perf bench mem: Move mem op parameters into a structure

Move benchmark function parameters in struct bench_params.

Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250917152418.4077386-4-ankur.a.arora@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: terminus

tools/perf/bench/mem-functions.c

@@ -30,7 +30,7 @@
 
 static const char	*size_str	= "1MB";
 static const char	*function_str	= "all";
-static int		nr_loops	= 1;
+static unsigned int	nr_loops	= 1;
 static bool		use_cycles;
 static int		cycles_fd;
 
@@ -42,7 +42,7 @@ static const struct option options[] = {
 	OPT_STRING('f', "function", &function_str, "all",
 		    "Specify the function to run, \"all\" runs all available functions, \"help\" lists them"),
 
-	OPT_INTEGER('l', "nr_loops", &nr_loops,
+	OPT_UINTEGER('l', "nr_loops", &nr_loops,
 		    "Specify the number of loops to run. (default: 1)"),
 
 	OPT_BOOLEAN('c', "cycles", &use_cycles,
@@ -56,6 +56,12 @@ union bench_clock {
 	struct timeval	tv;
 };
 
+struct bench_params {
+	size_t		size;
+	size_t		size_total;
+	unsigned int	nr_loops;
+};
+
 typedef void *(*memcpy_t)(void *, const void *, size_t);
 typedef void *(*memset_t)(void *, int, size_t);
 
@@ -134,49 +140,51 @@ static double timeval2double(struct timeval *ts)
 
 struct bench_mem_info {
 	const struct function *functions;
-	union bench_clock (*do_op)(const struct function *r, size_t size, void *src, void *dst);
+	union bench_clock (*do_op)(const struct function *r, struct bench_params *p,
+				   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, size_t size_total)
+static void __bench_mem_function(struct bench_mem_info *info, struct bench_params *p,
+				 int r_idx)
 {
 	const struct function *r = &info->functions[r_idx];
 	double result_bps = 0.0;
 	union bench_clock rt = { 0 };
-	void *src = NULL, *dst = zalloc(size);
+	void *src = NULL, *dst = zalloc(p->size);
 
 	printf("# function '%s' (%s)\n", r->name, r->desc);
 
 	if (dst == NULL)
 		goto out_alloc_failed;
 
 	if (info->alloc_src) {
-		src = zalloc(size);
+		src = zalloc(p->size);
 		if (src == NULL)
 			goto out_alloc_failed;
 	}
 
 	if (bench_format == BENCH_FORMAT_DEFAULT)
 		printf("# Copying %s bytes ...\n\n", size_str);
 
-	rt = info->do_op(r, size, src, dst);
+	rt = info->do_op(r, p, src, dst);
 
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
 		if (use_cycles) {
-			printf(" %14lf cycles/byte\n", (double)rt.cycles/(double)size_total);
+			printf(" %14lf cycles/byte\n", (double)rt.cycles/(double)p->size_total);
 		} else {
-			result_bps = (double)size_total/timeval2double(&rt.tv);
+			result_bps = (double)p->size_total/timeval2double(&rt.tv);
 			print_bps(result_bps);
 		}
 		break;
 
 	case BENCH_FORMAT_SIMPLE:
 		if (use_cycles) {
-			printf("%lf\n", (double)rt.cycles/(double)size_total);
+			printf("%lf\n", (double)rt.cycles/(double)p->size_total);
 		} else {
-			result_bps = (double)size_total/timeval2double(&rt.tv);
+			result_bps = (double)p->size_total/timeval2double(&rt.tv);
 			printf("%lf\n", result_bps);
 		}
 		break;
@@ -198,8 +206,7 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
 static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *info)
 {
 	int i;
-	size_t size;
-	size_t size_total;
+	struct bench_params p = { 0 };
 
 	argc = parse_options(argc, argv, options, info->usage, 0);
 
@@ -211,17 +218,18 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 		}
 	}
 
-	size = (size_t)perf_atoll((char *)size_str);
-	size_total = size * nr_loops;
+	p.nr_loops = nr_loops;
+	p.size = (size_t)perf_atoll((char *)size_str);
 
-	if ((s64)size <= 0) {
+	if ((s64)p.size <= 0) {
 		fprintf(stderr, "Invalid size:%s\n", size_str);
 		return 1;
 	}
+	p.size_total = p.size * p.nr_loops;
 
 	if (!strncmp(function_str, "all", 3)) {
 		for (i = 0; info->functions[i].name; i++)
-			__bench_mem_function(info, i, size, size_total);
+			__bench_mem_function(info, &p, i);
 		return 0;
 	}
 
@@ -240,7 +248,7 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 		return 1;
 	}
 
-	__bench_mem_function(info, i, size, size_total);
+	__bench_mem_function(info, &p, i);
 
 	return 0;
 }
@@ -257,18 +265,17 @@ static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst)
 	fn(dst, src, size);
 }
 
-static union bench_clock do_memcpy(const struct function *r, size_t size,
+static union bench_clock do_memcpy(const struct function *r, struct bench_params *p,
 				   void *src, void *dst)
 {
 	union bench_clock start, end;
 	memcpy_t fn = r->fn.memcpy;
-	int i;
 
-	memcpy_prefault(fn, size, src, dst);
+	memcpy_prefault(fn, p->size, src, dst);
 
 	clock_get(&start);
-	for (i = 0; i < nr_loops; ++i)
-		fn(dst, src, size);
+	for (unsigned int i = 0; i < p->nr_loops; ++i)
+		fn(dst, src, p->size);
 	clock_get(&end);
 
 	return clock_diff(&start, &end);
@@ -305,22 +312,21 @@ int bench_mem_memcpy(int argc, const char **argv)
 	return bench_mem_common(argc, argv, &info);
 }
 
-static union bench_clock do_memset(const struct function *r, size_t size,
+static union bench_clock do_memset(const struct function *r, struct bench_params *p,
 				   void *src __maybe_unused, void *dst)
 {
 	union bench_clock start, end;
 	memset_t fn = r->fn.memset;
-	int i;
 
 	/*
 	 * We prefault the freshly allocated memory range here,
 	 * to not measure page fault overhead:
 	 */
-	fn(dst, -1, size);
+	fn(dst, -1, p->size);
 
 	clock_get(&start);
-	for (i = 0; i < nr_loops; ++i)
-		fn(dst, i, size);
+	for (unsigned int i = 0; i < p->nr_loops; ++i)
+		fn(dst, i, p->size);
 	clock_get(&end);
 
 	return clock_diff(&start, &end);