 0);
 
 	for (i = 0; i < nr; i++) {
-		if (run_bench_numa(tests[i][0], tests[i] + 1))
-			return -1;
+		run_bench_numa(tests[i][0], tests[i] + 1);
 	}
 
 	printf("\n");
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 69cfba8d4c6..07a8d7646a1 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -7,9 +7,7 @@
  * Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com>
  *  http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
  * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
- *
  */
-
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
@@ -28,12 +26,24 @@
 #include <sys/time.h>
 #include <sys/types.h>
 
+#include <pthread.h>
+
+struct thread_data {
+	int			nr;
+	int			pipe_read;
+	int			pipe_write;
+	pthread_t		pthread;
+};
+
 #define LOOPS_DEFAULT 1000000
-static int loops = LOOPS_DEFAULT;
+static	int			loops = LOOPS_DEFAULT;
+
+/* Use processes by default: */
+static bool			threaded;
 
 static const struct option options[] = {
-	OPT_INTEGER('l', "loop", &loops,
-		    "Specify number of loops"),
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_BOOLEAN('T', "threaded",	&threaded,	"Specify threads/process based task setup"),
 	OPT_END()
 };
 
@@ -42,13 +52,37 @@ static const char * const bench_sched_pipe_usage[] = {
 	NULL
 };
 
-int bench_sched_pipe(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+static void *worker_thread(void *__tdata)
 {
-	int pipe_1[2], pipe_2[2];
+	struct thread_data *td = __tdata;
 	int m = 0, i;
+	int ret;
+
+	for (i = 0; i < loops; i++) {
+		if (!td->nr) {
+			ret = read(td->pipe_read, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+			ret = write(td->pipe_write, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+		} else {
+			ret = write(td->pipe_write, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+			ret = read(td->pipe_read, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+		}
+	}
+
+	return NULL;
+}
+
+int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct thread_data threads[2], *td;
+	int pipe_1[2], pipe_2[2];
 	struct timeval start, stop, diff;
 	unsigned long long result_usec = 0;
+	int nr_threads = 2;
+	int t;
 
 	/*
 	 * why does "ret" exist?
@@ -58,43 +92,66 @@ int bench_sched_pipe(int argc, const char **argv,
 	int __maybe_unused ret, wait_stat;
 	pid_t pid, retpid __maybe_unused;
 
-	argc = parse_options(argc, argv, options,
-			     bench_sched_pipe_usage, 0);
+	argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0);
 
 	BUG_ON(pipe(pipe_1));
 	BUG_ON(pipe(pipe_2));
 
-	pid = fork();
-	assert(pid >= 0);
-
 	gettimeofday(&start, NULL);
 
-	if (!pid) {
-		for (i = 0; i < loops; i++) {
-			ret = read(pipe_1[0], &m, sizeof(int));
-			ret = write(pipe_2[1], &m, sizeof(int));
-		}
-	} else {
-		for (i = 0; i < loops; i++) {
-			ret = write(pipe_1[1], &m, sizeof(int));
-			ret = read(pipe_2[0], &m, sizeof(int));
+	for (t = 0; t < nr_threads; t++) {
+		td = threads + t;
+
+		td->nr = t;
+
+		if (t == 0) {
+			td->pipe_read = pipe_1[0];
+			td->pipe_write = pipe_2[1];
+		} else {
+			td->pipe_write = pipe_1[1];
+			td->pipe_read = pipe_2[0];
 		}
 	}
 
-	gettimeofday(&stop, NULL);
-	timersub(&stop, &start, &diff);
 
-	if (pid) {
+	if (threaded) {
+
+		for (t = 0; t < nr_threads; t++) {
+			td = threads + t;
+
+			ret = pthread_create(&td->pthread, NULL, worker_thread, td);
+			BUG_ON(ret);
+		}
+
+		for (t = 0; t < nr_threads; t++) {
+			td = threads + t;
+
+			ret = pthread_join(td->pthread, NULL);
+			BUG_ON(ret);
+		}
+
+	} else {
+		pid = fork();
+		assert(pid >= 0);
+
+		if (!pid) {
+			worker_thread(threads + 0);
+			exit(0);
+		} else {
+			worker_thread(threads + 1);
+		}
+
 		retpid = waitpid(pid, &wait_stat, 0);
 		assert((retpid == pid) && WIFEXITED(wait_stat));
-	} else {
-		exit(0);
 	}
 
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
-		printf("# Executed %d pipe operations between two tasks\n\n",
-			loops);
+		printf("# Executed %d pipe operations between two %s\n\n",
+			loops, threaded ? "threads" : "processes");
 
 		result_usec = diff.tv_sec * 1000000;
 		result_usec += diff.tv_usec;