[PATCH bpf-next 4/4] selftests/bpf: Add bpf_for() benchmark

[Puranjay Mohan <puranjay@kernel.org>]

The bpf_for() macro builds on the numeric open-coded iterator kfuncs
bpf_iter_num_{new,next,destroy}(). Add a benchmark, modelled on the
existing bpf_loop benchmark, that repeatedly runs a bpf_for() loop so the
per-iteration cost of the iterator can be measured, e.g. to quantify the
effect of inlining the iterator kfuncs in the verifier.

The BPF program runs an inner bpf_for(i, 0, nr_loops) loop with an empty
body 1000 times per trigger and accounts nr_loops hits per outer
iteration, mirroring bench_bpf_loop so the two are directly comparable.

nr_loops defaults to 1000 so that the per-iteration bpf_iter_num_next()
cost, rather than the one-time bpf_iter_num_new()/destroy() setup and
teardown, dominates the reported numbers:

  $ ./bench -p 1 --nr_loops 1000 bpf-for

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
---
 tools/testing/selftests/bpf/Makefile          |   2 +
 tools/testing/selftests/bpf/bench.c           |   4 +
 .../selftests/bpf/benchs/bench_bpf_for.c      | 105 ++++++++++++++++++
 .../selftests/bpf/benchs/run_bench_bpf_for.sh |  15 +++
 .../selftests/bpf/progs/bpf_for_bench.c       |  32 ++++++
 5 files changed, 158 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/benchs/bench_bpf_for.c
 create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_bpf_for.sh
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_for_bench.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index b642ee489ea64..00b6ff636e3c1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -967,6 +967,7 @@ $(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_bpf_for.o: $(OUTPUT)/bpf_for_bench.skel.h
 $(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
 $(OUTPUT)/bench_bpf_hashmap_full_update.o: $(OUTPUT)/bpf_hashmap_full_update_bench.skel.h
 $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h
@@ -992,6 +993,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_ringbufs.o \
 		 $(OUTPUT)/bench_bloom_filter_map.o \
 		 $(OUTPUT)/bench_bpf_loop.o \
+		 $(OUTPUT)/bench_bpf_for.o \
 		 $(OUTPUT)/bench_strncmp.o \
 		 $(OUTPUT)/bench_bpf_hashmap_full_update.o \
 		 $(OUTPUT)/bench_local_storage.o \
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 3d9d2cd7764bd..b86b73456d3ca 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -276,6 +276,7 @@ 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_bpf_for_argp;
 extern struct argp bench_local_storage_argp;
 extern struct argp bench_local_storage_rcu_tasks_trace_argp;
 extern struct argp bench_strncmp_argp;
@@ -292,6 +293,7 @@ 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_bpf_for_argp, 0, "bpf_for loop benchmark", 0 },
 	{ &bench_local_storage_argp, 0, "local_storage benchmark", 0 },
 	{ &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 },
 	{ &bench_local_storage_rcu_tasks_trace_argp, 0,
@@ -557,6 +559,7 @@ 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_bpf_for;
 extern const struct bench bench_strncmp_no_helper;
 extern const struct bench bench_strncmp_helper;
 extern const struct bench bench_bpf_hashmap_full_update;
@@ -640,6 +643,7 @@ static const struct bench *benchs[] = {
 	&bench_hashmap_without_bloom,
 	&bench_hashmap_with_bloom,
 	&bench_bpf_loop,
+	&bench_bpf_for,
 	&bench_strncmp_no_helper,
 	&bench_strncmp_helper,
 	&bench_bpf_hashmap_full_update,
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_for.c b/tools/testing/selftests/bpf/benchs/bench_bpf_for.c
new file mode 100644
index 0000000000000..789f8bfe25b9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_for.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <argp.h>
+#include "bench.h"
+#include "bpf_for_bench.skel.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+	struct bpf_for_bench *skel;
+} ctx;
+
+static struct {
+	__u32 nr_loops;
+} args = {
+	/*
+	 * Default to a large loop count so the per-iteration
+	 * bpf_iter_num_next() cost dominates the one-time
+	 * bpf_iter_num_new()/destroy() setup and teardown.
+	 */
+	.nr_loops = 1000,
+};
+
+enum {
+	ARG_NR_LOOPS = 4000,
+};
+
+static const struct argp_option opts[] = {
+	{ "nr_loops", ARG_NR_LOOPS, "nr_loops", 0,
+		"Set number of iterations for the bpf_for() loop"},
+	{},
+};
+
+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_for_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
+		exit(1);
+	}
+}
+
+static void *producer(void *input)
+{
+	while (true)
+		/* trigger the bpf program */
+		syscall(__NR_getpgid);
+
+	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_for_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_for = {
+	.name = "bpf-for",
+	.argp = &bench_bpf_for_argp,
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.measure = measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_for.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_for.sh
new file mode 100755
index 0000000000000..7da6453920dab
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_for.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: $t"
+	summarize_ops "bpf_for: " \
+	    "$($RUN_BENCH -p $t --nr_loops $i bpf-for)"
+	printf "\n"
+done
+done
diff --git a/tools/testing/selftests/bpf/progs/bpf_for_bench.c b/tools/testing/selftests/bpf/progs/bpf_for_bench.c
new file mode 100644
index 0000000000000..920f8f188e864
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_for_bench.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+u32 nr_loops;
+long hits;
+
+static int outer_loop(__u32 index, void *data)
+{
+	int i;
+
+	/*
+	 * Empty body: the work being measured is the open-coded numeric
+	 * iterator itself (bpf_iter_num_new/next/destroy behind bpf_for()).
+	 */
+	bpf_for(i, 0, nr_loops)
+		;
+	__sync_add_and_fetch(&hits, nr_loops);
+	return 0;
+}
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int benchmark(void *ctx)
+{
+	bpf_loop(1000, outer_loop, NULL, 0);
+	return 0;
+}
-- 
2.53.0-Meta