selftests/bpf: Add benchmark for bpf_strncmp() helper

Add benchmark to compare the performance between home-made strncmp()
in bpf program and bpf_strncmp() helper. In summary, the performance
win of bpf_strncmp() under x86-64 is greater than 18% when the compared
string length is greater than 64, and is 179% when the length is 4095.
Under arm64 the performance win is even bigger: 33% when the length
is greater than 64 and 600% when the length is 4095.

The following is the details:

no-helper-X: use home-made strncmp() to compare X-sized string
helper-Y: use bpf_strncmp() to compare Y-sized string

Under x86-64:

no-helper-1          3.504 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-1             3.347 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-8          3.357 ± 0.001M/s (drops 0.000 ± 0.000M/s)
helper-8             3.307 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-32         3.064 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-32            3.253 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-64         2.563 ± 0.001M/s (drops 0.000 ± 0.000M/s)
helper-64            3.040 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-128        1.975 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-128           2.641 ± 0.000M/s (drops 0.000 ± 0.000M/s)

no-helper-512        0.759 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-512           1.574 ± 0.000M/s (drops 0.000 ± 0.000M/s)

no-helper-2048       0.329 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-2048          0.602 ± 0.000M/s (drops 0.000 ± 0.000M/s)

no-helper-4095       0.117 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-4095          0.327 ± 0.000M/s (drops 0.000 ± 0.000M/s)

Under arm64:

no-helper-1          2.806 ± 0.004M/s (drops 0.000 ± 0.000M/s)
helper-1             2.819 ± 0.002M/s (drops 0.000 ± 0.000M/s)

no-helper-8          2.797 ± 0.109M/s (drops 0.000 ± 0.000M/s)
helper-8             2.786 ± 0.025M/s (drops 0.000 ± 0.000M/s)

no-helper-32         2.399 ± 0.011M/s (drops 0.000 ± 0.000M/s)
helper-32            2.703 ± 0.002M/s (drops 0.000 ± 0.000M/s)

no-helper-64         2.020 ± 0.015M/s (drops 0.000 ± 0.000M/s)
helper-64            2.702 ± 0.073M/s (drops 0.000 ± 0.000M/s)

no-helper-128        1.604 ± 0.001M/s (drops 0.000 ± 0.000M/s)
helper-128           2.516 ± 0.002M/s (drops 0.000 ± 0.000M/s)

no-helper-512        0.699 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-512           2.106 ± 0.003M/s (drops 0.000 ± 0.000M/s)

no-helper-2048       0.215 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-2048          1.223 ± 0.003M/s (drops 0.000 ± 0.000M/s)

no-helper-4095       0.112 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-4095          0.796 ± 0.000M/s (drops 0.000 ± 0.000M/s)

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211210141652.877186-4-houtao1@huawei.com

2 files changed, 173 insertions, 0 deletions

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/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