Merge tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Improvements for the flamegraph python script, including:
       - Display perf.data header
       - Display PIDs of user stacks
       - Added option to change color scheme
       - Default to blue/green color scheme to improve accessibility
       - Correctly identify kernel stacks when debuginfo is available

   - Improvements for 'perf bench futex':
       - Add --mlockall parameter
       - Add --broadcast and --pi to the 'requeue' sub benchmark

   - Add support for PMU aliases.

   - Introduce an ARM Coresight ETE decoder.

   - Add a 'perf bench' entry for evlist open/close operations, to help
     quantify improvements with multithreading 'perf record'.

   - Allow reporting the [un]throttle PERF_RECORD_ meta event in 'perf
     script's python scripting.

   - Add a 'perf test' entry for PMU aliases.

   - Add a 'perf test' entry for 'perf record/perf report/perf script'
     pipe mode.

  Fixes:

   - perf script dlfilter (API for filtering via dynamically loaded
     shared object introduced in v5.14) fixes and a 'perf test' entry
     for it.

   - Fix get_current_dir_name() compilation on Android.

   - Fix issues with asciidoc and double dashes uses.

   - Fix memory leaks in the BTF handling code.

   - Fix leftover problems in the Documentation from the infrastructure
     originally lifted from the git codebase.

   - Fix *probe_vfs_getname.sh 'perf test' failures.

   - Handle fd gaps in 'perf test's test__dso_data_reopen().

   - Make sure to show disasembly warnings for 'perf annotate --stdio'.

   - Fix output from pipe to file and vice-versa in 'perf
     record/report/script'.

   - Correct 'perf data -h' output.

   - Fix wrong comm in system-wide mode with 'perf record --delay'.

   - Do not allow --for-each-cgroup without cpu in 'perf stat'

   - Make 'perf test --skip' work on shell tests.

   - Fix libperf's verbose printing.

  Misc improvements:

   - Preparatory patches for multithreading various 'perf record' phases
     (synthesizing, opening, recording, etc).

   - Add sparse context/locking annotations in compiler-types.h, also to
     help with the multithreading effort.

   - Optimize the generation of the arch specific erno tables used in
     'perf trace'.

   - Optimize libperf's perf_cpu_map__max().

   - Improve ARM's CoreSight warnings.

   - Report collisions in AUX records.

   - Improve warnings for the LLVM 'perf test' entry.

   - Improve the PMU events 'perf test' codebase.

   - perf test: Do not compare overheads in the zstd comp test

   - Better support annotation on ARM.

   - Update 'perf trace's cmd string table to decode sys_bpf() first
     arg.

  Vendor events:

   - Add JSON events and metrics for Intel's Ice Lake, Tiger Lake and
     Elhart Lake.

   - Update JSON eventsand metrics for Intel's Cascade Lake and Sky Lake
     servers.

  Hardware tracing:

   - Improvements for the ARM hardware tracing auxtrace support"

* tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (130 commits)
  perf tests: Add test for PMU aliases
  perf pmu: Add PMU alias support
  perf session: Report collisions in AUX records
  perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta event
  perf build: Report failure for testing feature libopencsd
  perf cs-etm: Show a warning for an unknown magic number
  perf cs-etm: Print the decoder name
  perf cs-etm: Create ETE decoder
  perf cs-etm: Update OpenCSD decoder for ETE
  perf cs-etm: Fix typo
  perf cs-etm: Save TRCDEVARCH register
  perf cs-etm: Refactor out ETMv4 header saving
  perf cs-etm: Initialise architecture based on TRCIDR1
  perf cs-etm: Refactor initialisation of decoder params.
  tools build: Fix feature detect clean for out of source builds
  perf evlist: Add evlist__for_each_entry_from() macro
  perf evsel: Handle precise_ip fallback in evsel__open_cpu()
  perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu()
  perf evsel: Move test_attr__open() to success path in evsel__open_cpu()
  perf evsel: Move ignore_missing_thread() to fallback code
  ...

11 files changed, 607 insertions, 173 deletions

diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index e43f46931b41..61d45fcb4057 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -13,6 +13,7 @@ perf-y += synthesize.o
 perf-y += kallsyms-parse.o
 perf-y += find-bit-bench.o
 perf-y += inject-buildid.o
+perf-y += evlist-open-close.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index eac36afab2b3..b3480bc33fe8 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -48,6 +48,7 @@ int bench_epoll_ctl(int argc, const char **argv);
 int bench_synthesize(int argc, const char **argv);
 int bench_kallsyms_parse(int argc, const char **argv);
 int bench_inject_build_id(int argc, const char **argv);
+int bench_evlist_open_close(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c
new file mode 100644
index 000000000000..83e9897c64a1
--- /dev/null
+++ b/tools/perf/bench/evlist-open-close.c
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <limits.h>
+#include "bench.h"
+#include "../util/debug.h"
+#include "../util/stat.h"
+#include "../util/evlist.h"
+#include "../util/evsel.h"
+#include "../util/strbuf.h"
+#include "../util/record.h"
+#include "../util/parse-events.h"
+#include "internal/threadmap.h"
+#include "internal/cpumap.h"
+#include <linux/perf_event.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+#include <linux/string.h>
+#include <subcmd/parse-options.h>
+
+#define MMAP_FLUSH_DEFAULT 1
+
+static int iterations = 100;
+static int nr_events = 1;
+static const char *event_string = "dummy";
+
+static struct record_opts opts = {
+	.sample_time	     = true,
+	.mmap_pages	     = UINT_MAX,
+	.user_freq	     = UINT_MAX,
+	.user_interval	     = ULLONG_MAX,
+	.freq		     = 4000,
+	.target		     = {
+		.uses_mmap   = true,
+		.default_per_cpu = true,
+	},
+	.mmap_flush          = MMAP_FLUSH_DEFAULT,
+	.nr_threads_synthesize = 1,
+	.ctl_fd              = -1,
+	.ctl_fd_ack          = -1,
+};
+
+static const struct option options[] = {
+	OPT_STRING('e', "event", &event_string, "event", "event selector. use 'perf list' to list available events"),
+	OPT_INTEGER('n', "nr-events", &nr_events,
+		     "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"),
+	OPT_INTEGER('i', "iterations", &iterations, "Number of iterations used to compute average (default=100)"),
+	OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide, "system-wide collection from all CPUs"),
+	OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu", "list of cpus where to open events"),
+	OPT_STRING('p', "pid", &opts.target.pid, "pid", "record events on existing process id"),
+	OPT_STRING('t', "tid", &opts.target.tid, "tid", "record events on existing thread id"),
+	OPT_STRING('u', "uid", &opts.target.uid_str, "user", "user to profile"),
+	OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"),
+	OPT_END()
+};
+
+static const char *const bench_usage[] = {
+	"perf bench internals evlist-open-close <options>",
+	NULL
+};
+
+static int evlist__count_evsel_fds(struct evlist *evlist)
+{
+	struct evsel *evsel;
+	int cnt = 0;
+
+	evlist__for_each_entry(evlist, evsel)
+		cnt += evsel->core.threads->nr * evsel->core.cpus->nr;
+
+	return cnt;
+}
+
+static struct evlist *bench__create_evlist(char *evstr)
+{
+	struct parse_events_error err = { .idx = 0, };
+	struct evlist *evlist = evlist__new();
+	int ret;
+
+	if (!evlist) {
+		pr_err("Not enough memory to create evlist\n");
+		return NULL;
+	}
+
+	ret = parse_events(evlist, evstr, &err);
+	if (ret) {
+		parse_events_print_error(&err, evstr);
+		pr_err("Run 'perf list' for a list of valid events\n");
+		ret = 1;
+		goto out_delete_evlist;
+	}
+
+	ret = evlist__create_maps(evlist, &opts.target);
+	if (ret < 0) {
+		pr_err("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	evlist__config(evlist, &opts, NULL);
+
+	return evlist;
+
+out_delete_evlist:
+	evlist__delete(evlist);
+	return NULL;
+}
+
+static int bench__do_evlist_open_close(struct evlist *evlist)
+{
+	char sbuf[STRERR_BUFSIZE];
+	int err = evlist__open(evlist);
+
+	if (err < 0) {
+		pr_err("evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+		return err;
+	}
+
+	err = evlist__mmap(evlist, opts.mmap_pages);
+	if (err < 0) {
+		pr_err("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+		return err;
+	}
+
+	evlist__enable(evlist);
+	evlist__disable(evlist);
+	evlist__munmap(evlist);
+	evlist__close(evlist);
+
+	return 0;
+}
+
+static int bench_evlist_open_close__run(char *evstr)
+{
+	// used to print statistics only
+	struct evlist *evlist = bench__create_evlist(evstr);
+	double time_average, time_stddev;
+	struct timeval start, end, diff;
+	struct stats time_stats;
+	u64 runtime_us;
+	int i, err;
+
+	if (!evlist)
+		return -ENOMEM;
+
+	init_stats(&time_stats);
+
+	printf("  Number of cpus:\t%d\n", evlist->core.cpus->nr);
+	printf("  Number of threads:\t%d\n", evlist->core.threads->nr);
+	printf("  Number of events:\t%d (%d fds)\n",
+		evlist->core.nr_entries, evlist__count_evsel_fds(evlist));
+	printf("  Number of iterations:\t%d\n", iterations);
+
+	evlist__delete(evlist);
+
+	for (i = 0; i < iterations; i++) {
+		pr_debug("Started iteration %d\n", i);
+		evlist = bench__create_evlist(evstr);
+		if (!evlist)
+			return -ENOMEM;
+
+		gettimeofday(&start, NULL);
+		err = bench__do_evlist_open_close(evlist);
+		if (err) {
+			evlist__delete(evlist);
+			return err;
+		}
+
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &diff);
+		runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+		update_stats(&time_stats, runtime_us);
+
+		evlist__delete(evlist);
+		pr_debug("Iteration %d took:\t%" PRIu64 "us\n", i, runtime_us);
+	}
+
+	time_average = avg_stats(&time_stats);
+	time_stddev = stddev_stats(&time_stats);
+	printf("  Average open-close took: %.3f usec (+- %.3f usec)\n", time_average, time_stddev);
+
+	return 0;
+}
+
+static char *bench__repeat_event_string(const char *evstr, int n)
+{
+	char sbuf[STRERR_BUFSIZE];
+	struct strbuf buf;
+	int i, str_size = strlen(evstr),
+	    final_size = str_size * n + n,
+	    err = strbuf_init(&buf, final_size);
+
+	if (err) {
+		pr_err("strbuf_init: %s\n", str_error_r(err, sbuf, sizeof(sbuf)));
+		goto out_error;
+	}
+
+	for (i = 0; i < n; i++) {
+		err = strbuf_add(&buf, evstr, str_size);
+		if (err) {
+			pr_err("strbuf_add: %s\n", str_error_r(err, sbuf, sizeof(sbuf)));
+			goto out_error;
+		}
+
+		err = strbuf_addch(&buf, i == n-1 ? '\0' : ',');
+		if (err) {
+			pr_err("strbuf_addch: %s\n", str_error_r(err, sbuf, sizeof(sbuf)));
+			goto out_error;
+		}
+	}
+
+	return strbuf_detach(&buf, NULL);
+
+out_error:
+	strbuf_release(&buf);
+	return NULL;
+}
+
+
+int bench_evlist_open_close(int argc, const char **argv)
+{
+	char *evstr, errbuf[BUFSIZ];
+	int err;
+
+	argc = parse_options(argc, argv, options, bench_usage, 0);
+	if (argc) {
+		usage_with_options(bench_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	err = target__validate(&opts.target);
+	if (err) {
+		target__strerror(&opts.target, err, errbuf, sizeof(errbuf));
+		pr_err("%s\n", errbuf);
+		goto out;
+	}
+
+	err = target__parse_uid(&opts.target);
+	if (err) {
+		target__strerror(&opts.target, err, errbuf, sizeof(errbuf));
+		pr_err("%s", errbuf);
+		goto out;
+	}
+
+	/* Enable ignoring missing threads when -u/-p option is defined. */
+	opts.ignore_missing_thread = opts.target.uid != UINT_MAX || opts.target.pid;
+
+	evstr = bench__repeat_event_string(event_string, nr_events);
+	if (!evstr) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = bench_evlist_open_close__run(evstr);
+
+	free(evstr);
+out:
+	return err;
+}
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index b65373ce5c4f..fcdea3e44937 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <sys/time.h>
+#include <sys/mman.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
@@ -29,11 +30,7 @@
 
 #include <err.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;
+static bool done = false;
 static int futex_flag = 0;
 
 struct timeval bench__start, bench__end, bench__runtime;
@@ -49,12 +46,18 @@ struct worker {
 	unsigned long ops;
 };
 
+static struct bench_futex_parameters params = {
+	.nfutexes = 1024,
+	.runtime  = 10,
+};
+
 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_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &params.runtime, "Specify runtime (in seconds)"),
+	OPT_UINTEGER('f', "futexes", &params.nfutexes, "Specify amount of futexes per threads"),
+	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &params.fshared, "Use shared futexes instead of private ones"),
+	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),
 	OPT_END()
 };
 
@@ -78,7 +81,7 @@ static void *workerfn(void *arg)
 	pthread_mutex_unlock(&thread_lock);
 
 	do {
-		for (i = 0; i < nfutexes; i++, ops++) {
+		for (i = 0; i < params.nfutexes; i++, ops++) {
 			/*
 			 * We want the futex calls to fail in order to stress
 			 * the hashing of uaddr and not measure other steps,
@@ -86,7 +89,7 @@ static void *workerfn(void *arg)
 			 * the critical region protected by hb->lock.
 			 */
 			ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
-			if (!silent &&
+			if (!params.silent &&
 			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
 				warn("Non-expected futex return call");
 		}
@@ -112,7 +115,7 @@ static void print_summary(void)
 	double stddev = stddev_stats(&throughput_stats);
 
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
-	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+	       !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
 	       (int)bench__runtime.tv_sec);
 }
 
@@ -141,30 +144,35 @@ int bench_futex_hash(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	if (!nthreads) /* default to the number of CPUs */
-		nthreads = cpu->nr;
+	if (params.mlockall) {
+		if (mlockall(MCL_CURRENT | MCL_FUTURE))
+			err(EXIT_FAILURE, "mlockall");
+	}
+
+	if (!params.nthreads) /* default to the number of CPUs */
+		params.nthreads = cpu->nr;
 
-	worker = calloc(nthreads, sizeof(*worker));
+	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)
 		goto errmem;
 
-	if (!fshared)
+	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
 	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);
+	       getpid(), params.nthreads, params.nfutexes, params.fshared ? "shared":"private", params.runtime);
 
 	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;
+	threads_starting = params.nthreads;
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&bench__start, NULL);
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		worker[i].tid = i;
-		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
+		worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex));
 		if (!worker[i].futex)
 			goto errmem;
 
@@ -189,10 +197,10 @@ int bench_futex_hash(int argc, const char **argv)
 	pthread_cond_broadcast(&thread_worker);
 	pthread_mutex_unlock(&thread_lock);
 
-	sleep(nsecs);
+	sleep(params.runtime);
 	toggle_done(0, NULL, NULL);
 
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		ret = pthread_join(worker[i].thread, NULL);
 		if (ret)
 			err(EXIT_FAILURE, "pthread_join");
@@ -203,18 +211,18 @@ int bench_futex_hash(int argc, const char **argv)
 	pthread_cond_destroy(&thread_worker);
 	pthread_mutex_destroy(&thread_lock);
 
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		unsigned long t = bench__runtime.tv_sec > 0 ?
 			worker[i].ops / bench__runtime.tv_sec : 0;
 		update_stats(&throughput_stats, t);
-		if (!silent) {
-			if (nfutexes == 1)
+		if (!params.silent) {
+			if (params.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);
+				       &worker[i].futex[params.nfutexes-1], t);
 		}
 
 		zfree(&worker[i].futex);
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 89c6d160379c..5d1fe9c35807 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -21,6 +21,7 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
+#include <sys/mman.h>
 
 struct worker {
 	int tid;
@@ -31,22 +32,24 @@ struct worker {
 
 static u_int32_t global_futex = 0;
 static struct worker *worker;
-static unsigned int nsecs = 10;
-static bool silent = false, multi = false;
-static bool done = false, fshared = false;
-static unsigned int nthreads = 0;
+static bool done = false;
 static int futex_flag = 0;
 static pthread_mutex_t thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
 static pthread_cond_t thread_parent, thread_worker;
 
+static struct bench_futex_parameters params = {
+	.runtime  = 10,
+};
+
 static const struct option options[] = {
-	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
-	OPT_UINTEGER('r', "runtime", &nsecs,     "Specify runtime (in seconds)"),
-	OPT_BOOLEAN( 'M', "multi",   &multi,     "Use multiple futexes"),
-	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_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &params.runtime, "Specify runtime (in seconds)"),
+	OPT_BOOLEAN( 'M', "multi",   &params.multi, "Use multiple futexes"),
+	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &params.fshared, "Use shared futexes instead of private ones"),
+	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),
 	OPT_END()
 };
 
@@ -61,7 +64,7 @@ static void print_summary(void)
 	double stddev = stddev_stats(&throughput_stats);
 
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
-	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+	       !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
 	       (int)bench__runtime.tv_sec);
 }
 
@@ -93,7 +96,7 @@ static void *workerfn(void *arg)
 		ret = futex_lock_pi(w->futex, NULL, futex_flag);
 
 		if (ret) { /* handle lock acquisition */
-			if (!silent)
+			if (!params.silent)
 				warn("thread %d: Could not lock pi-lock for %p (%d)",
 				     w->tid, w->futex, ret);
 			if (done)
@@ -104,7 +107,7 @@ static void *workerfn(void *arg)
 
 		usleep(1);
 		ret = futex_unlock_pi(w->futex, futex_flag);
-		if (ret && !silent)
+		if (ret && !params.silent)
 			warn("thread %d: Could not unlock pi-lock for %p (%d)",
 			     w->tid, w->futex, ret);
 		ops++; /* account for thread's share of work */
@@ -120,12 +123,12 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
 	cpu_set_t cpuset;
 	unsigned int i;
 
-	threads_starting = nthreads;
+	threads_starting = params.nthreads;
 
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		worker[i].tid = i;
 
-		if (multi) {
+		if (params.multi) {
 			worker[i].futex = calloc(1, sizeof(u_int32_t));
 			if (!worker[i].futex)
 				err(EXIT_FAILURE, "calloc");
@@ -164,25 +167,30 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	if (!nthreads)
-		nthreads = cpu->nr;
+	if (params.mlockall) {
+		if (mlockall(MCL_CURRENT | MCL_FUTURE))
+			err(EXIT_FAILURE, "mlockall");
+	}
+
+	if (!params.nthreads)
+		params.nthreads = cpu->nr;
 
-	worker = calloc(nthreads, sizeof(*worker));
+	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!fshared)
+	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
 	printf("Run summary [PID %d]: %d threads doing pi lock/unlock pairing for %d secs.\n\n",
-	       getpid(), nthreads, nsecs);
+	       getpid(), params.nthreads, params.runtime);
 
 	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;
+	threads_starting = params.nthreads;
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&bench__start, NULL);
 
@@ -195,10 +203,10 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_cond_broadcast(&thread_worker);
 	pthread_mutex_unlock(&thread_lock);
 
-	sleep(nsecs);
+	sleep(params.runtime);
 	toggle_done(0, NULL, NULL);
 
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		ret = pthread_join(worker[i].thread, NULL);
 		if (ret)
 			err(EXIT_FAILURE, "pthread_join");
@@ -209,16 +217,16 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_cond_destroy(&thread_worker);
 	pthread_mutex_destroy(&thread_lock);
 
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		unsigned long t = bench__runtime.tv_sec > 0 ?
 			worker[i].ops / bench__runtime.tv_sec : 0;
 
 		update_stats(&throughput_stats, t);
-		if (!silent)
+		if (!params.silent)
 			printf("[thread %3d] futex: %p [ %ld ops/sec ]\n",
 			       worker[i].tid, worker[i].futex, t);
 
-		if (multi)
+		if (params.multi)
 			zfree(&worker[i].futex);
 	}
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 5fa23295ee5f..97fe31fd3a23 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -6,7 +6,8 @@
  *                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.
+ * requeues without waking up any tasks (in the non-pi case) -- thus
+ * mimicking a regular futex_wait.
  */
 
 /* For the CLR_() macros */
@@ -27,28 +28,35 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
+#include <sys/mman.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;
-
 static pthread_t *worker;
-static bool done = false, silent = false, fshared = false;
+static bool done = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
-static unsigned int threads_starting, nthreads = 0;
+static unsigned int threads_starting;
 static int futex_flag = 0;
 
+static struct bench_futex_parameters params = {
+	/*
+	 * How many tasks to requeue at a time.
+	 * Default to 1 in order to make the kernel work more.
+	 */
+	.nrequeue = 1,
+};
+
 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_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
-	OPT_BOOLEAN( 'S', "shared",   &fshared,  "Use shared futexes instead of private ones"),
+	OPT_UINTEGER('t', "threads",  &params.nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('q', "nrequeue", &params.nrequeue, "Specify amount of threads to requeue at once"),
+	OPT_BOOLEAN( 's', "silent",   &params.silent, "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",   &params.fshared, "Use shared futexes instead of private ones"),
+	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),
+	OPT_BOOLEAN( 'B', "broadcast", &params.broadcast, "Requeue all threads at once"),
+	OPT_BOOLEAN( 'p', "pi", &params.pi, "Use PI-aware variants of FUTEX_CMP_REQUEUE"),
+
 	OPT_END()
 };
 
@@ -65,13 +73,15 @@ static void print_summary(void)
 
 	printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
 	       requeued_avg,
-	       nthreads,
+	       params.nthreads,
 	       requeuetime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
 }
 
 static void *workerfn(void *arg __maybe_unused)
 {
+	int ret;
+
 	pthread_mutex_lock(&thread_lock);
 	threads_starting--;
 	if (!threads_starting)
@@ -79,7 +89,34 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, futex_flag);
+	while (1) {
+		if (!params.pi) {
+			ret = futex_wait(&futex1, 0, NULL, futex_flag);
+			if (!ret)
+				break;
+
+			if (ret && errno != EAGAIN) {
+				if (!params.silent)
+					warnx("futex_wait");
+				break;
+			}
+		} else {
+			ret = futex_wait_requeue_pi(&futex1, 0, &futex2,
+						    NULL, futex_flag);
+			if (!ret) {
+				/* got the lock at futex2 */
+				futex_unlock_pi(&futex2, futex_flag);
+				break;
+			}
+
+			if (ret && errno != EAGAIN) {
+				if (!params.silent)
+					warnx("futex_wait_requeue_pi");
+				break;
+			}
+		}
+	}
+
 	return NULL;
 }
 
@@ -89,10 +126,10 @@ static void block_threads(pthread_t *w,
 	cpu_set_t cpuset;
 	unsigned int i;
 
-	threads_starting = nthreads;
+	threads_starting = params.nthreads;
 
 	/* create and block all threads */
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
 		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
@@ -132,22 +169,31 @@ int bench_futex_requeue(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	if (!nthreads)
-		nthreads = cpu->nr;
+	if (params.mlockall) {
+		if (mlockall(MCL_CURRENT | MCL_FUTURE))
+			err(EXIT_FAILURE, "mlockall");
+	}
+
+	if (!params.nthreads)
+		params.nthreads = cpu->nr;
 
-	worker = calloc(nthreads, sizeof(*worker));
+	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!fshared)
+	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
-	if (nrequeue > nthreads)
-		nrequeue = nthreads;
+	if (params.nrequeue > params.nthreads)
+		params.nrequeue = params.nthreads;
 
-	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
-	       "%d at a time.\n\n",  getpid(), nthreads,
-	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);
+	if (params.broadcast)
+		params.nrequeue = params.nthreads;
+
+	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %s%p), "
+	       "%d at a time.\n\n",  getpid(), params.nthreads,
+	       params.fshared ? "shared":"private", &futex1,
+	       params.pi ? "PI ": "", &futex2, params.nrequeue);
 
 	init_stats(&requeued_stats);
 	init_stats(&requeuetime_stats);
@@ -157,7 +203,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	pthread_cond_init(&thread_worker, NULL);
 
 	for (j = 0; j < bench_repeat && !done; j++) {
-		unsigned int nrequeued = 0;
+		unsigned int nrequeued = 0, wakeups = 0;
 		struct timeval start, end, runtime;
 
 		/* create, launch & block all threads */
@@ -174,13 +220,31 @@ int bench_futex_requeue(int argc, const char **argv)
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		while (nrequeued < nthreads) {
+		while (nrequeued < params.nthreads) {
+			int r;
+
 			/*
-			 * Do not wakeup any tasks blocked on futex1, allowing
-			 * us to really measure futex_wait functionality.
+			 * For the regular non-pi case, do not wakeup any tasks
+			 * blocked on futex1, allowing us to really measure
+			 * futex_wait functionality. For the PI case the first
+			 * waiter is always awoken.
 			 */
-			nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
-						       nrequeue, futex_flag);
+			if (!params.pi) {
+				r = futex_cmp_requeue(&futex1, 0, &futex2, 0,
+						      params.nrequeue,
+						      futex_flag);
+			} else {
+				r = futex_cmp_requeue_pi(&futex1, 0, &futex2,
+							 params.nrequeue,
+							 futex_flag);
+				wakeups++; /* assume no error */
+			}
+
+			if (r < 0)
+				err(EXIT_FAILURE, "couldn't requeue from %p to %p",
+				    &futex1, &futex2);
+
+			nrequeued += r;
 		}
 
 		gettimeofday(&end, NULL);
@@ -189,17 +253,32 @@ int bench_futex_requeue(int argc, const char **argv)
 		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 / (double)USEC_PER_MSEC);
+		if (!params.silent) {
+			if (!params.pi)
+				printf("[Run %d]: Requeued %d of %d threads in "
+				       "%.4f ms\n", j + 1, nrequeued,
+				       params.nthreads,
+				       runtime.tv_usec / (double)USEC_PER_MSEC);
+			else {
+				nrequeued -= wakeups;
+				printf("[Run %d]: Awoke and Requeued (%d+%d) of "
+				       "%d threads in %.4f ms\n",
+				       j + 1, wakeups, nrequeued,
+				       params.nthreads,
+				       runtime.tv_usec / (double)USEC_PER_MSEC);
+			}
+
 		}
 
-		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
-		if (nthreads != nrequeued)
-			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
+		if (!params.pi) {
+			/* everybody should be blocked on futex2, wake'em up */
+			nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
+			if (params.nthreads != nrequeued)
+				warnx("couldn't wakeup all tasks (%d/%d)",
+				      nrequeued, params.nthreads);
+		}
 
-		for (i = 0; i < nthreads; i++) {
+		for (i = 0; i < params.nthreads; i++) {
 			ret = pthread_join(worker[i], NULL);
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 6e6f5247e1fe..e970e6b9ad53 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -34,6 +34,7 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
+#include <sys/mman.h>
 
 struct thread_data {
 	pthread_t worker;
@@ -47,8 +48,7 @@ static unsigned int nwakes = 1;
 static u_int32_t futex = 0;
 
 static pthread_t *blocked_worker;
-static bool done = false, silent = false, fshared = false;
-static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static bool done = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static pthread_barrier_t barrier;
@@ -56,11 +56,15 @@ static struct stats waketime_stats, wakeup_stats;
 static unsigned int threads_starting;
 static int futex_flag = 0;
 
+static struct bench_futex_parameters params;
+
 static const struct option options[] = {
-	OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
-	OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking 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_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakers", &params.nwakes, "Specify amount of waking threads"),
+	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &params.fshared, "Use shared futexes instead of private ones"),
+	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),
+
 	OPT_END()
 };
 
@@ -96,10 +100,10 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
 	pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
 
-	pthread_barrier_init(&barrier, NULL, nwaking_threads + 1);
+	pthread_barrier_init(&barrier, NULL, params.nwakes + 1);
 
 	/* create and block all threads */
-	for (i = 0; i < nwaking_threads; i++) {
+	for (i = 0; i < params.nwakes; i++) {
 		/*
 		 * Thread creation order will impact per-thread latency
 		 * as it will affect the order to acquire the hb spinlock.
@@ -112,7 +116,7 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
 	pthread_barrier_wait(&barrier);
 
-	for (i = 0; i < nwaking_threads; i++)
+	for (i = 0; i < params.nwakes; i++)
 		if (pthread_join(td[i].worker, NULL))
 			err(EXIT_FAILURE, "pthread_join");
 
@@ -143,10 +147,10 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
 	cpu_set_t cpuset;
 	unsigned int i;
 
-	threads_starting = nblocked_threads;
+	threads_starting = params.nthreads;
 
 	/* create and block all threads */
-	for (i = 0; i < nblocked_threads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
 		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
@@ -167,7 +171,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
 	init_stats(&__wakeup_stats);
 	init_stats(&__waketime_stats);
 
-	for (i = 0; i < nwaking_threads; i++) {
+	for (i = 0; i < params.nwakes; i++) {
 		update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
 		update_stats(&__wakeup_stats, waking_worker[i].nwoken);
 	}
@@ -178,7 +182,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
 
 	printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
 	       "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
-	       nblocked_threads, waketime_avg / USEC_PER_MSEC,
+	       params.nthreads, waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
 
@@ -193,7 +197,7 @@ static void print_summary(void)
 
 	printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
 	       wakeup_avg,
-	       nblocked_threads,
+	       params.nthreads,
 	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
@@ -203,7 +207,7 @@ static void do_run_stats(struct thread_data *waking_worker)
 {
 	unsigned int i;
 
-	for (i = 0; i < nwaking_threads; i++) {
+	for (i = 0; i < params.nwakes; i++) {
 		update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
 		update_stats(&wakeup_stats, waking_worker[i].nwoken);
 	}
@@ -238,36 +242,42 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
+	if (params.mlockall) {
+		if (mlockall(MCL_CURRENT | MCL_FUTURE))
+			err(EXIT_FAILURE, "mlockall");
+	}
+
 	cpu = perf_cpu_map__new(NULL);
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!nblocked_threads)
-		nblocked_threads = cpu->nr;
+	if (!params.nthreads)
+		params.nthreads = cpu->nr;
 
 	/* some sanity checks */
-	if (nwaking_threads > nblocked_threads || !nwaking_threads)
-		nwaking_threads = nblocked_threads;
+	if (params.nwakes > params.nthreads ||
+	    !params.nwakes)
+		params.nwakes = params.nthreads;
 
-	if (nblocked_threads % nwaking_threads)
+	if (params.nthreads % params.nwakes)
 		errx(EXIT_FAILURE, "Must be perfectly divisible");
 	/*
 	 * Each thread will wakeup nwakes tasks in
 	 * a single futex_wait call.
 	 */
-	nwakes = nblocked_threads/nwaking_threads;
+	nwakes = params.nthreads/params.nwakes;
 
-	blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+	blocked_worker = calloc(params.nthreads, sizeof(*blocked_worker));
 	if (!blocked_worker)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!fshared)
+	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
 	printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
 	       "futex %p), %d threads waking up %d at a time.\n\n",
-	       getpid(), nblocked_threads, fshared ? "shared":"private",
-	       &futex, nwaking_threads, nwakes);
+	       getpid(), params.nthreads, params.fshared ? "shared":"private",
+	       &futex, params.nwakes, nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -278,7 +288,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	pthread_cond_init(&thread_worker, NULL);
 
 	for (j = 0; j < bench_repeat && !done; j++) {
-		waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+		waking_worker = calloc(params.nwakes, sizeof(*waking_worker));
 		if (!waking_worker)
 			err(EXIT_FAILURE, "calloc");
 
@@ -297,14 +307,14 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 		/* Ok, all threads are patiently blocked, start waking folks up */
 		wakeup_threads(waking_worker, thread_attr);
 
-		for (i = 0; i < nblocked_threads; i++) {
+		for (i = 0; i < params.nthreads; i++) {
 			ret = pthread_join(blocked_worker[i], NULL);
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
 		}
 
 		do_run_stats(waking_worker);
-		if (!silent)
+		if (!params.silent)
 			print_run(waking_worker, j);
 
 		free(waking_worker);
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 6d217868f53c..77f058a47790 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -27,29 +27,34 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
+#include <sys/mman.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;
-
-pthread_t *worker;
-static bool done = false, silent = false, fshared = false;
+static pthread_t *worker;
+static bool done = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
-static unsigned int threads_starting, nthreads = 0;
+static unsigned int threads_starting;
 static int futex_flag = 0;
 
+static struct bench_futex_parameters params = {
+	/*
+	 * How many wakeups to do at a time.
+	 * Default to 1 in order to make the kernel work more.
+	 */
+	.nwakes  = 1,
+};
+
 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_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
-	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakes",  &params.nwakes, "Specify amount of threads to wake at once"),
+	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &params.fshared, "Use shared futexes instead of private ones"),
+	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),
+
 	OPT_END()
 };
 
@@ -84,7 +89,7 @@ static void print_summary(void)
 
 	printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
 	       wakeup_avg,
-	       nthreads,
+	       params.nthreads,
 	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
@@ -95,10 +100,10 @@ static void block_threads(pthread_t *w,
 	cpu_set_t cpuset;
 	unsigned int i;
 
-	threads_starting = nthreads;
+	threads_starting = params.nthreads;
 
 	/* create and block all threads */
-	for (i = 0; i < nthreads; i++) {
+	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
 		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
@@ -140,19 +145,25 @@ int bench_futex_wake(int argc, const char **argv)
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
-	if (!nthreads)
-		nthreads = cpu->nr;
+	if (params.mlockall) {
+		if (mlockall(MCL_CURRENT | MCL_FUTURE))
+			err(EXIT_FAILURE, "mlockall");
+	}
+
+	if (!params.nthreads)
+		params.nthreads = cpu->nr;
 
-	worker = calloc(nthreads, sizeof(*worker));
+	worker = calloc(params.nthreads, sizeof(*worker));
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	if (!fshared)
+	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
 	printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), "
 	       "waking up %d at a time.\n\n",
-	       getpid(), nthreads, fshared ? "shared":"private",  &futex1, nwakes);
+	       getpid(), params.nthreads, params.fshared ? "shared":"private",
+	       &futex1, params.nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -179,20 +190,22 @@ int bench_futex_wake(int argc, const char **argv)
 
 		/* Ok, all threads are patiently blocked, start waking folks up */
 		gettimeofday(&start, NULL);
-		while (nwoken != nthreads)
-			nwoken += futex_wake(&futex1, nwakes, futex_flag);
+		while (nwoken != params.nthreads)
+			nwoken += futex_wake(&futex1,
+					     params.nwakes, futex_flag);
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
 		update_stats(&wakeup_stats, nwoken);
 		update_stats(&waketime_stats, runtime.tv_usec);
 
-		if (!silent) {
+		if (!params.silent) {
 			printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
-			       j + 1, nwoken, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
+			       j + 1, nwoken, params.nthreads,
+			       runtime.tv_usec / (double)USEC_PER_MSEC);
 		}
 
-		for (i = 0; i < nthreads; i++) {
+		for (i = 0; i < params.nthreads; i++) {
 			ret = pthread_join(worker[i], NULL);
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 31b53cc7d5bc..b3853aac3021 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -13,6 +13,20 @@
 #include <sys/types.h>
 #include <linux/futex.h>
 
+struct bench_futex_parameters {
+	bool silent;
+	bool fshared;
+	bool mlockall;
+	bool multi; /* lock-pi */
+	bool pi; /* requeue-pi */
+	bool broadcast; /* requeue */
+	unsigned int runtime; /* seconds*/
+	unsigned int nthreads;
+	unsigned int nfutexes;
+	unsigned int nwakes;
+	unsigned int nrequeue;
+};
+
 /**
  * futex() - SYS_futex syscall wrapper
  * @uaddr:	address of first futex
@@ -20,7 +34,7 @@
  * @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\
+ * @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
  *
@@ -77,7 +91,7 @@ futex_unlock_pi(u_int32_t *uaddr, int 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
+* @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,
@@ -86,4 +100,38 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
 	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
 		 val, opflags);
 }
+
+/**
+ * futex_wait_requeue_pi() - block on uaddr and prepare to requeue to uaddr2
+ * @uaddr:	non-PI futex source
+ * @uaddr2:	PI futex target
+ *
+ * This is the first half of the requeue_pi mechanism. It shall always be
+ * paired with futex_cmp_requeue_pi().
+ */
+static inline int
+futex_wait_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
+		      struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0,
+		     opflags);
+}
+
+/**
+ * futex_cmp_requeue_pi() - requeue tasks from uaddr to uaddr2
+ * @uaddr:	non-PI futex source
+ * @uaddr2:	PI futex target
+ * @nr_requeue:	requeue up to this many tasks
+ *
+ * This is the second half of the requeue_pi mechanism. It shall always be
+ * paired with futex_wait_requeue_pi(). The first waker is always awoken.
+ */
+static inline int
+futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
+		     int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2,
+		     val, opflags);
+}
+
 #endif /* _FUTEX_H */
diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index 55d373b75791..17672790f123 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -133,7 +133,7 @@ static u64 dso_map_addr(struct bench_dso *dso)
 	return 0x400000ULL + dso->ino * 8192ULL;
 }
 
-static u32 synthesize_attr(struct bench_data *data)
+static ssize_t synthesize_attr(struct bench_data *data)
 {
 	union perf_event event;
 
@@ -151,7 +151,7 @@ static u32 synthesize_attr(struct bench_data *data)
 	return writen(data->input_pipe[1], &event, event.header.size);
 }
 
-static u32 synthesize_fork(struct bench_data *data)
+static ssize_t synthesize_fork(struct bench_data *data)
 {
 	union perf_event event;
 
@@ -169,8 +169,7 @@ static u32 synthesize_fork(struct bench_data *data)
 	return writen(data->input_pipe[1], &event, event.header.size);
 }
 
-static u32 synthesize_mmap(struct bench_data *data, struct bench_dso *dso,
-			   u64 timestamp)
+static ssize_t synthesize_mmap(struct bench_data *data, struct bench_dso *dso, u64 timestamp)
 {
 	union perf_event event;
 	size_t len = offsetof(struct perf_record_mmap2, filename);
@@ -198,23 +197,25 @@ static u32 synthesize_mmap(struct bench_data *data, struct bench_dso *dso,
 
 	if (len > sizeof(event.mmap2)) {
 		/* write mmap2 event first */
-		writen(data->input_pipe[1], &event, len - bench_id_hdr_size);
+		if (writen(data->input_pipe[1], &event, len - bench_id_hdr_size) < 0)
+			return -1;
 		/* zero-fill sample id header */
 		memset(id_hdr_ptr, 0, bench_id_hdr_size);
 		/* put timestamp in the right position */
 		ts_idx = (bench_id_hdr_size / sizeof(u64)) - 2;
 		id_hdr_ptr[ts_idx] = timestamp;
-		writen(data->input_pipe[1], id_hdr_ptr, bench_id_hdr_size);
-	} else {
-		ts_idx = (len / sizeof(u64)) - 2;
-		id_hdr_ptr[ts_idx] = timestamp;
-		writen(data->input_pipe[1], &event, len);
+		if (writen(data->input_pipe[1], id_hdr_ptr, bench_id_hdr_size) < 0)
+			return -1;
+
+		return len;
 	}
-	return len;
+
+	ts_idx = (len / sizeof(u64)) - 2;
+	id_hdr_ptr[ts_idx] = timestamp;
+	return writen(data->input_pipe[1], &event, len);
 }
 
-static u32 synthesize_sample(struct bench_data *data, struct bench_dso *dso,
-			     u64 timestamp)
+static ssize_t synthesize_sample(struct bench_data *data, struct bench_dso *dso, u64 timestamp)
 {
 	union perf_event event;
 	struct perf_sample sample = {
@@ -233,7 +234,7 @@ static u32 synthesize_sample(struct bench_data *data, struct bench_dso *dso,
 	return writen(data->input_pipe[1], &event, event.header.size);
 }
 
-static u32 synthesize_flush(struct bench_data *data)
+static ssize_t synthesize_flush(struct bench_data *data)
 {
 	struct perf_event_header header = {
 		.size = sizeof(header),
@@ -348,14 +349,16 @@ static int inject_build_id(struct bench_data *data, u64 *max_rss)
 	int status;
 	unsigned int i, k;
 	struct rusage rusage;
-	u64 len = 0;
 
 	/* this makes the child to run */
 	if (perf_header__write_pipe(data->input_pipe[1]) < 0)
 		return -1;
 
-	len += synthesize_attr(data);
-	len += synthesize_fork(data);
+	if (synthesize_attr(data) < 0)
+		return -1;
+
+	if (synthesize_fork(data) < 0)
+		return -1;
 
 	for (i = 0; i < nr_mmaps; i++) {
 		int idx = rand() % (nr_dsos - 1);
@@ -363,13 +366,18 @@ static int inject_build_id(struct bench_data *data, u64 *max_rss)
 		u64 timestamp = rand() % 1000000;
 
 		pr_debug2("   [%d] injecting: %s\n", i+1, dso->name);
-		len += synthesize_mmap(data, dso, timestamp);
+		if (synthesize_mmap(data, dso, timestamp) < 0)
+			return -1;
 
-		for (k = 0; k < nr_samples; k++)
-			len += synthesize_sample(data, dso, timestamp + k * 1000);
+		for (k = 0; k < nr_samples; k++) {
+			if (synthesize_sample(data, dso, timestamp + k * 1000) < 0)
+				return -1;
+		}
 
-		if ((i + 1) % 10 == 0)
-			len += synthesize_flush(data);
+		if ((i + 1) % 10 == 0) {
+			if (synthesize_flush(data) < 0)
+				return -1;
+		}
 	}
 
 	/* this makes the child to finish */
diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c
index b2924e3181dc..05f7c923c745 100644
--- a/tools/perf/bench/synthesize.c
+++ b/tools/perf/bench/synthesize.c
@@ -117,7 +117,7 @@ static int run_single_threaded(void)
 	int err;
 
 	perf_set_singlethreaded();
-	session = perf_session__new(NULL, false, NULL);
+	session = perf_session__new(NULL, NULL);
 	if (IS_ERR(session)) {
 		pr_err("Session creation failed.\n");
 		return PTR_ERR(session);
@@ -161,7 +161,7 @@ static int do_run_multi_threaded(struct target *target,
 	init_stats(&time_stats);
 	init_stats(&event_stats);
 	for (i = 0; i < multi_iterations; i++) {
-		session = perf_session__new(NULL, false, NULL);
+		session = perf_session__new(NULL, NULL);
 		if (IS_ERR(session))
 			return PTR_ERR(session);