1 files changed, 35 insertions, 11 deletions

diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index b4732dad9f89..69d8fdc87315 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,7 +7,17 @@
  * for each individual thread to service its share of work. Ultimately
  * it can be used to measure futex_wake() changes.
  */
+#include "bench.h"
+#include <linux/compiler.h>
+#include "../util/debug.h"
 
+#ifndef HAVE_PTHREAD_BARRIER
+int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+        pr_err("%s: pthread_barrier_t unavailable, disabling this test...\n", __func__);
+        return 0;
+}
+#else /* HAVE_PTHREAD_BARRIER */
 /* For the CLR_() macros */
 #include <string.h>
 #include <pthread.h>
@@ -15,12 +25,11 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
-#include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -42,8 +51,9 @@ static bool done = false, silent = false, fshared = false;
 static unsigned int nblocked_threads = 0, nwaking_threads = 0;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
+static pthread_barrier_t barrier;
 static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting;
+static unsigned int threads_starting;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -64,6 +74,8 @@ static void *waking_workerfn(void *arg)
         struct thread_data *waker = (struct thread_data *) arg;
         struct timeval start, end;
 
+        pthread_barrier_wait(&barrier);
+
         gettimeofday(&start, NULL);
 
         waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
@@ -84,6 +96,8 @@ 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);
+
         /* create and block all threads */
         for (i = 0; i < nwaking_threads; i++) {
                 /*
@@ -96,9 +110,13 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
                         err(EXIT_FAILURE, "pthread_create");
         }
 
+        pthread_barrier_wait(&barrier);
+
         for (i = 0; i < nwaking_threads; i++)
                 if (pthread_join(td[i].worker, NULL))
                         err(EXIT_FAILURE, "pthread_join");
+
+        pthread_barrier_destroy(&barrier);
 }
 
 static void *blocked_workerfn(void *arg __maybe_unused)
@@ -119,19 +137,20 @@ static void *blocked_workerfn(void *arg __maybe_unused)
         return NULL;
 }
 
-static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
+                          struct cpu_map *cpu)
 {
-        cpu_set_t cpu;
+        cpu_set_t cpuset;
         unsigned int i;
 
         threads_starting = nblocked_threads;
 
         /* create and block all threads */
         for (i = 0; i < nblocked_threads; i++) {
-                CPU_ZERO(&cpu);
-                CPU_SET(i % ncpus, &cpu);
+                CPU_ZERO(&cpuset);
+                CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
                         err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
                 if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
@@ -205,6 +224,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
         struct sigaction act;
         pthread_attr_t thread_attr;
         struct thread_data *waking_worker;
+        struct cpu_map *cpu;
 
         argc = parse_options(argc, argv, options,
                              bench_futex_wake_parallel_usage, 0);
@@ -217,9 +237,12 @@ int bench_futex_wake_parallel(int argc, const char **argv)
         act.sa_sigaction = toggle_done;
         sigaction(SIGINT, &act, NULL);
 
-        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+        cpu = cpu_map__new(NULL);
+        if (!cpu)
+                err(EXIT_FAILURE, "calloc");
+
         if (!nblocked_threads)
-                nblocked_threads = ncpus;
+                nblocked_threads = cpu->nr;
 
         /* some sanity checks */
         if (nwaking_threads > nblocked_threads || !nwaking_threads)
@@ -259,7 +282,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
                         err(EXIT_FAILURE, "calloc");
 
                 /* create, launch & block all threads */
-                block_threads(blocked_worker, thread_attr);
+                block_threads(blocked_worker, thread_attr, cpu);
 
                 /* make sure all threads are already blocked */
                 pthread_mutex_lock(&thread_lock);
@@ -297,3 +320,4 @@ int bench_futex_wake_parallel(int argc, const char **argv)
         free(blocked_worker);
         return ret;
 }
+#endif /* HAVE_PTHREAD_BARRIER */