4 files changed, 42 insertions, 54 deletions

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 8024cd5febd2..da04b8c5568a 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -63,8 +63,9 @@ static const char * const bench_futex_hash_usage[] = {
 static void *workerfn(void *arg)
 {
 	int ret;
-	unsigned int i;
 	struct worker *w = (struct worker *) arg;
+	unsigned int i;
+	unsigned long ops = w->ops; /* avoid cacheline bouncing */
 
 	pthread_mutex_lock(&thread_lock);
 	threads_starting--;
@@ -74,7 +75,7 @@ static void *workerfn(void *arg)
 	pthread_mutex_unlock(&thread_lock);
 
 	do {
-		for (i = 0; i < nfutexes; i++, w->ops++) {
+		for (i = 0; i < nfutexes; i++, ops++) {
 			/*
 			 * We want the futex calls to fail in order to stress
 			 * the hashing of uaddr and not measure other steps,
@@ -88,6 +89,7 @@ static void *workerfn(void *arg)
 		}
 	}  while (!done);
 
+	w->ops = ops;
 	return NULL;
 }
 
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 936d89d30483..91877777ec6e 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -48,7 +48,7 @@ static const struct option options[] = {
 };
 
 static const char * const bench_futex_lock_pi_usage[] = {
-	"perf bench futex requeue <options>",
+	"perf bench futex lock-pi <options>",
 	NULL
 };
 
@@ -75,6 +75,7 @@ static void toggle_done(int sig __maybe_unused,
 static void *workerfn(void *arg)
 {
 	struct worker *w = (struct worker *) arg;
+	unsigned long ops = w->ops;
 
 	pthread_mutex_lock(&thread_lock);
 	threads_starting--;
@@ -103,9 +104,10 @@ static void *workerfn(void *arg)
 		if (ret && !silent)
 			warn("thread %d: Could not unlock pi-lock for %p (%d)",
 			     w->tid, w->futex, ret);
-		w->ops++; /* account for thread's share of work */
+		ops++; /* account for thread's share of work */
 	}  while (!done);
 
+	w->ops = ops;
 	return NULL;
 }
 
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index c684910e5a48..52504a83b5a1 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -106,9 +106,10 @@ static double timeval2double(struct timeval *ts)
 
 struct bench_mem_info {
 	const struct function *functions;
-	u64 (*do_cycles)(const struct function *r, size_t size);
-	double (*do_gettimeofday)(const struct function *r, size_t size);
+	u64 (*do_cycles)(const struct function *r, size_t size, void *src, void *dst);
+	double (*do_gettimeofday)(const struct function *r, size_t size, void *src, void *dst);
 	const char *const *usage;
+	bool alloc_src;
 };
 
 static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t size, double size_total)
@@ -116,16 +117,26 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
 	const struct function *r = &info->functions[r_idx];
 	double result_bps = 0.0;
 	u64 result_cycles = 0;
+	void *src = NULL, *dst = zalloc(size);
 
 	printf("# function '%s' (%s)\n", r->name, r->desc);
 
+	if (dst == NULL)
+		goto out_alloc_failed;
+
+	if (info->alloc_src) {
+		src = zalloc(size);
+		if (src == NULL)
+			goto out_alloc_failed;
+	}
+
 	if (bench_format == BENCH_FORMAT_DEFAULT)
 		printf("# Copying %s bytes ...\n\n", size_str);
 
 	if (use_cycles) {
-		result_cycles = info->do_cycles(r, size);
+		result_cycles = info->do_cycles(r, size, src, dst);
 	} else {
-		result_bps = info->do_gettimeofday(r, size);
+		result_bps = info->do_gettimeofday(r, size, src, dst);
 	}
 
 	switch (bench_format) {
@@ -149,6 +160,14 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
 		BUG_ON(1);
 		break;
 	}
+
+out_free:
+	free(src);
+	free(dst);
+	return;
+out_alloc_failed:
+	printf("# Memory allocation failed - maybe size (%s) is too large?\n", size_str);
+	goto out_free;
 }
 
 static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *info)
@@ -201,28 +220,14 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 	return 0;
 }
 
-static void memcpy_alloc_mem(void **dst, void **src, size_t size)
-{
-	*dst = zalloc(size);
-	if (!*dst)
-		die("memory allocation failed - maybe size is too large?\n");
-
-	*src = zalloc(size);
-	if (!*src)
-		die("memory allocation failed - maybe size is too large?\n");
-
-	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
-	memset(*src, 0, size);
-}
-
-static u64 do_memcpy_cycles(const struct function *r, size_t size)
+static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
 {
 	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	void *src = NULL, *dst = NULL;
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	memcpy_alloc_mem(&dst, &src, size);
+	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
+	memset(src, 0, size);
 
 	/*
 	 * We prefault the freshly allocated memory range here,
@@ -235,20 +240,15 @@ static u64 do_memcpy_cycles(const struct function *r, size_t size)
 		fn(dst, src, size);
 	cycle_end = get_cycles();
 
-	free(src);
-	free(dst);
 	return cycle_end - cycle_start;
 }
 
-static double do_memcpy_gettimeofday(const struct function *r, size_t size)
+static double do_memcpy_gettimeofday(const struct function *r, size_t size, void *src, void *dst)
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	memcpy_t fn = r->fn.memcpy;
-	void *src = NULL, *dst = NULL;
 	int i;
 
-	memcpy_alloc_mem(&dst, &src, size);
-
 	/*
 	 * We prefault the freshly allocated memory range here,
 	 * to not measure page fault overhead:
@@ -262,9 +262,6 @@ static double do_memcpy_gettimeofday(const struct function *r, size_t size)
 
 	timersub(&tv_end, &tv_start, &tv_diff);
 
-	free(src);
-	free(dst);
-
 	return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
 }
 
@@ -294,27 +291,18 @@ int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unu
 		.do_cycles		= do_memcpy_cycles,
 		.do_gettimeofday	= do_memcpy_gettimeofday,
 		.usage			= bench_mem_memcpy_usage,
+		.alloc_src              = true,
 	};
 
 	return bench_mem_common(argc, argv, &info);
 }
 
-static void memset_alloc_mem(void **dst, size_t size)
-{
-	*dst = zalloc(size);
-	if (!*dst)
-		die("memory allocation failed - maybe size is too large?\n");
-}
-
-static u64 do_memset_cycles(const struct function *r, size_t size)
+static u64 do_memset_cycles(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
 {
 	u64 cycle_start = 0ULL, cycle_end = 0ULL;
 	memset_t fn = r->fn.memset;
-	void *dst = NULL;
 	int i;
 
-	memset_alloc_mem(&dst, size);
-
 	/*
 	 * We prefault the freshly allocated memory range here,
 	 * to not measure page fault overhead:
@@ -326,19 +314,15 @@ static u64 do_memset_cycles(const struct function *r, size_t size)
 		fn(dst, i, size);
 	cycle_end = get_cycles();
 
-	free(dst);
 	return cycle_end - cycle_start;
 }
 
-static double do_memset_gettimeofday(const struct function *r, size_t size)
+static double do_memset_gettimeofday(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	memset_t fn = r->fn.memset;
-	void *dst = NULL;
 	int i;
 
-	memset_alloc_mem(&dst, size);
-
 	/*
 	 * We prefault the freshly allocated memory range here,
 	 * to not measure page fault overhead:
@@ -352,7 +336,6 @@ static double do_memset_gettimeofday(const struct function *r, size_t size)
 
 	timersub(&tv_end, &tv_start, &tv_diff);
 
-	free(dst);
 	return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
 }
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904e486b..3083fc36282b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -43,6 +43,7 @@
 /*
  * Debug printf:
  */
+#undef dprintf
 #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
 
 struct thread_data {
@@ -1573,13 +1574,13 @@ static int __bench_numa(const char *name)
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
 	if (g->p.show_details >= 2) {
-		char tname[32];
+		char tname[14 + 2 * 10 + 1];
 		struct thread_data *td;
 		for (p = 0; p < g->p.nr_proc; p++) {
 			for (t = 0; t < g->p.nr_threads; t++) {
-				memset(tname, 0, 32);
+				memset(tname, 0, sizeof(tname));
 				td = g->threads + p*g->p.nr_threads + t;
-				snprintf(tname, 32, "process%d:thread%d", p, t);
+				snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
 				print_res(tname, td->speed_gbs,
 					"GB/sec",	"thread-speed", "GB/sec/thread speed");
 				print_res(tname, td->system_time_ns / NSEC_PER_SEC,