Merge branch 'introduce bpf_strncmp() helper'

Hou Tao says:

====================

Hi,

The motivation for introducing bpf_strncmp() helper comes from
two aspects:

(1) clang doesn't always replace strncmp() automatically
In tracing program, sometimes we need to using a home-made
strncmp() to check whether or not the file name is expected.

(2) the performance of home-made strncmp is not so good
As shown in the benchmark in patch #4, the performance of
bpf_strncmp() helper is 18% or 33% better than home-made strncmp()
under x86-64 or arm64 when the compared string length is 64. When
the string length grows to 4095, the performance win will be
179% or 600% under x86-64 or arm64.

Any comments are welcome.
Regards,
Tao

Change Log:
v2:
 * rebased on bpf-next
 * drop patch "selftests/bpf: factor out common helpers for benchmarks"
   (suggested by Andrii)
 * remove unnecessary inline functions and add comments for programs which
   will be rejected by verifier in patch 4 (suggested by Andrii)
 * rename variables used in will-fail programs to clarify the purposes.

v1: https://lore.kernel.org/bpf/20211130142215.1237217-1-houtao1@huawei.com
 * change API to bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
 * add benchmark refactor and benchmark between bpf_strncmp() and strncmp()

RFC: https://lore.kernel.org/bpf/20211106132822.1396621-1-houtao1@huawei.com/
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

16 files changed, 526 insertions, 34 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0ceb54c6342f..7a40022e3d00 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2163,6 +2163,7 @@ extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
 extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
 extern const struct bpf_func_proto bpf_find_vma_proto;
 extern const struct bpf_func_proto bpf_loop_proto;
+extern const struct bpf_func_proto bpf_strncmp_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c26871263f1f..2820c77e4846 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4983,6 +4983,16 @@ union bpf_attr {
  *	Return
  *		The number of loops performed, **-EINVAL** for invalid **flags**,
  *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ *	Description
+ *		Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ *		to be null-terminated and **s1_sz** is the maximum storage
+ *		size of **s1**. **s2** must be a read-only string.
+ *	Return
+ *		An integer less than, equal to, or greater than zero
+ *		if the first **s1_sz** bytes of **s1** is found to be
+ *		less than, to match, or be greater than **s2**.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5167,6 +5177,7 @@ union bpf_attr {
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
 	FN(loop),			\
+	FN(strncmp),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 19fecfeaa9c2..8babae03d30a 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -565,6 +565,20 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 };
 #endif
 
+BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
+{
+	return strncmp(s1, s2, s1_sz);
+}
+
+const struct bpf_func_proto bpf_strncmp_proto = {
+	.func		= bpf_strncmp,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_CONST_STR,
+};
+
 BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
 	   struct bpf_pidns_info *, nsdata, u32, size)
 {
@@ -1378,6 +1392,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_for_each_map_elem_proto;
 	case BPF_FUNC_loop:
 		return &bpf_loop_proto;
+	case BPF_FUNC_strncmp:
+		return &bpf_strncmp_proto;
 	default:
 		break;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c26871263f1f..2820c77e4846 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4983,6 +4983,16 @@ union bpf_attr {
  *	Return
  *		The number of loops performed, **-EINVAL** for invalid **flags**,
  *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ *	Description
+ *		Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ *		to be null-terminated and **s1_sz** is the maximum storage
+ *		size of **s1**. **s2** must be a read-only string.
+ *	Return
+ *		An integer less than, equal to, or greater than zero
+ *		if the first **s1_sz** bytes of **s1** is found to be
+ *		less than, to match, or be greater than **s2**.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5167,6 +5177,7 @@ union bpf_attr {
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
 	FN(loop),			\
+	FN(strncmp),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a795bca4c8ec..43f6f3159431 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -537,6 +537,7 @@ $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
 			    $(OUTPUT)/perfbuf_bench.skel.h
 $(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h
 $(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h
+$(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -547,7 +548,8 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_trigger.o \
 		 $(OUTPUT)/bench_ringbufs.o \
 		 $(OUTPUT)/bench_bloom_filter_map.o \
-		 $(OUTPUT)/bench_bpf_loop.o
+		 $(OUTPUT)/bench_bpf_loop.o \
+		 $(OUTPUT)/bench_strncmp.o
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 3d6082b97a56..bbb42e2cee0c 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -39,7 +39,7 @@ static int bump_memlock_rlimit(void)
 	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
 }
 
-void setup_libbpf()
+void setup_libbpf(void)
 {
 	int err;
 
@@ -205,11 +205,13 @@ static const struct argp_option opts[] = {
 extern struct argp bench_ringbufs_argp;
 extern struct argp bench_bloom_map_argp;
 extern struct argp bench_bpf_loop_argp;
+extern struct argp bench_strncmp_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
 	{ &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 },
 	{ &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 },
+	{ &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 },
 	{},
 };
 
@@ -409,6 +411,8 @@ extern const struct bench bench_bloom_false_positive;
 extern const struct bench bench_hashmap_without_bloom;
 extern const struct bench bench_hashmap_with_bloom;
 extern const struct bench bench_bpf_loop;
+extern const struct bench bench_strncmp_no_helper;
+extern const struct bench bench_strncmp_helper;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -441,6 +445,8 @@ static const struct bench *benchs[] = {
 	&bench_hashmap_without_bloom,
 	&bench_hashmap_with_bloom,
 	&bench_bpf_loop,
+	&bench_strncmp_no_helper,
+	&bench_strncmp_helper,
 };
 
 static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index 50785503756b..fb3e213df3dc 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -38,8 +38,8 @@ struct bench_res {
 
 struct bench {
 	const char *name;
-	void (*validate)();
-	void (*setup)();
+	void (*validate)(void);
+	void (*setup)(void);
 	void *(*producer_thread)(void *ctx);
 	void *(*consumer_thread)(void *ctx);
 	void (*measure)(struct bench_res* res);
@@ -54,7 +54,7 @@ struct counter {
 extern struct env env;
 extern const struct bench *bench;
 
-void setup_libbpf();
+void setup_libbpf(void);
 void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
 void hits_drops_report_final(struct bench_res res[], int res_cnt);
 void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns);
@@ -62,7 +62,8 @@ void false_hits_report_final(struct bench_res res[], int res_cnt);
 void ops_report_progress(int iter, struct bench_res *res, long delta_ns);
 void ops_report_final(struct bench_res res[], int res_cnt);
 
-static inline __u64 get_time_ns() {
+static inline __u64 get_time_ns(void)
+{
 	struct timespec t;
 
 	clock_gettime(CLOCK_MONOTONIC, &t);
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 52d4a2f91dbd..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;
 
@@ -390,7 +390,7 @@ 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;
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 049a5ad56f65..7f957c55a3ca 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -11,7 +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");
@@ -45,7 +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();
 
@@ -67,37 +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);
@@ -183,22 +183,22 @@ static void usetup(bool use_retprobe, bool use_nop)
 	ctx.skel->links.bench_trigger_uprobe = link;
 }
 
-static void uprobe_setup_with_nop()
+static void uprobe_setup_with_nop(void)
 {
 	usetup(false, true);
 }
 
-static void uretprobe_setup_with_nop()
+static void uretprobe_setup_with_nop(void)
 {
 	usetup(true, true);
 }
 
-static void uprobe_setup_without_nop()
+static void uprobe_setup_without_nop(void)
 {
 	usetup(false, false);
 }
 
-static void uretprobe_setup_without_nop()
+static void uretprobe_setup_without_nop(void)
 {
 	usetup(true, false);
 }
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/prog_tests/test_strncmp.c b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
new file mode 100644
index 000000000000..b57a3009465f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+#include "strncmp_test.skel.h"
+
+static int trigger_strncmp(const struct strncmp_test *skel)
+{
+	int cmp;
+
+	usleep(1);
+
+	cmp = skel->bss->cmp_ret;
+	if (cmp > 0)
+		return 1;
+	if (cmp < 0)
+		return -1;
+	return 0;
+}
+
+/*
+ * Compare str and target after making str[i] != target[i].
+ * When exp is -1, make str[i] < target[i] and delta = -1.
+ */
+static void strncmp_full_str_cmp(struct strncmp_test *skel, const char *name,
+				 int exp)
+{
+	size_t nr = sizeof(skel->bss->str);
+	char *str = skel->bss->str;
+	int delta = exp;
+	int got;
+	size_t i;
+
+	memcpy(str, skel->rodata->target, nr);
+	for (i = 0; i < nr - 1; i++) {
+		str[i] += delta;
+
+		got = trigger_strncmp(skel);
+		ASSERT_EQ(got, exp, name);
+
+		str[i] -= delta;
+	}
+}
+
+static void test_strncmp_ret(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err, got;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.do_strncmp, true);
+
+	err = strncmp_test__load(skel);
+	if (!ASSERT_EQ(err, 0, "strncmp_test load"))
+		goto out;
+
+	err = strncmp_test__attach(skel);
+	if (!ASSERT_EQ(err, 0, "strncmp_test attach"))
+		goto out;
+
+	skel->bss->target_pid = getpid();
+
+	/* Empty str */
+	skel->bss->str[0] = '\0';
+	got = trigger_strncmp(skel);
+	ASSERT_EQ(got, -1, "strncmp: empty str");
+
+	/* Same string */
+	memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
+	got = trigger_strncmp(skel);
+	ASSERT_EQ(got, 0, "strncmp: same str");
+
+	/* Not-null-termainted string  */
+	memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
+	skel->bss->str[sizeof(skel->bss->str) - 1] = 'A';
+	got = trigger_strncmp(skel);
+	ASSERT_EQ(got, 1, "strncmp: not-null-term str");
+
+	strncmp_full_str_cmp(skel, "strncmp: less than", -1);
+	strncmp_full_str_cmp(skel, "strncmp: greater than", 1);
+out:
+	strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_not_const_str_size(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.strncmp_bad_not_const_str_size,
+				  true);
+
+	err = strncmp_test__load(skel);
+	ASSERT_ERR(err, "strncmp_test load bad_not_const_str_size");
+
+	strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_writable_target(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.strncmp_bad_writable_target,
+				  true);
+
+	err = strncmp_test__load(skel);
+	ASSERT_ERR(err, "strncmp_test load bad_writable_target");
+
+	strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_not_null_term_target(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.strncmp_bad_not_null_term_target,
+				  true);
+
+	err = strncmp_test__load(skel);
+	ASSERT_ERR(err, "strncmp_test load bad_not_null_term_target");
+
+	strncmp_test__destroy(skel);
+}
+
+void test_test_strncmp(void)
+{
+	if (test__start_subtest("strncmp_ret"))
+		test_strncmp_ret();
+	if (test__start_subtest("strncmp_bad_not_const_str_size"))
+		test_strncmp_bad_not_const_str_size();
+	if (test__start_subtest("strncmp_bad_writable_target"))
+		test_strncmp_bad_writable_target();
+	if (test__start_subtest("strncmp_bad_not_null_term_target"))
+		test_strncmp_bad_not_null_term_target();
+}
diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c
new file mode 100644
index 000000000000..18373a7df76e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 4096
+
+/* Will be updated by benchmark before program loading */
+const volatile unsigned int cmp_str_len = 1;
+const char target[STRNCMP_STR_SZ];
+
+long hits = 0;
+char str[STRNCMP_STR_SZ];
+
+char _license[] SEC("license") = "GPL";
+
+static __always_inline int local_strncmp(const char *s1, unsigned int sz,
+					 const char *s2)
+{
+	int ret = 0;
+	unsigned int i;
+
+	for (i = 0; i < sz; i++) {
+		/* E.g. 0xff > 0x31 */
+		ret = (unsigned char)s1[i] - (unsigned char)s2[i];
+		if (ret || !s1[i])
+			break;
+	}
+
+	return ret;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_no_helper(void *ctx)
+{
+	if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_helper(void *ctx)
+{
+	if (bpf_strncmp(str, cmp_str_len + 1, target) < 0)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/progs/strncmp_test.c b/tools/testing/selftests/bpf/progs/strncmp_test.c
new file mode 100644
index 000000000000..900d930d48a8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strncmp_test.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 8
+
+const char target[STRNCMP_STR_SZ] = "EEEEEEE";
+char str[STRNCMP_STR_SZ];
+int cmp_ret = 0;
+int target_pid = 0;
+
+const char no_str_target[STRNCMP_STR_SZ] = "12345678";
+char writable_target[STRNCMP_STR_SZ];
+unsigned int no_const_str_size = STRNCMP_STR_SZ;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int do_strncmp(void *ctx)
+{
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, target);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_not_const_str_size(void *ctx)
+{
+	/* The value of string size is not const, so will fail */
+	cmp_ret = bpf_strncmp(str, no_const_str_size, target);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_writable_target(void *ctx)
+{
+	/* Compared target is not read-only, so will fail */
+	cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, writable_target);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_not_null_term_target(void *ctx)
+{
+	/* Compared target is not null-terminated, so will fail */
+	cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, no_str_target);
+	return 0;
+}