forked from Minki/linux
a64d3af5d9
Switch to the use of mutex wrappers that provide better error checking. Signed-off-by: Ian Rogers <irogers@google.com> Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Truong <alexandre.truong@arm.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andres Freund <andres@anarazel.de> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: André Almeida <andrealmeid@igalia.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Cc: Colin Ian King <colin.king@intel.com> Cc: Dario Petrillo <dario.pk1@gmail.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Dave Marchevsky <davemarchevsky@fb.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Fangrui Song <maskray@google.com> Cc: Hewenliang <hewenliang4@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jason Wang <wangborong@cdjrlc.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin Liška <mliska@suse.cz> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Pavithra Gurushankar <gpavithrasha@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Quentin Monnet <quentin@isovalent.com> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Remi Bernon <rbernon@codeweavers.com> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tom Rix <trix@redhat.com> Cc: Weiguo Li <liwg06@foxmail.com> Cc: Wenyu Liu <liuwenyu7@huawei.com> Cc: William Cohen <wcohen@redhat.com> Cc: Zechuan Chen <chenzechuan1@huawei.com> Cc: bpf@vger.kernel.org Cc: llvm@lists.linux.dev Cc: yaowenbin <yaowenbin1@huawei.com> Link: https://lore.kernel.org/r/20220826164242.43412-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
254 lines
6.1 KiB
C
254 lines
6.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2015 Davidlohr Bueso.
|
|
*/
|
|
|
|
/* For the CLR_() macros */
|
|
#include <string.h>
|
|
#include <pthread.h>
|
|
|
|
#include <signal.h>
|
|
#include "../util/mutex.h"
|
|
#include "../util/stat.h"
|
|
#include <subcmd/parse-options.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/zalloc.h>
|
|
#include <errno.h>
|
|
#include <perf/cpumap.h>
|
|
#include "bench.h"
|
|
#include "futex.h"
|
|
|
|
#include <err.h>
|
|
#include <stdlib.h>
|
|
#include <sys/time.h>
|
|
#include <sys/mman.h>
|
|
|
|
struct worker {
|
|
int tid;
|
|
u_int32_t *futex;
|
|
pthread_t thread;
|
|
unsigned long ops;
|
|
};
|
|
|
|
static u_int32_t global_futex = 0;
|
|
static struct worker *worker;
|
|
static bool done = false;
|
|
static int futex_flag = 0;
|
|
static struct mutex thread_lock;
|
|
static unsigned int threads_starting;
|
|
static struct stats throughput_stats;
|
|
static struct cond thread_parent, thread_worker;
|
|
|
|
static struct bench_futex_parameters params = {
|
|
.runtime = 10,
|
|
};
|
|
|
|
static const struct option options[] = {
|
|
OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"),
|
|
OPT_UINTEGER('r', "runtime", ¶ms.runtime, "Specify runtime (in seconds)"),
|
|
OPT_BOOLEAN( 'M', "multi", ¶ms.multi, "Use multiple futexes"),
|
|
OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
|
|
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
|
|
OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
|
|
OPT_END()
|
|
};
|
|
|
|
static const char * const bench_futex_lock_pi_usage[] = {
|
|
"perf bench futex lock-pi <options>",
|
|
NULL
|
|
};
|
|
|
|
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",
|
|
!params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
|
|
(int)bench__runtime.tv_sec);
|
|
}
|
|
|
|
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(&bench__end, NULL);
|
|
timersub(&bench__end, &bench__start, &bench__runtime);
|
|
}
|
|
|
|
static void *workerfn(void *arg)
|
|
{
|
|
struct worker *w = (struct worker *) arg;
|
|
unsigned long ops = w->ops;
|
|
|
|
mutex_lock(&thread_lock);
|
|
threads_starting--;
|
|
if (!threads_starting)
|
|
cond_signal(&thread_parent);
|
|
cond_wait(&thread_worker, &thread_lock);
|
|
mutex_unlock(&thread_lock);
|
|
|
|
do {
|
|
int ret;
|
|
again:
|
|
ret = futex_lock_pi(w->futex, NULL, futex_flag);
|
|
|
|
if (ret) { /* handle lock acquisition */
|
|
if (!params.silent)
|
|
warn("thread %d: Could not lock pi-lock for %p (%d)",
|
|
w->tid, w->futex, ret);
|
|
if (done)
|
|
break;
|
|
|
|
goto again;
|
|
}
|
|
|
|
usleep(1);
|
|
ret = futex_unlock_pi(w->futex, futex_flag);
|
|
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 */
|
|
} while (!done);
|
|
|
|
w->ops = ops;
|
|
return NULL;
|
|
}
|
|
|
|
static void create_threads(struct worker *w, pthread_attr_t thread_attr,
|
|
struct perf_cpu_map *cpu)
|
|
{
|
|
cpu_set_t *cpuset;
|
|
unsigned int i;
|
|
int nrcpus = perf_cpu_map__nr(cpu);
|
|
size_t size;
|
|
|
|
threads_starting = params.nthreads;
|
|
|
|
cpuset = CPU_ALLOC(nrcpus);
|
|
BUG_ON(!cpuset);
|
|
size = CPU_ALLOC_SIZE(nrcpus);
|
|
|
|
for (i = 0; i < params.nthreads; i++) {
|
|
worker[i].tid = i;
|
|
|
|
if (params.multi) {
|
|
worker[i].futex = calloc(1, sizeof(u_int32_t));
|
|
if (!worker[i].futex)
|
|
err(EXIT_FAILURE, "calloc");
|
|
} else
|
|
worker[i].futex = &global_futex;
|
|
|
|
CPU_ZERO_S(size, cpuset);
|
|
CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
|
|
|
|
if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
|
|
CPU_FREE(cpuset);
|
|
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
|
|
}
|
|
|
|
if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) {
|
|
CPU_FREE(cpuset);
|
|
err(EXIT_FAILURE, "pthread_create");
|
|
}
|
|
}
|
|
CPU_FREE(cpuset);
|
|
}
|
|
|
|
int bench_futex_lock_pi(int argc, const char **argv)
|
|
{
|
|
int ret = 0;
|
|
unsigned int i;
|
|
struct sigaction act;
|
|
pthread_attr_t thread_attr;
|
|
struct perf_cpu_map *cpu;
|
|
|
|
argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
|
|
if (argc)
|
|
goto err;
|
|
|
|
cpu = perf_cpu_map__new(NULL);
|
|
if (!cpu)
|
|
err(EXIT_FAILURE, "calloc");
|
|
|
|
memset(&act, 0, sizeof(act));
|
|
sigfillset(&act.sa_mask);
|
|
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 = perf_cpu_map__nr(cpu);
|
|
|
|
worker = calloc(params.nthreads, sizeof(*worker));
|
|
if (!worker)
|
|
err(EXIT_FAILURE, "calloc");
|
|
|
|
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(), params.nthreads, params.runtime);
|
|
|
|
init_stats(&throughput_stats);
|
|
mutex_init(&thread_lock);
|
|
cond_init(&thread_parent);
|
|
cond_init(&thread_worker);
|
|
|
|
threads_starting = params.nthreads;
|
|
pthread_attr_init(&thread_attr);
|
|
gettimeofday(&bench__start, NULL);
|
|
|
|
create_threads(worker, thread_attr, cpu);
|
|
pthread_attr_destroy(&thread_attr);
|
|
|
|
mutex_lock(&thread_lock);
|
|
while (threads_starting)
|
|
cond_wait(&thread_parent, &thread_lock);
|
|
cond_broadcast(&thread_worker);
|
|
mutex_unlock(&thread_lock);
|
|
|
|
sleep(params.runtime);
|
|
toggle_done(0, NULL, NULL);
|
|
|
|
for (i = 0; i < params.nthreads; i++) {
|
|
ret = pthread_join(worker[i].thread, NULL);
|
|
if (ret)
|
|
err(EXIT_FAILURE, "pthread_join");
|
|
}
|
|
|
|
/* cleanup & report results */
|
|
cond_destroy(&thread_parent);
|
|
cond_destroy(&thread_worker);
|
|
mutex_destroy(&thread_lock);
|
|
|
|
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 (!params.silent)
|
|
printf("[thread %3d] futex: %p [ %ld ops/sec ]\n",
|
|
worker[i].tid, worker[i].futex, t);
|
|
|
|
if (params.multi)
|
|
zfree(&worker[i].futex);
|
|
}
|
|
|
|
print_summary();
|
|
|
|
free(worker);
|
|
perf_cpu_map__put(cpu);
|
|
return ret;
|
|
err:
|
|
usage_with_options(bench_futex_lock_pi_usage, options);
|
|
exit(EXIT_FAILURE);
|
|
}
|