10 files changed, 491 insertions, 36 deletions

diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
index 6eeeed2913e6..5bcb8a8cdeb2 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
@@ -63,29 +63,34 @@ static const struct argp_option opts[] = {
 
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
 {
+	long ret;
+
 	switch (key) {
 	case ARG_NR_ENTRIES:
-		args.nr_entries = strtol(arg, NULL, 10);
-		if (args.nr_entries == 0) {
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
 			fprintf(stderr, "Invalid nr_entries count.");
 			argp_usage(state);
 		}
+		args.nr_entries = ret;
 		break;
 	case ARG_NR_HASH_FUNCS:
-		args.nr_hash_funcs = strtol(arg, NULL, 10);
-		if (args.nr_hash_funcs == 0 || args.nr_hash_funcs > 15) {
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > 15) {
 			fprintf(stderr,
 				"The bloom filter must use 1 to 15 hash functions.");
 			argp_usage(state);
 		}
+		args.nr_hash_funcs = ret;
 		break;
 	case ARG_VALUE_SIZE:
-		args.value_size = strtol(arg, NULL, 10);
-		if (args.value_size < 2 || args.value_size > 256) {
+		ret = strtol(arg, NULL, 10);
+		if (ret < 2 || ret > 256) {
 			fprintf(stderr,
 				"Invalid value size. Must be between 2 and 256 bytes");
 			argp_usage(state);
 		}
+		args.value_size = ret;
 		break;
 	default:
 		return ARGP_ERR_UNKNOWN;
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
new file mode 100644
index 000000000000..d0a6572bfab6
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <argp.h>
+#include "bench.h"
+#include "bpf_loop_bench.skel.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+	struct bpf_loop_bench *skel;
+} ctx;
+
+static struct {
+	__u32 nr_loops;
+} args = {
+	.nr_loops = 10,
+};
+
+enum {
+	ARG_NR_LOOPS = 4000,
+};
+
+static const struct argp_option opts[] = {
+	{ "nr_loops", ARG_NR_LOOPS, "nr_loops", 0,
+		"Set number of loops for the bpf_loop helper"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_NR_LOOPS:
+		args.nr_loops = strtol(arg, NULL, 10);
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_bpf_loop_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+}
+
+static void *producer(void *input)
+{
+	while (true)
+		/* trigger the bpf program */
+		syscall(__NR_getpgid);
+
+	return NULL;
+}
+
+static void *consumer(void *input)
+{
+	return NULL;
+}
+
+static void measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+static void setup(void)
+{
+	struct bpf_link *link;
+
+	setup_libbpf();
+
+	ctx.skel = bpf_loop_bench__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx.skel->progs.benchmark);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+
+	ctx.skel->bss->nr_loops = args.nr_loops;
+}
+
+const struct bench bench_bpf_loop = {
+	.name = "bpf-loop",
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c
index befba7a82643..078972ce208e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_count.c
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@@ -36,7 +36,7 @@ static struct count_local_ctx {
 	struct counter *hits;
 } count_local_ctx;
 
-static void count_local_setup()
+static void count_local_setup(void)
 {
 	struct count_local_ctx *ctx = &count_local_ctx;
 
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
index c7ec114eca56..3c203b6d6a6e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_rename.c
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -11,7 +11,7 @@ static struct ctx {
 	int fd;
 } ctx;
 
-static void validate()
+static void validate(void)
 {
 	if (env.producer_cnt != 1) {
 		fprintf(stderr, "benchmark doesn't support multi-producer!\n");
@@ -43,7 +43,7 @@ static void measure(struct bench_res *res)
 	res->hits = atomic_swap(&ctx.hits.value, 0);
 }
 
-static void setup_ctx()
+static void setup_ctx(void)
 {
 	setup_libbpf();
 
@@ -71,36 +71,36 @@ static void attach_bpf(struct bpf_program *prog)
 	}
 }
 
-static void setup_base()
+static void setup_base(void)
 {
 	setup_ctx();
 }
 
-static void setup_kprobe()
+static void setup_kprobe(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog1);
 }
 
-static void setup_kretprobe()
+static void setup_kretprobe(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog2);
 }
 
-static void setup_rawtp()
+static void setup_rawtp(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog3);
 }
 
-static void setup_fentry()
+static void setup_fentry(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog4);
 }
 
-static void setup_fexit()
+static void setup_fexit(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog5);
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index d167bffac679..da8593b3494a 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -88,12 +88,12 @@ const struct argp bench_ringbufs_argp = {
 
 static struct counter buf_hits;
 
-static inline void bufs_trigger_batch()
+static inline void bufs_trigger_batch(void)
 {
 	(void)syscall(__NR_getpgid);
 }
 
-static void bufs_validate()
+static void bufs_validate(void)
 {
 	if (env.consumer_cnt != 1) {
 		fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
@@ -132,7 +132,7 @@ static void ringbuf_libbpf_measure(struct bench_res *res)
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }
 
-static struct ringbuf_bench *ringbuf_setup_skeleton()
+static struct ringbuf_bench *ringbuf_setup_skeleton(void)
 {
 	struct ringbuf_bench *skel;
 
@@ -167,7 +167,7 @@ static int buf_process_sample(void *ctx, void *data, size_t len)
 	return 0;
 }
 
-static void ringbuf_libbpf_setup()
+static void ringbuf_libbpf_setup(void)
 {
 	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
 	struct bpf_link *link;
@@ -223,7 +223,7 @@ static void ringbuf_custom_measure(struct bench_res *res)
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }
 
-static void ringbuf_custom_setup()
+static void ringbuf_custom_setup(void)
 {
 	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
 	const size_t page_size = getpagesize();
@@ -352,7 +352,7 @@ static void perfbuf_measure(struct bench_res *res)
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }
 
-static struct perfbuf_bench *perfbuf_setup_skeleton()
+static struct perfbuf_bench *perfbuf_setup_skeleton(void)
 {
 	struct perfbuf_bench *skel;
 
@@ -390,15 +390,10 @@ perfbuf_process_sample_raw(void *input_ctx, int cpu,
 	return LIBBPF_PERF_EVENT_CONT;
 }
 
-static void perfbuf_libbpf_setup()
+static void perfbuf_libbpf_setup(void)
 {
 	struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
 	struct perf_event_attr attr;
-	struct perf_buffer_raw_opts pb_opts = {
-		.event_cb = perfbuf_process_sample_raw,
-		.ctx = (void *)(long)0,
-		.attr = &attr,
-	};
 	struct bpf_link *link;
 
 	ctx->skel = perfbuf_setup_skeleton();
@@ -423,7 +418,8 @@ static void perfbuf_libbpf_setup()
 	}
 
 	ctx->perfbuf = perf_buffer__new_raw(bpf_map__fd(ctx->skel->maps.perfbuf),
-					    args.perfbuf_sz, &pb_opts);
+					    args.perfbuf_sz, &attr,
+					    perfbuf_process_sample_raw, NULL, NULL);
 	if (!ctx->perfbuf) {
 		fprintf(stderr, "failed to create perfbuf\n");
 		exit(1);
diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
new file mode 100644
index 000000000000..494b591c0289
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <argp.h>
+#include "bench.h"
+#include "strncmp_bench.skel.h"
+
+static struct strncmp_ctx {
+	struct strncmp_bench *skel;
+} ctx;
+
+static struct strncmp_args {
+	u32 cmp_str_len;
+} args = {
+	.cmp_str_len = 32,
+};
+
+enum {
+	ARG_CMP_STR_LEN = 5000,
+};
+
+static const struct argp_option opts[] = {
+	{ "cmp-str-len", ARG_CMP_STR_LEN, "CMP_STR_LEN", 0,
+	  "Set the length of compared string" },
+	{},
+};
+
+static error_t strncmp_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_CMP_STR_LEN:
+		args.cmp_str_len = strtoul(arg, NULL, 10);
+		if (!args.cmp_str_len ||
+		    args.cmp_str_len >= sizeof(ctx.skel->bss->str)) {
+			fprintf(stderr, "Invalid cmp str len (limit %zu)\n",
+				sizeof(ctx.skel->bss->str));
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_strncmp_argp = {
+	.options = opts,
+	.parser = strncmp_parse_arg,
+};
+
+static void strncmp_validate(void)
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "strncmp benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+}
+
+static void strncmp_setup(void)
+{
+	int err;
+	char *target;
+	size_t i, sz;
+
+	sz = sizeof(ctx.skel->rodata->target);
+	if (!sz || sz < sizeof(ctx.skel->bss->str)) {
+		fprintf(stderr, "invalid string size (target %zu, src %zu)\n",
+			sz, sizeof(ctx.skel->bss->str));
+		exit(1);
+	}
+
+	setup_libbpf();
+
+	ctx.skel = strncmp_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	srandom(time(NULL));
+	target = ctx.skel->rodata->target;
+	for (i = 0; i < sz - 1; i++)
+		target[i] = '1' + random() % 9;
+	target[sz - 1] = '\0';
+
+	ctx.skel->rodata->cmp_str_len = args.cmp_str_len;
+
+	memcpy(ctx.skel->bss->str, target, args.cmp_str_len);
+	ctx.skel->bss->str[args.cmp_str_len] = '\0';
+	/* Make bss->str < rodata->target */
+	ctx.skel->bss->str[args.cmp_str_len - 1] -= 1;
+
+	err = strncmp_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		strncmp_bench__destroy(ctx.skel);
+		exit(1);
+	}
+}
+
+static void strncmp_attach_prog(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(prog);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void strncmp_no_helper_setup(void)
+{
+	strncmp_setup();
+	strncmp_attach_prog(ctx.skel->progs.strncmp_no_helper);
+}
+
+static void strncmp_helper_setup(void)
+{
+	strncmp_setup();
+	strncmp_attach_prog(ctx.skel->progs.strncmp_helper);
+}
+
+static void *strncmp_producer(void *ctx)
+{
+	while (true)
+		(void)syscall(__NR_getpgid);
+	return NULL;
+}
+
+static void *strncmp_consumer(void *ctx)
+{
+	return NULL;
+}
+
+static void strncmp_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+const struct bench bench_strncmp_no_helper = {
+	.name = "strncmp-no-helper",
+	.validate = strncmp_validate,
+	.setup = strncmp_no_helper_setup,
+	.producer_thread = strncmp_producer,
+	.consumer_thread = strncmp_consumer,
+	.measure = strncmp_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_strncmp_helper = {
+	.name = "strncmp-helper",
+	.validate = strncmp_validate,
+	.setup = strncmp_helper_setup,
+	.producer_thread = strncmp_producer,
+	.consumer_thread = strncmp_consumer,
+	.measure = strncmp_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index f41a491a8cc0..7f957c55a3ca 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 #include "bench.h"
 #include "trigger_bench.skel.h"
+#include "trace_helpers.h"
 
 /* BPF triggering benchmarks */
 static struct trigger_ctx {
@@ -10,7 +11,7 @@ static struct trigger_ctx {
 
 static struct counter base_hits;
 
-static void trigger_validate()
+static void trigger_validate(void)
 {
 	if (env.consumer_cnt != 1) {
 		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
@@ -44,7 +45,7 @@ static void trigger_measure(struct bench_res *res)
 	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
 }
 
-static void setup_ctx()
+static void setup_ctx(void)
 {
 	setup_libbpf();
 
@@ -66,37 +67,37 @@ static void attach_bpf(struct bpf_program *prog)
 	}
 }
 
-static void trigger_tp_setup()
+static void trigger_tp_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_tp);
 }
 
-static void trigger_rawtp_setup()
+static void trigger_rawtp_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_raw_tp);
 }
 
-static void trigger_kprobe_setup()
+static void trigger_kprobe_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
 }
 
-static void trigger_fentry_setup()
+static void trigger_fentry_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry);
 }
 
-static void trigger_fentry_sleep_setup()
+static void trigger_fentry_sleep_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep);
 }
 
-static void trigger_fmodret_setup()
+static void trigger_fmodret_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
@@ -107,6 +108,101 @@ static void *trigger_consumer(void *input)
 	return NULL;
 }
 
+/* make sure call is not inlined and not avoided by compiler, so __weak and
+ * inline asm volatile in the body of the function
+ *
+ * There is a performance difference between uprobing at nop location vs other
+ * instructions. So use two different targets, one of which starts with nop
+ * and another doesn't.
+ *
+ * GCC doesn't generate stack setup preample for these functions due to them
+ * having no input arguments and doing nothing in the body.
+ */
+__weak void uprobe_target_with_nop(void)
+{
+	asm volatile ("nop");
+}
+
+__weak void uprobe_target_without_nop(void)
+{
+	asm volatile ("");
+}
+
+static void *uprobe_base_producer(void *input)
+{
+	while (true) {
+		uprobe_target_with_nop();
+		atomic_inc(&base_hits.value);
+	}
+	return NULL;
+}
+
+static void *uprobe_producer_with_nop(void *input)
+{
+	while (true)
+		uprobe_target_with_nop();
+	return NULL;
+}
+
+static void *uprobe_producer_without_nop(void *input)
+{
+	while (true)
+		uprobe_target_without_nop();
+	return NULL;
+}
+
+static void usetup(bool use_retprobe, bool use_nop)
+{
+	size_t uprobe_offset;
+	ssize_t base_addr;
+	struct bpf_link *link;
+
+	setup_libbpf();
+
+	ctx.skel = trigger_bench__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	base_addr = get_base_addr();
+	if (use_nop)
+		uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr);
+	else
+		uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr);
+
+	link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
+					  use_retprobe,
+					  -1 /* all PIDs */,
+					  "/proc/self/exe",
+					  uprobe_offset);
+	if (!link) {
+		fprintf(stderr, "failed to attach uprobe!\n");
+		exit(1);
+	}
+	ctx.skel->links.bench_trigger_uprobe = link;
+}
+
+static void uprobe_setup_with_nop(void)
+{
+	usetup(false, true);
+}
+
+static void uretprobe_setup_with_nop(void)
+{
+	usetup(true, true);
+}
+
+static void uprobe_setup_without_nop(void)
+{
+	usetup(false, false);
+}
+
+static void uretprobe_setup_without_nop(void)
+{
+	usetup(true, false);
+}
+
 const struct bench bench_trig_base = {
 	.name = "trig-base",
 	.validate = trigger_validate,
@@ -182,3 +278,53 @@ const struct bench bench_trig_fmodret = {
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
+
+const struct bench bench_trig_uprobe_base = {
+	.name = "trig-uprobe-base",
+	.setup = NULL, /* no uprobe/uretprobe is attached */
+	.producer_thread = uprobe_base_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_base_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uprobe_with_nop = {
+	.name = "trig-uprobe-with-nop",
+	.setup = uprobe_setup_with_nop,
+	.producer_thread = uprobe_producer_with_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uretprobe_with_nop = {
+	.name = "trig-uretprobe-with-nop",
+	.setup = uretprobe_setup_with_nop,
+	.producer_thread = uprobe_producer_with_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uprobe_without_nop = {
+	.name = "trig-uprobe-without-nop",
+	.setup = uprobe_setup_without_nop,
+	.producer_thread = uprobe_producer_without_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uretprobe_without_nop = {
+	.name = "trig-uretprobe-without-nop",
+	.setup = uretprobe_setup_without_nop,
+	.producer_thread = uprobe_producer_without_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh
new file mode 100755
index 000000000000..d4f5f73b356b
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+for t in 1 4 8 12 16; do
+for i in 10 100 500 1000 5000 10000 50000 100000 500000 1000000; do
+subtitle "nr_loops: $i, nr_threads: $t"
+	summarize_ops "bpf_loop: " \
+	    "$($RUN_BENCH -p $t --nr_loops $i bpf-loop)"
+	printf "\n"
+done
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh b/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh
new file mode 100755
index 000000000000..142697284b45
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+for s in 1 8 64 512 2048 4095; do
+	for b in no-helper helper; do
+		summarize ${b}-${s} "$($RUN_BENCH --cmp-str-len=$s strncmp-${b})"
+	done
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_common.sh b/tools/testing/selftests/bpf/benchs/run_common.sh
index 9a16be78b180..6c5e6023a69f 100644
--- a/tools/testing/selftests/bpf/benchs/run_common.sh
+++ b/tools/testing/selftests/bpf/benchs/run_common.sh
@@ -33,6 +33,14 @@ function percentage()
 	echo "$*" | sed -E "s/.*Percentage\s=\s+([0-9]+\.[0-9]+).*/\1/"
 }
 
+function ops()
+{
+	echo -n "throughput: "
+	echo -n "$*" | sed -E "s/.*throughput\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+\sM\sops\/s).*/\1/"
+	echo -n -e ", latency: "
+	echo "$*" | sed -E "s/.*latency\s+([0-9]+\.[0-9]+\sns\/op).*/\1/"
+}
+
 function total()
 {
 	echo "$*" | sed -E "s/.*total operations\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
@@ -52,6 +60,13 @@ function summarize_percentage()
 	printf "%-20s %s%%\n" "$bench" "$(percentage $summary)"
 }
 
+function summarize_ops()
+{
+	bench="$1"
+	summary=$(echo $2 | tail -n1)
+	printf "%-20s %s\n" "$bench" "$(ops $summary)"
+}
+
 function summarize_total()
 {
 	bench="$1"