perf bench futex: Add --mlockall parameter

This adds, across all futex benchmarks, the -m/--mlockall option
which is a common operation for realtime workloads by not incurring
in page faults in paths that want determinism. As such, threads
started after a call to mlockall(2) will generate page faults
immediately since the new stack is immediately forced to memory,
due to the MCL_FUTURE flag.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lore.kernel.org/lkml/20210809043301.66002-5-dave@stgolabs.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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"
@@ -56,6 +57,7 @@ static const struct option options[] = {
 	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()
 };
 
@@ -142,6 +144,11 @@ int bench_futex_hash(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");
+	}
+
 	if (!params.nthreads) /* default to the number of CPUs */
 		params.nthreads = cpu->nr;
 

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;
@@ -48,6 +49,7 @@ static const struct option options[] = {
 	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()
 };
 
@@ -165,6 +167,11 @@ int bench_futex_lock_pi(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");
+	}
+
 	if (!params.nthreads)
 		params.nthreads = cpu->nr;
 

tools/perf/bench/futex-requeue.c

@@ -27,6 +27,7 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
+#include <sys/mman.h>
 
 static u_int32_t futex1 = 0, futex2 = 0;
 
@@ -51,6 +52,7 @@ static const struct option options[] = {
 	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_END()
 };
 
@@ -134,6 +136,11 @@ int bench_futex_requeue(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");
+	}
+
 	if (!params.nthreads)
 		params.nthreads = cpu->nr;
 

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;
@@ -62,6 +63,8 @@ static const struct option options[] = {
 	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()
 };
 
@@ -239,6 +242,11 @@ 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");

tools/perf/bench/futex-wake.c

@@ -27,6 +27,7 @@
 #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;
@@ -52,6 +53,8 @@ static const struct option options[] = {
 	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()
 };
 
@@ -142,6 +145,11 @@ int bench_futex_wake(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");
+	}
+
 	if (!params.nthreads)
 		params.nthreads = cpu->nr;
 

tools/perf/bench/futex.h

@@ -16,6 +16,7 @@
 struct bench_futex_parameters {
 	bool silent;
 	bool fshared;
+	bool mlockall;
 	bool multi; /* lock-pi */
 	unsigned int runtime; /* seconds*/
 	unsigned int nthreads;